diff --git a/alembic/env.py b/alembic/env.py
index 2cf7e6c8..ff14698b 100644
--- a/alembic/env.py
+++ b/alembic/env.py
@@ -1,4 +1,3 @@
-import logging
 from datetime import datetime
 from logging.config import fileConfig
 
@@ -7,7 +6,7 @@
 from sqlalchemy import pool
 
 from src.db.helpers.connect import get_postgres_connection_string
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
diff --git a/alembic/versions/2025_07_31_1536-99eceed6e614_add_web_status_info_table.py b/alembic/versions/2025_07_31_1536-99eceed6e614_add_web_status_info_table.py
new file mode 100644
index 00000000..891bef3a
--- /dev/null
+++ b/alembic/versions/2025_07_31_1536-99eceed6e614_add_web_status_info_table.py
@@ -0,0 +1,156 @@
+"""Add HTML Status Info table
+
+Revision ID: 99eceed6e614
+Revises: 637de6eaa3ab
+Create Date: 2025-07-31 15:36:40.966605
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+from src.util.alembic_helpers import id_column, created_at_column, updated_at_column, url_id_column, switch_enum_type
+
+# revision identifiers, used by Alembic.
+revision: str = '99eceed6e614'
+down_revision: Union[str, None] = '637de6eaa3ab'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+WEB_STATUS_ENUM = sa.Enum(
+    "not_attempted",
+    "success",
+    "error",
+    "404_not_found",
+    name="web_status"
+)
+SCRAPE_STATUS_ENUM = sa.Enum(
+    "success",
+    "error",
+    name="scrape_status",
+)
+
+URL_WEB_METADATA_TABLE_NAME = 'url_web_metadata'
+URL_SCRAPE_INFO = 'url_scrape_info'
+
+
+
+
+
+def upgrade() -> None:
+    _create_url_html_info_table()
+    _add_url_probe_task_type_enum()
+    _set_up_scrape_info_table()
+    _use_existing_html_data_to_add_scrape_info()
+
+def _use_existing_html_data_to_add_scrape_info():
+    op.execute(
+        f"""
+        INSERT INTO {URL_SCRAPE_INFO} (url_id, status)
+        SELECT url_id, 'success'::scrape_status
+        FROM url_compressed_html
+        """
+    )
+    op.execute(
+        f"""
+        INSERT INTO {URL_SCRAPE_INFO} (url_id, status)
+        SELECT distinct(url_id), 'success'::scrape_status
+        FROM url_html_content
+        LEFT JOIN URL_COMPRESSED_HTML USING (url_id)
+        WHERE URL_COMPRESSED_HTML.url_id IS NULL
+        """
+    )
+
+def downgrade() -> None:
+    _drop_scrape_info_table()
+    # Drop Enums
+    WEB_STATUS_ENUM.drop(op.get_bind(), checkfirst=True)
+    _drop_url_probe_task_type_enum()
+    _tear_down_scrape_info_table()
+
+
+def _set_up_scrape_info_table():
+    op.create_table(
+        URL_SCRAPE_INFO,
+        id_column(),
+        url_id_column(),
+        sa.Column(
+            'status',
+            SCRAPE_STATUS_ENUM,
+            nullable=False,
+            comment='The status of the most recent scrape attempt.'
+        ),
+        created_at_column(),
+        updated_at_column(),
+        sa.UniqueConstraint('url_id', name='uq_url_scrape_info_url_id')
+    )
+
+
+
+
+def _tear_down_scrape_info_table():
+    op.drop_table(URL_SCRAPE_INFO)
+    # Drop enum
+    SCRAPE_STATUS_ENUM.drop(op.get_bind(), checkfirst=True)
+
+
+def _add_url_probe_task_type_enum() -> None:
+    switch_enum_type(
+        table_name='tasks',
+        column_name='task_type',
+        enum_name='task_type',
+        new_enum_values=[
+            'HTML',
+            'Relevancy',
+            'Record Type',
+            'Agency Identification',
+            'Misc Metadata',
+            'Submit Approved URLs',
+            'Duplicate Detection',
+            '404 Probe',
+            'Sync Agencies',
+            'Sync Data Sources',
+            'Push to Hugging Face',
+            'URL Probe'
+        ]
+    )
+
+def _drop_url_probe_task_type_enum() -> None:
+    switch_enum_type(
+        table_name='tasks',
+        column_name='task_type',
+        enum_name='task_type',
+        new_enum_values=[
+            'HTML',
+            'Relevancy',
+            'Record Type',
+            'Agency Identification',
+            'Misc Metadata',
+            'Submit Approved URLs',
+            'Duplicate Detection',
+            '404 Probe',
+            'Sync Agencies',
+            'Sync Data Sources',
+            'Push to Hugging Face'
+        ]
+    )
+
+def _create_url_html_info_table() -> None:
+    op.create_table(
+        URL_WEB_METADATA_TABLE_NAME,
+        id_column(),
+        url_id_column(),
+        sa.Column('accessed', sa.Boolean(), nullable=False),
+        sa.Column('status_code', sa.Integer(), nullable=True),
+        sa.Column('content_type', sa.Text(), nullable=True),
+        sa.Column('error_message', sa.Text(), nullable=True),
+        created_at_column(),
+        updated_at_column(),
+        sa.UniqueConstraint('url_id', name='uq_url_web_status_info_url_id'),
+        sa.CheckConstraint('status_code >= 100', name='ck_url_web_status_info_status_code_min'),
+        sa.CheckConstraint('status_code <= 999', name='ck_url_web_status_info_status_code_max'),
+    )
+
+def _drop_scrape_info_table() -> None:
+    op.drop_table(URL_WEB_METADATA_TABLE_NAME)
diff --git a/local_database/classes/DockerClient.py b/local_database/classes/DockerClient.py
index ca9d535b..5c33e7d9 100644
--- a/local_database/classes/DockerClient.py
+++ b/local_database/classes/DockerClient.py
@@ -1,5 +1,7 @@
 import docker
 from docker.errors import NotFound, APIError
+from docker.models.containers import Container
+from docker.models.networks import Network
 
 from local_database.DTOs import DockerfileInfo, DockerInfo
 
@@ -9,7 +11,7 @@ class DockerClient:
     def __init__(self):
         self.client = docker.from_env()
 
-    def run_command(self, command: str, container_id: str):
+    def run_command(self, command: str, container_id: str) -> None:
         exec_id = self.client.api.exec_create(
             container_id,
             cmd=command,
@@ -20,7 +22,7 @@ def run_command(self, command: str, container_id: str):
         for line in output_stream:
             print(line.decode().rstrip())
 
-    def start_network(self, network_name):
+    def start_network(self, network_name) -> Network:
         try:
             self.client.networks.create(network_name, driver="bridge")
         except APIError as e:
@@ -30,14 +32,14 @@ def start_network(self, network_name):
             print("Network already exists")
         return self.client.networks.get(network_name)
 
-    def stop_network(self, network_name):
+    def stop_network(self, network_name) -> None:
         self.client.networks.get(network_name).remove()
 
     def get_image(
             self,
             dockerfile_info: DockerfileInfo,
             force_rebuild: bool = False
-    ):
+    ) -> None:
         if dockerfile_info.dockerfile_directory:
             # Build image from Dockerfile
             self.client.images.build(
@@ -58,7 +60,7 @@ def get_image(
         except NotFound:
             self.client.images.pull(dockerfile_info.image_tag)
 
-    def get_existing_container(self, docker_info_name: str):
+    def get_existing_container(self, docker_info_name: str) -> Container | None:
         try:
             return self.client.containers.get(docker_info_name)
         except NotFound:
diff --git a/local_database/classes/DockerContainer.py b/local_database/classes/DockerContainer.py
index 33b71ce0..0a86e601 100644
--- a/local_database/classes/DockerContainer.py
+++ b/local_database/classes/DockerContainer.py
@@ -11,19 +11,19 @@ def __init__(self, dc: DockerClient, container: Container):
         self.dc = dc
         self.container = container
 
-    def run_command(self, command: str):
+    def run_command(self, command: str) -> None:
         self.dc.run_command(command, self.container.id)
 
-    def stop(self):
+    def stop(self) -> None:
         self.container.stop()
 
-    def log_to_file(self):
+    def log_to_file(self) -> None:
         logs = self.container.logs(stdout=True, stderr=True)
         container_name = self.container.name
         with open(f"{container_name}.log", "wb") as f:
             f.write(logs)
 
-    def wait_for_pg_to_be_ready(self):
+    def wait_for_pg_to_be_ready(self) -> None:
         for i in range(30):
             exit_code, output = self.container.exec_run("pg_isready")
             print(output)
diff --git a/local_database/classes/DockerManager.py b/local_database/classes/DockerManager.py
index ac294dc1..fc32c3bc 100644
--- a/local_database/classes/DockerManager.py
+++ b/local_database/classes/DockerManager.py
@@ -4,6 +4,8 @@
 
 import docker
 from docker.errors import APIError
+from docker.models.containers import Container
+from docker.models.networks import Network
 
 from local_database.DTOs import DockerfileInfo, DockerInfo
 from local_database.classes.DockerClient import DockerClient
@@ -20,7 +22,7 @@ def __init__(self):
         self.network = self.start_network()
 
     @staticmethod
-    def start_docker_engine():
+    def start_docker_engine() -> None:
         system = platform.system()
 
         match system:
@@ -41,7 +43,7 @@ def start_docker_engine():
                 sys.exit(1)
 
     @staticmethod
-    def is_docker_running():
+    def is_docker_running() -> bool:
         try:
             client = docker.from_env()
             client.ping()
@@ -50,16 +52,23 @@ def is_docker_running():
             print(f"Docker is not running: {e}")
             return False
 
-    def run_command(self, command: str, container_id: str):
+    def run_command(
+        self,
+        command: str,
+        container_id: str
+    ) -> None:
         self.client.run_command(command, container_id)
 
-    def start_network(self):
+    def start_network(self) -> Network:
         return self.client.start_network(self.network_name)
 
-    def stop_network(self):
+    def stop_network(self) -> None:
         self.client.stop_network(self.network_name)
 
-    def get_image(self, dockerfile_info: DockerfileInfo):
+    def get_image(
+        self,
+        dockerfile_info: DockerfileInfo
+    ) -> None:
         self.client.get_image(dockerfile_info)
 
     def run_container(
@@ -74,5 +83,5 @@ def run_container(
         )
         return DockerContainer(self.client, raw_container)
 
-    def get_containers(self):
+    def get_containers(self) -> list[Container]:
         return self.client.client.containers.list()
\ No newline at end of file
diff --git a/local_database/classes/TimestampChecker.py b/local_database/classes/TimestampChecker.py
index 56779fd4..fc2c25a0 100644
--- a/local_database/classes/TimestampChecker.py
+++ b/local_database/classes/TimestampChecker.py
@@ -1,27 +1,26 @@
-import datetime
 import os
-from typing import Optional
+from datetime import datetime, timedelta
 
 
 class TimestampChecker:
     def __init__(self):
-        self.last_run_time: Optional[datetime.datetime] = self.load_last_run_time()
+        self.last_run_time: datetime | None = self.load_last_run_time()
 
-    def load_last_run_time(self) -> Optional[datetime.datetime]:
+    def load_last_run_time(self) -> datetime | None:
         # Check if file `last_run.txt` exists
         # If it does, load the last run time
         if os.path.exists("local_state/last_run.txt"):
             with open("local_state/last_run.txt", "r") as f:
-                return datetime.datetime.strptime(
+                return datetime.strptime(
                     f.read(),
                     "%Y-%m-%d %H:%M:%S"
                 )
         return None
 
-    def last_run_within_24_hours(self):
+    def last_run_within_24_hours(self) -> bool:
         if self.last_run_time is None:
             return False
-        return datetime.datetime.now() - self.last_run_time < datetime.timedelta(days=1)
+        return datetime.now() - self.last_run_time < timedelta(days=1)
 
     def set_last_run_time(self):
         # If directory `local_state` doesn't exist, create it
@@ -29,4 +28,4 @@ def set_last_run_time(self):
             os.makedirs("local_state")
 
         with open("local_state/last_run.txt", "w") as f:
-            f.write(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+            f.write(datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
diff --git a/local_database/create_database.py b/local_database/create_database.py
index 67eae70b..e18cbd2a 100644
--- a/local_database/create_database.py
+++ b/local_database/create_database.py
@@ -15,7 +15,7 @@
 
 
 # Connect to the default 'postgres' database to create other databases
-def connect(database="postgres", autocommit=True):
+def connect(database="postgres", autocommit=True) -> psycopg2.extensions.connection:
     conn = psycopg2.connect(
         dbname=database,
         user=POSTGRES_USER,
@@ -27,7 +27,7 @@ def connect(database="postgres", autocommit=True):
         conn.set_isolation_level(psycopg2.extensions.ISOLATION_LEVEL_AUTOCOMMIT)
     return conn
 
-def create_database(db_name):
+def create_database(db_name: str) -> None:
     conn = connect("postgres")
     with conn.cursor() as cur:
         cur.execute(sql.SQL("""
@@ -48,7 +48,7 @@ def create_database(db_name):
         except Exception as e:
             print(f"❌ Failed to create {db_name}: {e}")
 
-def main():
+def main() -> None:
     print("Creating databases...")
     create_database(LOCAL_SOURCE_COLLECTOR_DB_NAME)
 
diff --git a/local_database/setup.py b/local_database/setup.py
index 99ff1da9..64f5af48 100644
--- a/local_database/setup.py
+++ b/local_database/setup.py
@@ -7,14 +7,19 @@
 MAX_RETRIES = 20
 SLEEP_SECONDS = 1
 
-def run_command(cmd, check=True, capture_output=False, **kwargs):
+def run_command(
+    cmd: str,
+    check: bool = True,
+    capture_output: bool = False,
+    **kwargs: dict
+) -> subprocess.CompletedProcess:
     try:
         return subprocess.run(cmd, shell=True, check=check, capture_output=capture_output, text=True, **kwargs)
     except subprocess.CalledProcessError as e:
         print(f"Command '{cmd}' failed: {e}")
         sys.exit(1)
 
-def get_postgres_container_id():
+def get_postgres_container_id() -> str:
     result = run_command(f"docker-compose ps -q {POSTGRES_SERVICE_NAME}", capture_output=True)
     container_id = result.stdout.strip()
     if not container_id:
@@ -22,7 +27,7 @@ def get_postgres_container_id():
         sys.exit(1)
     return container_id
 
-def wait_for_postgres(container_id):
+def wait_for_postgres(container_id: str) -> None:
     print("Waiting for Postgres to be ready...")
     for i in range(MAX_RETRIES):
         try:
@@ -36,7 +41,7 @@ def wait_for_postgres(container_id):
     print("Postgres did not become ready in time.")
     sys.exit(1)
 
-def main():
+def main() -> None:
     print("Stopping Docker Compose...")
     run_command("docker-compose down")
 
diff --git a/src/api/endpoints/annotate/agency/get/queries/next_for_annotation.py b/src/api/endpoints/annotate/agency/get/queries/next_for_annotation.py
index 27f7a382..66a5e3fb 100644
--- a/src/api/endpoints/annotate/agency/get/queries/next_for_annotation.py
+++ b/src/api/endpoints/annotate/agency/get/queries/next_for_annotation.py
@@ -7,7 +7,7 @@
 from src.api.endpoints.annotate.agency.get.queries.agency_suggestion import GetAgencySuggestionsQueryBuilder
 from src.collectors.enums import URLStatus
 from src.core.enums import SuggestedStatus
-from src.core.tasks.url.operators.url_html.scraper.parser.util import convert_to_response_html_info
+from src.core.tasks.url.operators.html.scraper.parser.util import convert_to_response_html_info
 from src.db.dtos.url.mapping import URLMapping
 from src.db.models.instantiations.link.batch_url import LinkBatchURL
 from src.db.models.instantiations.link.url_agency.sqlalchemy import LinkURLAgency
diff --git a/src/api/endpoints/annotate/dtos/shared/base/response.py b/src/api/endpoints/annotate/dtos/shared/base/response.py
index a7e30385..1e9fc5fa 100644
--- a/src/api/endpoints/annotate/dtos/shared/base/response.py
+++ b/src/api/endpoints/annotate/dtos/shared/base/response.py
@@ -3,7 +3,7 @@
 from pydantic import BaseModel, Field
 
 from src.api.endpoints.annotate.dtos.shared.batch import AnnotationBatchInfo
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
 from src.db.dtos.url.mapping import URLMapping
 
 
diff --git a/src/api/endpoints/batch/urls/dto.py b/src/api/endpoints/batch/urls/dto.py
index 13e8659c..90f9b209 100644
--- a/src/api/endpoints/batch/urls/dto.py
+++ b/src/api/endpoints/batch/urls/dto.py
@@ -1,6 +1,6 @@
 from pydantic import BaseModel
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class GetURLsByBatchResponse(BaseModel):
diff --git a/src/api/endpoints/batch/urls/query.py b/src/api/endpoints/batch/urls/query.py
index 49b95e13..980b4c81 100644
--- a/src/api/endpoints/batch/urls/query.py
+++ b/src/api/endpoints/batch/urls/query.py
@@ -1,8 +1,8 @@
 from sqlalchemy import Select
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.db.models.instantiations.link.batch_url import LinkBatchURL
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.queries.base.builder import QueryBuilderBase
 
diff --git a/src/api/endpoints/review/next/dto.py b/src/api/endpoints/review/next/dto.py
index 7fc53b17..a9c378b9 100644
--- a/src/api/endpoints/review/next/dto.py
+++ b/src/api/endpoints/review/next/dto.py
@@ -5,7 +5,7 @@
 from src.api.endpoints.annotate.agency.get.dto import GetNextURLForAgencyAgencyInfo
 from src.api.endpoints.annotate.relevance.get.dto import RelevanceAnnotationResponseInfo
 from src.core.enums import RecordType, SuggestedStatus
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
 
 
 class FinalReviewAnnotationRelevantInfo(BaseModel):
diff --git a/src/api/endpoints/review/next/query.py b/src/api/endpoints/review/next/query.py
index 0ec83dc1..d89aa4da 100644
--- a/src/api/endpoints/review/next/query.py
+++ b/src/api/endpoints/review/next/query.py
@@ -7,7 +7,7 @@
 from src.api.endpoints.review.next.dto import FinalReviewOptionalMetadata, FinalReviewBatchInfo, \
     GetNextURLForFinalReviewOuterResponse, GetNextURLForFinalReviewResponse, FinalReviewAnnotationInfo
 from src.collectors.enums import URLStatus
-from src.core.tasks.url.operators.url_html.scraper.parser.util import convert_to_response_html_info
+from src.core.tasks.url.operators.html.scraper.parser.util import convert_to_response_html_info
 from src.db.constants import USER_ANNOTATION_MODELS
 from src.db.dto_converter import DTOConverter
 from src.db.dtos.url.html_content import URLHTMLContentInfo
diff --git a/src/api/endpoints/task/by_id/dto.py b/src/api/endpoints/task/by_id/dto.py
index 9213aa90..eba6cece 100644
--- a/src/api/endpoints/task/by_id/dto.py
+++ b/src/api/endpoints/task/by_id/dto.py
@@ -3,8 +3,8 @@
 
 from pydantic import BaseModel
 
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.db.enums import TaskType
 from src.core.enums import BatchStatus
 
diff --git a/src/api/endpoints/task/by_id/query.py b/src/api/endpoints/task/by_id/query.py
index 8133085f..c2b32234 100644
--- a/src/api/endpoints/task/by_id/query.py
+++ b/src/api/endpoints/task/by_id/query.py
@@ -5,7 +5,7 @@
 from src.api.endpoints.task.by_id.dto import TaskInfo
 from src.collectors.enums import URLStatus
 from src.core.enums import BatchStatus
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
 from src.db.enums import TaskType
 from src.db.models.instantiations.task.core import Task
diff --git a/src/api/main.py b/src/api/main.py
index 46ae4a3a..e9916724 100644
--- a/src/api/main.py
+++ b/src/api/main.py
@@ -26,11 +26,11 @@
 from src.core.tasks.scheduled.manager import AsyncScheduledTaskManager
 from src.core.tasks.url.loader import URLTaskOperatorLoader
 from src.core.tasks.url.manager import TaskManager
-from src.core.tasks.url.operators.url_html.scraper.parser.core import HTMLResponseParser
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
+from src.core.tasks.url.operators.html.scraper.parser.core import HTMLResponseParser
+from src.external.url_request.core import URLRequestInterface
 from src.db.client.async_ import AsyncDatabaseClient
 from src.db.client.sync import DatabaseClient
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.core import RootURLCache
+from src.core.tasks.url.operators.html.scraper.root_url_cache.core import RootURLCache
 from src.external.huggingface.hub.client import HuggingFaceHubClient
 from src.external.huggingface.inference.client import HuggingFaceInferenceClient
 from src.external.pdap.client import PDAPClient
diff --git a/src/core/preprocessors/autogoogler.py b/src/core/preprocessors/autogoogler.py
index 460cf0e0..b41eba76 100644
--- a/src/core/preprocessors/autogoogler.py
+++ b/src/core/preprocessors/autogoogler.py
@@ -1,7 +1,7 @@
 from typing import List
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.core.preprocessors.base import PreprocessorBase
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class AutoGooglerPreprocessor(PreprocessorBase):
diff --git a/src/core/preprocessors/base.py b/src/core/preprocessors/base.py
index beb31cb7..2f777d5f 100644
--- a/src/core/preprocessors/base.py
+++ b/src/core/preprocessors/base.py
@@ -2,7 +2,7 @@
 from abc import ABC
 from typing import List
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class PreprocessorBase(ABC):
diff --git a/src/core/preprocessors/ckan.py b/src/core/preprocessors/ckan.py
index b72ee3c9..0b1cef2e 100644
--- a/src/core/preprocessors/ckan.py
+++ b/src/core/preprocessors/ckan.py
@@ -1,7 +1,7 @@
 from datetime import datetime
 from typing import List
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class CKANPreprocessor:
diff --git a/src/core/preprocessors/common_crawler.py b/src/core/preprocessors/common_crawler.py
index 16f5d730..d2f0d988 100644
--- a/src/core/preprocessors/common_crawler.py
+++ b/src/core/preprocessors/common_crawler.py
@@ -1,7 +1,7 @@
 from typing import List
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.core.preprocessors.base import PreprocessorBase
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class CommonCrawlerPreprocessor(PreprocessorBase):
diff --git a/src/core/preprocessors/example.py b/src/core/preprocessors/example.py
index 691d23c6..580b739e 100644
--- a/src/core/preprocessors/example.py
+++ b/src/core/preprocessors/example.py
@@ -1,8 +1,8 @@
 from typing import List
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.collectors.source_collectors.example.dtos.output import ExampleOutputDTO
 from src.core.preprocessors.base import PreprocessorBase
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class ExamplePreprocessor(PreprocessorBase):
diff --git a/src/core/preprocessors/muckrock.py b/src/core/preprocessors/muckrock.py
index b42a198f..b0f1d9bc 100644
--- a/src/core/preprocessors/muckrock.py
+++ b/src/core/preprocessors/muckrock.py
@@ -1,7 +1,7 @@
 from typing import List
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.core.preprocessors.base import PreprocessorBase
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 class MuckrockPreprocessor(PreprocessorBase):
diff --git a/src/core/tasks/scheduled/huggingface/queries/check/requester.py b/src/core/tasks/scheduled/huggingface/queries/check/requester.py
index 6af94560..33a79043 100644
--- a/src/core/tasks/scheduled/huggingface/queries/check/requester.py
+++ b/src/core/tasks/scheduled/huggingface/queries/check/requester.py
@@ -7,7 +7,7 @@
 from src.collectors.enums import URLStatus
 from src.db.helpers.session import session_helper as sh
 from src.db.models.instantiations.state.huggingface import HuggingFaceUploadState
-from src.db.models.instantiations.url.compressed_html import URLCompressedHTML
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 
 
diff --git a/src/core/tasks/scheduled/huggingface/queries/get/core.py b/src/core/tasks/scheduled/huggingface/queries/get/core.py
index 7deea322..906f4d4f 100644
--- a/src/core/tasks/scheduled/huggingface/queries/get/core.py
+++ b/src/core/tasks/scheduled/huggingface/queries/get/core.py
@@ -1,5 +1,3 @@
-from typing import Any
-
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
@@ -7,7 +5,7 @@
 from src.core.tasks.scheduled.huggingface.queries.get.convert import convert_url_status_to_relevant, \
     convert_fine_to_coarse_record_type
 from src.core.tasks.scheduled.huggingface.queries.get.model import GetForLoadingToHuggingFaceOutput
-from src.db.models.instantiations.url.compressed_html import URLCompressedHTML
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.queries.base.builder import QueryBuilderBase
 from src.db.utils.compression import decompress_html
diff --git a/src/core/tasks/url/loader.py b/src/core/tasks/url/loader.py
index 50ff8920..59896f94 100644
--- a/src/core/tasks/url/loader.py
+++ b/src/core/tasks/url/loader.py
@@ -7,15 +7,16 @@
 from src.core.tasks.url.operators.agency_identification.subtasks.loader import AgencyIdentificationSubtaskLoader
 from src.core.tasks.url.operators.auto_relevant.core import URLAutoRelevantTaskOperator
 from src.core.tasks.url.operators.base import URLTaskOperatorBase
+from src.core.tasks.url.operators.probe.core import URLProbeTaskOperator
+from src.core.tasks.url.operators.probe_404.core import URL404ProbeTaskOperator
 from src.core.tasks.url.operators.record_type.core import URLRecordTypeTaskOperator
 from src.core.tasks.url.operators.record_type.llm_api.record_classifier.openai import OpenAIRecordClassifier
-from src.core.tasks.url.operators.submit_approved_url.core import SubmitApprovedURLTaskOperator
-from src.core.tasks.url.operators.url_404_probe.core import URL404ProbeTaskOperator
-from src.core.tasks.url.operators.url_duplicate.core import URLDuplicateTaskOperator
-from src.core.tasks.url.operators.url_html.core import URLHTMLTaskOperator
-from src.core.tasks.url.operators.url_html.scraper.parser.core import HTMLResponseParser
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
-from src.core.tasks.url.operators.url_miscellaneous_metadata.core import URLMiscellaneousMetadataTaskOperator
+from src.core.tasks.url.operators.submit_approved.core import SubmitApprovedURLTaskOperator
+from src.core.tasks.url.operators.duplicate.core import URLDuplicateTaskOperator
+from src.core.tasks.url.operators.html.core import URLHTMLTaskOperator
+from src.core.tasks.url.operators.html.scraper.parser.core import HTMLResponseParser
+from src.external.url_request.core import URLRequestInterface
+from src.core.tasks.url.operators.misc_metadata.core import URLMiscellaneousMetadataTaskOperator
 from src.db.client.async_ import AsyncDatabaseClient
 from src.external.huggingface.inference.client import HuggingFaceInferenceClient
 from src.external.pdap.client import PDAPClient
@@ -101,8 +102,16 @@ async def get_url_auto_relevance_task_operator(self):
         )
         return operator
 
+    async def get_url_probe_task_operator(self):
+        operator = URLProbeTaskOperator(
+            adb_client=self.adb_client,
+            url_request_interface=self.url_request_interface
+        )
+        return operator
+
     async def get_task_operators(self) -> list[URLTaskOperatorBase]:
         return [
+            await self.get_url_probe_task_operator(),
             await self.get_url_html_task_operator(),
             await self.get_url_duplicate_task_operator(),
             await self.get_url_404_probe_task_operator(),
diff --git a/src/core/tasks/url/operators/agency_identification/dtos/suggestion.py b/src/core/tasks/url/operators/agency_identification/dtos/suggestion.py
index f42ecfc2..39f2cab3 100644
--- a/src/core/tasks/url/operators/agency_identification/dtos/suggestion.py
+++ b/src/core/tasks/url/operators/agency_identification/dtos/suggestion.py
@@ -8,9 +8,9 @@
 class URLAgencySuggestionInfo(BaseModel):
     url_id: int
     suggestion_type: SuggestionType = SuggestionType.UNKNOWN
-    pdap_agency_id: Optional[int] = None
-    agency_name: Optional[str] = None
-    state: Optional[str] = None
-    county: Optional[str] = None
-    locality: Optional[str] = None
-    user_id: Optional[int] = None
+    pdap_agency_id: int | None = None
+    agency_name: str | None = None
+    state: str | None = None
+    county: str | None = None
+    locality: str | None = None
+    user_id: int | None = None
diff --git a/src/core/tasks/url/operators/auto_relevant/queries/get_tdos.py b/src/core/tasks/url/operators/auto_relevant/queries/get_tdos.py
index 78e4c983..2ec72836 100644
--- a/src/core/tasks/url/operators/auto_relevant/queries/get_tdos.py
+++ b/src/core/tasks/url/operators/auto_relevant/queries/get_tdos.py
@@ -6,7 +6,7 @@
 
 from src.collectors.enums import URLStatus
 from src.core.tasks.url.operators.auto_relevant.models.tdo import URLRelevantTDO
-from src.db.models.instantiations.url.compressed_html import URLCompressedHTML
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.models.instantiations.url.suggestion.relevant.auto.sqlalchemy import AutoRelevantSuggestion
 from src.db.queries.base.builder import QueryBuilderBase
diff --git a/src/core/tasks/url/operators/submit_approved_url/__init__.py b/src/core/tasks/url/operators/duplicate/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/submit_approved_url/__init__.py
rename to src/core/tasks/url/operators/duplicate/__init__.py
diff --git a/src/core/tasks/url/operators/url_duplicate/core.py b/src/core/tasks/url/operators/duplicate/core.py
similarity index 95%
rename from src/core/tasks/url/operators/url_duplicate/core.py
rename to src/core/tasks/url/operators/duplicate/core.py
index ed3d00a5..dba0147c 100644
--- a/src/core/tasks/url/operators/url_duplicate/core.py
+++ b/src/core/tasks/url/operators/duplicate/core.py
@@ -4,7 +4,7 @@
 
 from src.db.client.async_ import AsyncDatabaseClient
 from src.db.enums import TaskType
-from src.core.tasks.url.operators.url_duplicate.tdo import URLDuplicateTDO
+from src.core.tasks.url.operators.duplicate.tdo import URLDuplicateTDO
 from src.core.tasks.url.operators.base import URLTaskOperatorBase
 from src.external.pdap.client import PDAPClient
 
diff --git a/src/core/tasks/url/operators/url_duplicate/tdo.py b/src/core/tasks/url/operators/duplicate/tdo.py
similarity index 100%
rename from src/core/tasks/url/operators/url_duplicate/tdo.py
rename to src/core/tasks/url/operators/duplicate/tdo.py
diff --git a/src/core/tasks/url/operators/submit_approved_url/queries/__init__.py b/src/core/tasks/url/operators/html/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/submit_approved_url/queries/__init__.py
rename to src/core/tasks/url/operators/html/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/content_info_getter.py b/src/core/tasks/url/operators/html/content_info_getter.py
similarity index 78%
rename from src/core/tasks/url/operators/url_html/content_info_getter.py
rename to src/core/tasks/url/operators/html/content_info_getter.py
index 644e12e4..fb7bdd59 100644
--- a/src/core/tasks/url/operators/url_html/content_info_getter.py
+++ b/src/core/tasks/url/operators/html/content_info_getter.py
@@ -1,5 +1,6 @@
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
-from src.db.dtos.url.html_content import URLHTMLContentInfo, HTMLContentType
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.db.dtos.url.html_content import URLHTMLContentInfo
+from src.db.models.instantiations.url.html.content.enums import HTMLContentType
 
 
 class HTMLContentInfoGetter:
diff --git a/src/core/tasks/url/operators/html/core.py b/src/core/tasks/url/operators/html/core.py
new file mode 100644
index 00000000..00c1d1c3
--- /dev/null
+++ b/src/core/tasks/url/operators/html/core.py
@@ -0,0 +1,84 @@
+from src.core.tasks.url.operators.base import URLTaskOperatorBase
+from src.core.tasks.url.operators.html.filter import filter_just_urls, filter_404_subset
+from src.core.tasks.url.operators.html.queries.insert.query import InsertURLHTMLInfoQueryBuilder
+from src.core.tasks.url.operators.html.scraper.parser.core import HTMLResponseParser
+from src.core.tasks.url.operators.html.tdo import UrlHtmlTDO
+from src.db.client.async_ import AsyncDatabaseClient
+from src.db.enums import TaskType
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
+from src.external.url_request.core import URLRequestInterface
+
+
+class URLHTMLTaskOperator(URLTaskOperatorBase):
+
+    def __init__(
+            self,
+            url_request_interface: URLRequestInterface,
+            adb_client: AsyncDatabaseClient,
+            html_parser: HTMLResponseParser
+    ):
+        super().__init__(adb_client)
+        self.url_request_interface = url_request_interface
+        self.html_parser = html_parser
+
+    @property
+    def task_type(self) -> TaskType:
+        return TaskType.HTML
+
+    async def meets_task_prerequisites(self) -> bool:
+        return await self.adb_client.has_non_errored_urls_without_html_data()
+
+    async def inner_task_logic(self) -> None:
+        tdos = await self._get_non_errored_urls_without_html_data()
+        url_ids = [task_info.url_info.id for task_info in tdos]
+        await self.link_urls_to_task(url_ids=url_ids)
+
+        await self._get_raw_html_data_for_urls(tdos)
+        await self._process_html_data(tdos)
+
+        tdos_404 = await filter_404_subset(tdos)
+        await self._update_404s_in_database(tdos_404)
+        await self._update_html_data_in_database(tdos)
+
+
+    async def _get_non_errored_urls_without_html_data(self) -> list[UrlHtmlTDO]:
+        pending_urls: list[URLInfo] = await self.adb_client.get_non_errored_urls_without_html_data()
+        tdos = [
+            UrlHtmlTDO(
+                url_info=url_info,
+            ) for url_info in pending_urls
+        ]
+        return tdos
+
+    async def _get_raw_html_data_for_urls(self, tdos: list[UrlHtmlTDO]) -> None:
+        just_urls = await filter_just_urls(tdos)
+        url_response_infos = await self.url_request_interface.make_requests_with_html(just_urls)
+        for tdto, url_response_info in zip(tdos, url_response_infos):
+            tdto.url_response_info = url_response_info
+
+    async def _update_404s_in_database(self, tdos_404: list[UrlHtmlTDO]) -> None:
+        url_ids = [tdo.url_info.id for tdo in tdos_404]
+        await self.adb_client.mark_all_as_404(url_ids)
+
+
+    async def _process_html_data(self, tdos: list[UrlHtmlTDO]) -> None:
+        """
+        Modifies:
+            tdto.html_tag_info
+        """
+        for tdto in tdos:
+            if not tdto.url_response_info.success:
+                continue
+            html_tag_info = await self.html_parser.parse(
+                url=tdto.url_info.url,
+                html_content=tdto.url_response_info.html,
+                content_type=tdto.url_response_info.content_type
+            )
+            tdto.html_tag_info = html_tag_info
+
+    async def _update_html_data_in_database(self, tdos: list[UrlHtmlTDO]) -> None:
+        await self.adb_client.run_query_builder(
+            InsertURLHTMLInfoQueryBuilder(tdos, task_id=self.task_id)
+        )
+
+
diff --git a/src/core/tasks/url/operators/html/filter.py b/src/core/tasks/url/operators/html/filter.py
new file mode 100644
index 00000000..86da0e8a
--- /dev/null
+++ b/src/core/tasks/url/operators/html/filter.py
@@ -0,0 +1,13 @@
+from http import HTTPStatus
+
+from src.core.tasks.url.operators.html.tdo import UrlHtmlTDO
+
+
+async def filter_just_urls(tdos: list[UrlHtmlTDO]):
+    return [task_info.url_info.url for task_info in tdos]
+
+async def filter_404_subset(tdos: list[UrlHtmlTDO]) -> list[UrlHtmlTDO]:
+    return [
+        tdo for tdo in tdos
+        if tdo.url_response_info.status == HTTPStatus.NOT_FOUND
+    ]
diff --git a/src/core/tasks/url/operators/url_404_probe/__init__.py b/src/core/tasks/url/operators/html/models/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_404_probe/__init__.py
rename to src/core/tasks/url/operators/html/models/__init__.py
diff --git a/src/core/tasks/url/operators/url_duplicate/__init__.py b/src/core/tasks/url/operators/html/models/subsets/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_duplicate/__init__.py
rename to src/core/tasks/url/operators/html/models/subsets/__init__.py
diff --git a/src/core/tasks/url/operators/html/models/subsets/error_404.py b/src/core/tasks/url/operators/html/models/subsets/error_404.py
new file mode 100644
index 00000000..f526368c
--- /dev/null
+++ b/src/core/tasks/url/operators/html/models/subsets/error_404.py
@@ -0,0 +1,8 @@
+from pydantic import BaseModel
+
+from src.core.tasks.url.operators.html.tdo import UrlHtmlTDO
+
+
+class ErrorSubsets(BaseModel):
+    is_404: list[UrlHtmlTDO]
+    not_404: list[UrlHtmlTDO]
\ No newline at end of file
diff --git a/src/core/tasks/url/operators/html/models/subsets/success_error.py b/src/core/tasks/url/operators/html/models/subsets/success_error.py
new file mode 100644
index 00000000..75429a6e
--- /dev/null
+++ b/src/core/tasks/url/operators/html/models/subsets/success_error.py
@@ -0,0 +1,8 @@
+from pydantic import BaseModel
+
+from src.core.tasks.url.operators.html.tdo import UrlHtmlTDO
+
+
+class SuccessErrorSubset(BaseModel):
+    success: list[UrlHtmlTDO]
+    error: list[UrlHtmlTDO]
\ No newline at end of file
diff --git a/src/core/tasks/url/operators/url_html/__init__.py b/src/core/tasks/url/operators/html/queries/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/__init__.py
rename to src/core/tasks/url/operators/html/queries/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/queries/get_pending_urls_without_html_data.py b/src/core/tasks/url/operators/html/queries/get.py
similarity index 87%
rename from src/core/tasks/url/operators/url_html/queries/get_pending_urls_without_html_data.py
rename to src/core/tasks/url/operators/html/queries/get.py
index ff7f7c10..d09f8bca 100644
--- a/src/core/tasks/url/operators/url_html/queries/get_pending_urls_without_html_data.py
+++ b/src/core/tasks/url/operators/html/queries/get.py
@@ -1,6 +1,6 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.queries.base.builder import QueryBuilderBase
 from src.db.statement_composer import StatementComposer
@@ -9,7 +9,7 @@
 class GetPendingURLsWithoutHTMLDataQueryBuilder(QueryBuilderBase):
 
     async def run(self, session: AsyncSession) -> list[URLInfo]:
-        statement = StatementComposer.pending_urls_without_html_data()
+        statement = StatementComposer.has_non_errored_urls_without_html_data()
         statement = statement.limit(100).order_by(URL.id)
         scalar_result = await session.scalars(statement)
         url_results: list[URL] = scalar_result.all()
diff --git a/src/core/tasks/url/operators/url_html/queries/__init__.py b/src/core/tasks/url/operators/html/queries/insert/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/queries/__init__.py
rename to src/core/tasks/url/operators/html/queries/insert/__init__.py
diff --git a/src/core/tasks/url/operators/html/queries/insert/convert.py b/src/core/tasks/url/operators/html/queries/insert/convert.py
new file mode 100644
index 00000000..9c9906d8
--- /dev/null
+++ b/src/core/tasks/url/operators/html/queries/insert/convert.py
@@ -0,0 +1,73 @@
+from http import HTTPStatus
+
+from src.core.tasks.url.operators.html.content_info_getter import HTMLContentInfoGetter
+from src.core.tasks.url.operators.html.tdo import UrlHtmlTDO
+from src.db.dtos.url.html_content import URLHTMLContentInfo
+from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
+from src.db.models.instantiations.url.html.compressed.pydantic import URLCompressedHTMLPydantic
+from src.db.models.instantiations.url.scrape_info.enums import ScrapeStatus
+from src.db.models.instantiations.url.scrape_info.pydantic import URLScrapeInfoInsertModel
+from src.db.utils.compression import compress_html
+from src.external.url_request.dtos.url_response import URLResponseInfo
+
+
+def convert_to_compressed_html(tdos: list[UrlHtmlTDO]) -> list[URLCompressedHTMLPydantic]:
+    models = []
+    for tdo in tdos:
+        if tdo.url_response_info.status != HTTPStatus.OK:
+            continue
+        model = URLCompressedHTMLPydantic(
+            url_id=tdo.url_info.id,
+            compressed_html=compress_html(tdo.url_response_info.html)
+        )
+        models.append(model)
+    return models
+
+
+
+def _convert_to_html_content_info_getter(tdo: UrlHtmlTDO) -> HTMLContentInfoGetter:
+    return HTMLContentInfoGetter(
+        response_html_info=tdo.html_tag_info,
+        url_id=tdo.url_info.id
+    )
+
+def convert_to_html_content_info_list(tdos: list[UrlHtmlTDO]) -> list[URLHTMLContentInfo]:
+    html_content_infos = []
+    for tdo in tdos:
+        if tdo.url_response_info.status != HTTPStatus.OK:
+            continue
+        hcig = _convert_to_html_content_info_getter(tdo)
+        results = hcig.get_all_html_content()
+        html_content_infos.extend(results)
+    return html_content_infos
+
+def get_scrape_status(response_info: URLResponseInfo) -> ScrapeStatus:
+    if response_info.success:
+        return ScrapeStatus.SUCCESS
+    return ScrapeStatus.ERROR
+
+def convert_to_scrape_infos(tdos: list[UrlHtmlTDO]) -> list[URLScrapeInfoInsertModel]:
+    models = []
+    for tdo in tdos:
+        model = URLScrapeInfoInsertModel(
+            url_id=tdo.url_info.id,
+            status=get_scrape_status(tdo.url_response_info)
+        )
+        models.append(model)
+    return models
+
+def convert_to_url_errors(
+    tdos: list[UrlHtmlTDO],
+    task_id: int
+) -> list[URLErrorPydanticInfo]:
+    models = []
+    for tdo in tdos:
+        if tdo.url_response_info.success:
+            continue
+        model = URLErrorPydanticInfo(
+            url_id=tdo.url_info.id,
+            error=tdo.url_response_info.exception,
+            task_id=task_id
+        )
+        models.append(model)
+    return models
\ No newline at end of file
diff --git a/src/core/tasks/url/operators/html/queries/insert/query.py b/src/core/tasks/url/operators/html/queries/insert/query.py
new file mode 100644
index 00000000..e0bff2e6
--- /dev/null
+++ b/src/core/tasks/url/operators/html/queries/insert/query.py
@@ -0,0 +1,30 @@
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from src.core.tasks.url.operators.html.queries.insert.convert import convert_to_compressed_html, \
+    convert_to_html_content_info_list, convert_to_scrape_infos, convert_to_url_errors
+from src.core.tasks.url.operators.html.tdo import UrlHtmlTDO
+from src.db.queries.base.builder import QueryBuilderBase
+from src.db.helpers.session import session_helper as sh
+
+class InsertURLHTMLInfoQueryBuilder(QueryBuilderBase):
+
+    def __init__(self, tdos: list[UrlHtmlTDO], task_id: int):
+        super().__init__()
+        self.tdos = tdos
+        self.task_id = task_id
+
+    async def run(self, session: AsyncSession) -> None:
+        compressed_html_models = convert_to_compressed_html(self.tdos)
+        url_html_content_list = convert_to_html_content_info_list(self.tdos)
+        scrape_info_list = convert_to_scrape_infos(self.tdos)
+        url_errors = convert_to_url_errors(self.tdos, task_id=self.task_id)
+
+        for models in [
+            compressed_html_models,
+            url_html_content_list,
+            scrape_info_list,
+            url_errors
+        ]:
+            await sh.bulk_insert(session, models=models)
+
+
diff --git a/src/core/tasks/url/operators/url_html/scraper/README.md b/src/core/tasks/url/operators/html/scraper/README.md
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/README.md
rename to src/core/tasks/url/operators/html/scraper/README.md
diff --git a/src/core/tasks/url/operators/url_html/scraper/__init__.py b/src/core/tasks/url/operators/html/scraper/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/__init__.py
rename to src/core/tasks/url/operators/html/scraper/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/README.md b/src/core/tasks/url/operators/html/scraper/parser/README.md
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/parser/README.md
rename to src/core/tasks/url/operators/html/scraper/parser/README.md
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/__init__.py b/src/core/tasks/url/operators/html/scraper/parser/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/parser/__init__.py
rename to src/core/tasks/url/operators/html/scraper/parser/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/constants.py b/src/core/tasks/url/operators/html/scraper/parser/constants.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/parser/constants.py
rename to src/core/tasks/url/operators/html/scraper/parser/constants.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/core.py b/src/core/tasks/url/operators/html/scraper/parser/core.py
similarity index 89%
rename from src/core/tasks/url/operators/url_html/scraper/parser/core.py
rename to src/core/tasks/url/operators/html/scraper/parser/core.py
index 737f03dd..a212b951 100644
--- a/src/core/tasks/url/operators/url_html/scraper/parser/core.py
+++ b/src/core/tasks/url/operators/html/scraper/parser/core.py
@@ -3,11 +3,11 @@
 
 from bs4 import BeautifulSoup
 
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
-from src.core.tasks.url.operators.url_html.scraper.parser.enums import ParserTypeEnum
-from src.core.tasks.url.operators.url_html.scraper.parser.constants import HEADER_TAGS
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.core import RootURLCache
-from src.core.tasks.url.operators.url_html.scraper.parser.util import remove_excess_whitespace, add_https, remove_trailing_backslash, \
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.core.tasks.url.operators.html.scraper.parser.enums import ParserTypeEnum
+from src.core.tasks.url.operators.html.scraper.parser.constants import HEADER_TAGS
+from src.core.tasks.url.operators.html.scraper.root_url_cache.core import RootURLCache
+from src.core.tasks.url.operators.html.scraper.parser.util import remove_excess_whitespace, add_https, remove_trailing_backslash, \
     drop_hostname
 
 
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/dtos/__init__.py b/src/core/tasks/url/operators/html/scraper/parser/dtos/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/parser/dtos/__init__.py
rename to src/core/tasks/url/operators/html/scraper/parser/dtos/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/dtos/response_html.py b/src/core/tasks/url/operators/html/scraper/parser/dtos/response_html.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/parser/dtos/response_html.py
rename to src/core/tasks/url/operators/html/scraper/parser/dtos/response_html.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/enums.py b/src/core/tasks/url/operators/html/scraper/parser/enums.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/parser/enums.py
rename to src/core/tasks/url/operators/html/scraper/parser/enums.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/mapping.py b/src/core/tasks/url/operators/html/scraper/parser/mapping.py
similarity index 80%
rename from src/core/tasks/url/operators/url_html/scraper/parser/mapping.py
rename to src/core/tasks/url/operators/html/scraper/parser/mapping.py
index 6b5f0b83..641af779 100644
--- a/src/core/tasks/url/operators/url_html/scraper/parser/mapping.py
+++ b/src/core/tasks/url/operators/html/scraper/parser/mapping.py
@@ -1,4 +1,4 @@
-from src.db.dtos.url.html_content import HTMLContentType
+from src.db.models.instantiations.url.html.content.enums import HTMLContentType
 
 ENUM_TO_ATTRIBUTE_MAPPING = {
     HTMLContentType.TITLE: "title",
diff --git a/src/core/tasks/url/operators/url_html/scraper/parser/util.py b/src/core/tasks/url/operators/html/scraper/parser/util.py
similarity index 84%
rename from src/core/tasks/url/operators/url_html/scraper/parser/util.py
rename to src/core/tasks/url/operators/html/scraper/parser/util.py
index 09453984..a4ea2d1b 100644
--- a/src/core/tasks/url/operators/url_html/scraper/parser/util.py
+++ b/src/core/tasks/url/operators/html/scraper/parser/util.py
@@ -1,8 +1,8 @@
 from urllib.parse import urlparse
 
 from src.db.dtos.url.html_content import URLHTMLContentInfo
-from src.core.tasks.url.operators.url_html.scraper.parser.mapping import ENUM_TO_ATTRIBUTE_MAPPING
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.core.tasks.url.operators.html.scraper.parser.mapping import ENUM_TO_ATTRIBUTE_MAPPING
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
 
 
 def convert_to_response_html_info(html_content_infos: list[URLHTMLContentInfo]):
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/__init__.py b/src/core/tasks/url/operators/html/scraper/root_url_cache/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/request_interface/__init__.py
rename to src/core/tasks/url/operators/html/scraper/root_url_cache/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/root_url_cache/constants.py b/src/core/tasks/url/operators/html/scraper/root_url_cache/constants.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/root_url_cache/constants.py
rename to src/core/tasks/url/operators/html/scraper/root_url_cache/constants.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/root_url_cache/core.py b/src/core/tasks/url/operators/html/scraper/root_url_cache/core.py
similarity index 92%
rename from src/core/tasks/url/operators/url_html/scraper/root_url_cache/core.py
rename to src/core/tasks/url/operators/html/scraper/root_url_cache/core.py
index c30bc16e..284ad678 100644
--- a/src/core/tasks/url/operators/url_html/scraper/root_url_cache/core.py
+++ b/src/core/tasks/url/operators/html/scraper/root_url_cache/core.py
@@ -5,8 +5,8 @@
 from bs4 import BeautifulSoup
 
 from src.db.client.async_ import AsyncDatabaseClient
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.constants import REQUEST_HEADERS
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.dtos.response import RootURLCacheResponseInfo
+from src.core.tasks.url.operators.html.scraper.root_url_cache.constants import REQUEST_HEADERS
+from src.core.tasks.url.operators.html.scraper.root_url_cache.dtos.response import RootURLCacheResponseInfo
 
 DEBUG = False
 
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/__init__.py b/src/core/tasks/url/operators/html/scraper/root_url_cache/dtos/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/__init__.py
rename to src/core/tasks/url/operators/html/scraper/root_url_cache/dtos/__init__.py
diff --git a/src/core/tasks/url/operators/url_html/scraper/root_url_cache/dtos/response.py b/src/core/tasks/url/operators/html/scraper/root_url_cache/dtos/response.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/root_url_cache/dtos/response.py
rename to src/core/tasks/url/operators/html/scraper/root_url_cache/dtos/response.py
diff --git a/src/core/tasks/url/operators/html/tdo.py b/src/core/tasks/url/operators/html/tdo.py
new file mode 100644
index 00000000..6395e363
--- /dev/null
+++ b/src/core/tasks/url/operators/html/tdo.py
@@ -0,0 +1,14 @@
+from typing import Optional
+
+from pydantic import BaseModel
+
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
+from src.external.url_request.dtos.url_response import URLResponseInfo
+
+
+class UrlHtmlTDO(BaseModel):
+    url_info: URLInfo
+    url_response_info: URLResponseInfo | None = None
+    html_tag_info: ResponseHTMLInfo | None = None
+
diff --git a/src/core/tasks/url/operators/url_html/scraper/root_url_cache/__init__.py b/src/core/tasks/url/operators/misc_metadata/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/root_url_cache/__init__.py
rename to src/core/tasks/url/operators/misc_metadata/__init__.py
diff --git a/src/core/tasks/url/operators/url_miscellaneous_metadata/core.py b/src/core/tasks/url/operators/misc_metadata/core.py
similarity index 96%
rename from src/core/tasks/url/operators/url_miscellaneous_metadata/core.py
rename to src/core/tasks/url/operators/misc_metadata/core.py
index 446c32c4..9921846b 100644
--- a/src/core/tasks/url/operators/url_miscellaneous_metadata/core.py
+++ b/src/core/tasks/url/operators/misc_metadata/core.py
@@ -4,7 +4,7 @@
 from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
 from src.db.enums import TaskType
 from src.collectors.enums import CollectorType
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 from src.core.tasks.url.operators.base import URLTaskOperatorBase
 from src.core.tasks.url.subtasks.miscellaneous_metadata.auto_googler import AutoGooglerMiscMetadataSubtask
 from src.core.tasks.url.subtasks.miscellaneous_metadata.ckan import CKANMiscMetadataSubtask
diff --git a/src/core/tasks/url/operators/url_html/scraper/root_url_cache/dtos/__init__.py b/src/core/tasks/url/operators/misc_metadata/queries/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/root_url_cache/dtos/__init__.py
rename to src/core/tasks/url/operators/misc_metadata/queries/__init__.py
diff --git a/src/core/tasks/url/operators/url_miscellaneous_metadata/queries/get_pending_urls_missing_miscellaneous_data.py b/src/core/tasks/url/operators/misc_metadata/queries/get_pending_urls_missing_miscellaneous_data.py
similarity index 89%
rename from src/core/tasks/url/operators/url_miscellaneous_metadata/queries/get_pending_urls_missing_miscellaneous_data.py
rename to src/core/tasks/url/operators/misc_metadata/queries/get_pending_urls_missing_miscellaneous_data.py
index e5add9ce..ed411bd6 100644
--- a/src/core/tasks/url/operators/url_miscellaneous_metadata/queries/get_pending_urls_missing_miscellaneous_data.py
+++ b/src/core/tasks/url/operators/misc_metadata/queries/get_pending_urls_missing_miscellaneous_data.py
@@ -2,8 +2,8 @@
 from sqlalchemy.orm import selectinload
 
 from src.collectors.enums import CollectorType
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO, URLHTMLMetadataInfo
-from src.db.dtos.url.html_content import HTMLContentType
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO, URLHTMLMetadataInfo
+from src.db.models.instantiations.url.html.content.enums import HTMLContentType
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.queries.base.builder import QueryBuilderBase
 from src.db.statement_composer import StatementComposer
diff --git a/src/core/tasks/url/operators/url_miscellaneous_metadata/queries/has_pending_urls_missing_miscellaneous_data.py b/src/core/tasks/url/operators/misc_metadata/queries/has_pending_urls_missing_miscellaneous_data.py
similarity index 100%
rename from src/core/tasks/url/operators/url_miscellaneous_metadata/queries/has_pending_urls_missing_miscellaneous_data.py
rename to src/core/tasks/url/operators/misc_metadata/queries/has_pending_urls_missing_miscellaneous_data.py
diff --git a/src/core/tasks/url/operators/url_miscellaneous_metadata/tdo.py b/src/core/tasks/url/operators/misc_metadata/tdo.py
similarity index 100%
rename from src/core/tasks/url/operators/url_miscellaneous_metadata/tdo.py
rename to src/core/tasks/url/operators/misc_metadata/tdo.py
diff --git a/src/core/tasks/url/operators/url_miscellaneous_metadata/__init__.py b/src/core/tasks/url/operators/probe/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_miscellaneous_metadata/__init__.py
rename to src/core/tasks/url/operators/probe/__init__.py
diff --git a/src/core/tasks/url/operators/probe/core.py b/src/core/tasks/url/operators/probe/core.py
new file mode 100644
index 00000000..98d4f8ab
--- /dev/null
+++ b/src/core/tasks/url/operators/probe/core.py
@@ -0,0 +1,77 @@
+from typing import final
+from typing_extensions import override
+
+from src.core.tasks.url.operators.base import URLTaskOperatorBase
+from src.core.tasks.url.operators.probe.tdo import URLProbeTDO
+from src.db.models.instantiations.url.web_metadata.pydantic import URLWebMetadataPydantic
+from src.external.url_request.core import URLRequestInterface
+from src.db.client.async_ import AsyncDatabaseClient
+from src.db.dtos.url.mapping import URLMapping
+from src.db.enums import TaskType
+
+@final
+class URLProbeTaskOperator(URLTaskOperatorBase):
+
+    def __init__(
+        self,
+        adb_client: AsyncDatabaseClient,
+        url_request_interface: URLRequestInterface
+    ):
+        super().__init__(adb_client=adb_client)
+        self.url_request_interface = url_request_interface
+
+
+    @property
+    @override
+    def task_type(self) -> TaskType:
+        return TaskType.PROBE_URL
+
+    @override
+    async def meets_task_prerequisites(self) -> bool:
+        return await self.adb_client.has_urls_without_probe()
+
+    async def get_urls_without_probe(self) -> list[URLProbeTDO]:
+        url_mappings: list[URLMapping] = await self.adb_client.get_urls_without_probe()
+        return [URLProbeTDO(url_mapping=url_mapping) for url_mapping in url_mappings]
+
+    @override
+    async def inner_task_logic(self) -> None:
+        tdos = await self.get_urls_without_probe()
+        await self.link_urls_to_task(
+            url_ids=[tdo.url_mapping.url_id for tdo in tdos]
+        )
+        await self.probe_urls(tdos)
+        await self.update_database(tdos)
+
+    async def probe_urls(self, tdos: list[URLProbeTDO]) -> None:
+        """Probe URLs and add responses to URLProbeTDO
+
+        Modifies:
+            URLProbeTDO.response
+        """
+        url_to_tdo: dict[str, URLProbeTDO] = {
+            tdo.url_mapping.url: tdo for tdo in tdos
+        }
+        responses = await self.url_request_interface.probe_urls(
+            urls=[tdo.url_mapping.url for tdo in tdos]
+        )
+        # Re-associate the responses with the URL mappings
+        for response in responses:
+            tdo = url_to_tdo[response.url]
+            tdo.response = response
+
+    async def update_database(self, tdos: list[URLProbeTDO]) -> None:
+        web_metadata_objects: list[URLWebMetadataPydantic] = []
+        for tdo in tdos:
+            response = tdo.response
+            web_metadata_object = URLWebMetadataPydantic(
+                url_id=tdo.url_mapping.url_id,
+                accessed=response.status_code is not None,
+                status_code=response.status_code,
+                content_type=response.content_type,
+                error_message=response.error
+            )
+            web_metadata_objects.append(web_metadata_object)
+        await self.adb_client.bulk_insert(web_metadata_objects)
+
+
diff --git a/src/core/tasks/url/operators/url_miscellaneous_metadata/queries/__init__.py b/src/core/tasks/url/operators/probe/queries/__init__.py
similarity index 100%
rename from src/core/tasks/url/operators/url_miscellaneous_metadata/queries/__init__.py
rename to src/core/tasks/url/operators/probe/queries/__init__.py
diff --git a/src/core/tasks/url/operators/probe/queries/get_urls.py b/src/core/tasks/url/operators/probe/queries/get_urls.py
new file mode 100644
index 00000000..9df9191f
--- /dev/null
+++ b/src/core/tasks/url/operators/probe/queries/get_urls.py
@@ -0,0 +1,31 @@
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+from typing_extensions import override, final
+
+from src.db.dtos.url.mapping import URLMapping
+from src.db.models.instantiations.url.core.sqlalchemy import URL
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from src.db.helpers.session import session_helper as sh
+from src.db.queries.base.builder import QueryBuilderBase
+
+
+@final
+class GetURLsWithoutProbeQueryBuilder(QueryBuilderBase):
+
+    @override
+    async def run(self, session: AsyncSession) -> list[URLMapping]:
+        query = (
+            select(
+                URL.id.label("url_id"),
+                URL.url
+            )
+            .outerjoin(
+                URLWebMetadata,
+                URL.id == URLWebMetadata.url_id
+            )
+            .where(
+                URLWebMetadata.id.is_(None)
+            )
+        )
+        db_mappings = await sh.mappings(session, query=query)
+        return [URLMapping(**mapping) for mapping in db_mappings]
\ No newline at end of file
diff --git a/src/core/tasks/url/operators/probe/queries/has_urls.py b/src/core/tasks/url/operators/probe/queries/has_urls.py
new file mode 100644
index 00000000..1ae7835b
--- /dev/null
+++ b/src/core/tasks/url/operators/probe/queries/has_urls.py
@@ -0,0 +1,27 @@
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+from typing_extensions import override, final
+
+from src.db.helpers.session import session_helper as sh
+from src.db.models.instantiations.url.core.sqlalchemy import URL
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from src.db.queries.base.builder import QueryBuilderBase
+
+@final
+class HasURLsWithoutProbeQueryBuilder(QueryBuilderBase):
+
+    @override
+    async def run(self, session: AsyncSession) -> bool:
+        query = (
+            select(
+                URL.id
+            )
+            .outerjoin(
+                URLWebMetadata,
+                URL.id == URLWebMetadata.url_id
+            )
+            .where(
+                URLWebMetadata.id.is_(None)
+            )
+        )
+        return await sh.has_results(session, query=query)
diff --git a/src/core/tasks/url/operators/probe/queries/insert.py b/src/core/tasks/url/operators/probe/queries/insert.py
new file mode 100644
index 00000000..2b312e36
--- /dev/null
+++ b/src/core/tasks/url/operators/probe/queries/insert.py
@@ -0,0 +1,15 @@
+from sqlalchemy.ext.asyncio import AsyncSession
+from typing_extensions import override, final
+
+from src.db.queries.base.builder import QueryBuilderBase
+
+@final
+class InsertURLMetadataInfoQueryBuilder(QueryBuilderBase):
+
+    def __init__(
+        self,
+
+    ):
+
+    @override
+    async def run(self, session: AsyncSession) -> None:
diff --git a/src/core/tasks/url/operators/probe/tdo.py b/src/core/tasks/url/operators/probe/tdo.py
new file mode 100644
index 00000000..8af513c1
--- /dev/null
+++ b/src/core/tasks/url/operators/probe/tdo.py
@@ -0,0 +1,9 @@
+from pydantic import BaseModel
+
+from src.external.url_request.probe.model import URLProbeResponse
+from src.db.dtos.url.mapping import URLMapping
+
+
+class URLProbeTDO(BaseModel):
+    url_mapping: URLMapping
+    response: URLProbeResponse | None = None
diff --git a/api/main.py b/src/core/tasks/url/operators/probe_404/__init__.py
similarity index 100%
rename from api/main.py
rename to src/core/tasks/url/operators/probe_404/__init__.py
diff --git a/src/core/tasks/url/operators/url_404_probe/core.py b/src/core/tasks/url/operators/probe_404/core.py
similarity index 92%
rename from src/core/tasks/url/operators/url_404_probe/core.py
rename to src/core/tasks/url/operators/probe_404/core.py
index 7da96068..6600d17d 100644
--- a/src/core/tasks/url/operators/url_404_probe/core.py
+++ b/src/core/tasks/url/operators/probe_404/core.py
@@ -2,10 +2,10 @@
 
 from pydantic import BaseModel
 
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
+from src.core.tasks.url.operators.probe_404.tdo import URL404ProbeTDO
+from src.external.url_request.core import URLRequestInterface
 from src.db.client.async_ import AsyncDatabaseClient
 from src.db.enums import TaskType
-from src.core.tasks.url.operators.url_404_probe.tdo import URL404ProbeTDO
 from src.core.tasks.url.operators.base import URLTaskOperatorBase
 
 
diff --git a/src/core/tasks/url/operators/url_404_probe/tdo.py b/src/core/tasks/url/operators/probe_404/tdo.py
similarity index 100%
rename from src/core/tasks/url/operators/url_404_probe/tdo.py
rename to src/core/tasks/url/operators/probe_404/tdo.py
diff --git a/src/core/tasks/url/operators/submit_approved/__init__.py b/src/core/tasks/url/operators/submit_approved/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/core/tasks/url/operators/submit_approved_url/core.py b/src/core/tasks/url/operators/submit_approved/core.py
similarity index 96%
rename from src/core/tasks/url/operators/submit_approved_url/core.py
rename to src/core/tasks/url/operators/submit_approved/core.py
index d2e20c3a..e6b1be9f 100644
--- a/src/core/tasks/url/operators/submit_approved_url/core.py
+++ b/src/core/tasks/url/operators/submit_approved/core.py
@@ -1,7 +1,7 @@
 from src.db.client.async_ import AsyncDatabaseClient
 from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
 from src.db.enums import TaskType
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmitApprovedURLTDO
+from src.core.tasks.url.operators.submit_approved.tdo import SubmitApprovedURLTDO
 from src.core.tasks.url.operators.base import URLTaskOperatorBase
 from src.external.pdap.client import PDAPClient
 
diff --git a/src/core/tasks/url/operators/submit_approved/queries/__init__.py b/src/core/tasks/url/operators/submit_approved/queries/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/core/tasks/url/operators/submit_approved_url/queries/get.py b/src/core/tasks/url/operators/submit_approved/queries/get.py
similarity index 96%
rename from src/core/tasks/url/operators/submit_approved_url/queries/get.py
rename to src/core/tasks/url/operators/submit_approved/queries/get.py
index ea40ce79..db128326 100644
--- a/src/core/tasks/url/operators/submit_approved_url/queries/get.py
+++ b/src/core/tasks/url/operators/submit_approved/queries/get.py
@@ -3,7 +3,7 @@
 from sqlalchemy.orm import selectinload
 
 from src.collectors.enums import URLStatus
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmitApprovedURLTDO
+from src.core.tasks.url.operators.submit_approved.tdo import SubmitApprovedURLTDO
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.queries.base.builder import QueryBuilderBase
 from src.db.helpers.session import session_helper as sh
diff --git a/src/core/tasks/url/operators/submit_approved_url/queries/has_validated.py b/src/core/tasks/url/operators/submit_approved/queries/has_validated.py
similarity index 100%
rename from src/core/tasks/url/operators/submit_approved_url/queries/has_validated.py
rename to src/core/tasks/url/operators/submit_approved/queries/has_validated.py
diff --git a/src/core/tasks/url/operators/submit_approved_url/queries/mark_submitted.py b/src/core/tasks/url/operators/submit_approved/queries/mark_submitted.py
similarity index 93%
rename from src/core/tasks/url/operators/submit_approved_url/queries/mark_submitted.py
rename to src/core/tasks/url/operators/submit_approved/queries/mark_submitted.py
index 9c68ec21..347fba11 100644
--- a/src/core/tasks/url/operators/submit_approved_url/queries/mark_submitted.py
+++ b/src/core/tasks/url/operators/submit_approved/queries/mark_submitted.py
@@ -2,7 +2,7 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from src.collectors.enums import URLStatus
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmittedURLInfo
+from src.core.tasks.url.operators.submit_approved.tdo import SubmittedURLInfo
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.models.instantiations.url.data_source.sqlalchemy import URLDataSource
 from src.db.queries.base.builder import QueryBuilderBase
diff --git a/src/core/tasks/url/operators/submit_approved_url/tdo.py b/src/core/tasks/url/operators/submit_approved/tdo.py
similarity index 100%
rename from src/core/tasks/url/operators/submit_approved_url/tdo.py
rename to src/core/tasks/url/operators/submit_approved/tdo.py
diff --git a/src/core/tasks/url/operators/url_html/core.py b/src/core/tasks/url/operators/url_html/core.py
deleted file mode 100644
index 39a09546..00000000
--- a/src/core/tasks/url/operators/url_html/core.py
+++ /dev/null
@@ -1,149 +0,0 @@
-from http import HTTPStatus
-
-from src.db.client.async_ import AsyncDatabaseClient
-from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
-from src.db.models.instantiations.url.core.pydantic import URLInfo
-from src.db.dtos.url.raw_html import RawHTMLInfo
-from src.db.enums import TaskType
-from src.core.tasks.url.operators.url_html.tdo import UrlHtmlTDO
-from src.core.tasks.url.operators.url_html.content_info_getter import HTMLContentInfoGetter
-from src.core.tasks.url.operators.base import URLTaskOperatorBase
-from src.core.tasks.url.operators.url_html.scraper.parser.core import HTMLResponseParser
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
-
-
-class URLHTMLTaskOperator(URLTaskOperatorBase):
-
-    def __init__(
-            self,
-            url_request_interface: URLRequestInterface,
-            adb_client: AsyncDatabaseClient,
-            html_parser: HTMLResponseParser
-    ):
-        super().__init__(adb_client)
-        self.url_request_interface = url_request_interface
-        self.html_parser = html_parser
-
-    @property
-    def task_type(self):
-        return TaskType.HTML
-
-    async def meets_task_prerequisites(self):
-        return await self.adb_client.has_pending_urls_without_html_data()
-
-    async def inner_task_logic(self):
-        tdos = await self.get_pending_urls_without_html_data()
-        url_ids = [task_info.url_info.id for task_info in tdos]
-        await self.link_urls_to_task(url_ids=url_ids)
-        await self.get_raw_html_data_for_urls(tdos)
-        success_subset, error_subset = await self.separate_success_and_error_subsets(tdos)
-        non_404_error_subset, is_404_error_subset = await self.separate_error_and_404_subsets(error_subset)
-        await self.process_html_data(success_subset)
-        await self.update_database(is_404_error_subset, non_404_error_subset, success_subset)
-
-    async def update_database(
-        self,
-        is_404_error_subset: list[UrlHtmlTDO],
-        non_404_error_subset: list[UrlHtmlTDO],
-        success_subset: list[UrlHtmlTDO]
-    ):
-        await self.update_errors_in_database(non_404_error_subset)
-        await self.update_404s_in_database(is_404_error_subset)
-        await self.update_html_data_in_database(success_subset)
-
-    async def get_just_urls(self, tdos: list[UrlHtmlTDO]):
-        return [task_info.url_info.url for task_info in tdos]
-
-    async def get_pending_urls_without_html_data(self):
-        pending_urls: list[URLInfo] = await self.adb_client.get_pending_urls_without_html_data()
-        tdos = [
-            UrlHtmlTDO(
-                url_info=url_info,
-            ) for url_info in pending_urls
-        ]
-        return tdos
-
-    async def get_raw_html_data_for_urls(self, tdos: list[UrlHtmlTDO]):
-        just_urls = await self.get_just_urls(tdos)
-        url_response_infos = await self.url_request_interface.make_requests_with_html(just_urls)
-        for tdto, url_response_info in zip(tdos, url_response_infos):
-            tdto.url_response_info = url_response_info
-
-    async def separate_success_and_error_subsets(
-            self,
-            tdos: list[UrlHtmlTDO]
-    ) -> tuple[
-        list[UrlHtmlTDO], # Successful
-        list[UrlHtmlTDO]  # Error
-    ]:
-        errored_tdos = []
-        successful_tdos = []
-        for tdto in tdos:
-            if not tdto.url_response_info.success:
-                errored_tdos.append(tdto)
-            else:
-                successful_tdos.append(tdto)
-        return successful_tdos, errored_tdos
-
-    async def separate_error_and_404_subsets(
-        self,
-        tdos: list[UrlHtmlTDO]
-    ) -> tuple[
-        list[UrlHtmlTDO], # Error
-        list[UrlHtmlTDO]  # 404
-    ]:
-        tdos_error = []
-        tdos_404 = []
-        for tdo in tdos:
-            if tdo.url_response_info.status is None:
-                tdos_error.append(tdo)
-                continue
-            if tdo.url_response_info.status == HTTPStatus.NOT_FOUND:
-                tdos_404.append(tdo)
-            else:
-                tdos_error.append(tdo)
-        return tdos_error, tdos_404
-
-    async def update_404s_in_database(self, tdos_404: list[UrlHtmlTDO]):
-        url_ids = [tdo.url_info.id for tdo in tdos_404]
-        await self.adb_client.mark_all_as_404(url_ids)
-
-    async def update_errors_in_database(self, error_tdos: list[UrlHtmlTDO]):
-        error_infos = []
-        for error_tdo in error_tdos:
-            error_info = URLErrorPydanticInfo(
-                task_id=self.task_id,
-                url_id=error_tdo.url_info.id,
-                error=str(error_tdo.url_response_info.exception),
-            )
-            error_infos.append(error_info)
-        await self.adb_client.add_url_error_infos(error_infos)
-
-    async def process_html_data(self, tdos: list[UrlHtmlTDO]):
-        for tdto in tdos:
-
-            html_tag_info = await self.html_parser.parse(
-                url=tdto.url_info.url,
-                html_content=tdto.url_response_info.html,
-                content_type=tdto.url_response_info.content_type
-            )
-            tdto.html_tag_info = html_tag_info
-
-    async def update_html_data_in_database(self, tdos: list[UrlHtmlTDO]):
-        html_content_infos = []
-        raw_html_data = []
-        for tdto in tdos:
-            hcig = HTMLContentInfoGetter(
-                response_html_info=tdto.html_tag_info,
-                url_id=tdto.url_info.id
-            )
-            rhi = RawHTMLInfo(
-                url_id=tdto.url_info.id,
-                html=tdto.url_response_info.html
-            )
-            raw_html_data.append(rhi)
-            results = hcig.get_all_html_content()
-            html_content_infos.extend(results)
-
-        await self.adb_client.add_html_content_infos(html_content_infos)
-        await self.adb_client.add_raw_html(raw_html_data)
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/core.py b/src/core/tasks/url/operators/url_html/scraper/request_interface/core.py
deleted file mode 100644
index f45780cb..00000000
--- a/src/core/tasks/url/operators/url_html/scraper/request_interface/core.py
+++ /dev/null
@@ -1,80 +0,0 @@
-from http import HTTPStatus
-from typing import Optional
-
-from aiohttp import ClientSession, ClientResponseError
-from playwright.async_api import async_playwright
-from tqdm.asyncio import tqdm
-
-from src.core.tasks.url.operators.url_html.scraper.request_interface.constants import HTML_CONTENT_TYPE
-from src.core.tasks.url.operators.url_html.scraper.request_interface.dtos.request_resources import RequestResources
-from src.core.tasks.url.operators.url_html.scraper.request_interface.dtos.url_response import URLResponseInfo
-
-
-class URLRequestInterface:
-
-    async def get_response(self, session: ClientSession, url: str) -> URLResponseInfo:
-        try:
-            async with session.get(url, timeout=20) as response:
-                response.raise_for_status()
-                text = await response.text()
-                return URLResponseInfo(
-                    success=True,
-                    html=text,
-                    content_type=response.headers.get("content-type"),
-                    status=HTTPStatus(response.status)
-                )
-        except ClientResponseError as e:
-            return URLResponseInfo(success=False, status=HTTPStatus(e.status), exception=str(e))
-        except Exception as e:
-            print(f"An error occurred while fetching {url}: {e}")
-            return URLResponseInfo(success=False, exception=str(e))
-
-    async def fetch_and_render(self, rr: RequestResources, url: str) -> Optional[URLResponseInfo]:
-        simple_response = await self.get_response(rr.session, url)
-        if not simple_response.success:
-            return simple_response
-
-        if simple_response.content_type != HTML_CONTENT_TYPE:
-            return simple_response
-
-        return await self.get_dynamic_html_content(rr, url)
-
-    async def get_dynamic_html_content(self, rr, url):
-        # For HTML responses, attempt to load the page to check for dynamic html content
-        async with rr.semaphore:
-            page = await rr.browser.new_page()
-            try:
-                await page.goto(url)
-                await page.wait_for_load_state("networkidle")
-                html_content = await page.content()
-                return URLResponseInfo(
-                    success=True,
-                    html=html_content,
-                    content_type=HTML_CONTENT_TYPE,
-                    status=HTTPStatus.OK
-                )
-            except Exception as e:
-                return URLResponseInfo(success=False, exception=str(e))
-            finally:
-                await page.close()
-
-    async def fetch_urls(self, urls: list[str]) -> list[URLResponseInfo]:
-        async with ClientSession() as session:
-            async with async_playwright() as playwright:
-                browser = await playwright.chromium.launch(headless=True)
-                request_resources = RequestResources(session=session, browser=browser)
-                tasks = [self.fetch_and_render(request_resources, url) for url in urls]
-                results = await tqdm.gather(*tasks)
-                return results
-
-    async def make_requests_with_html(
-            self,
-            urls: list[str],
-    ) -> list[URLResponseInfo]:
-        return await self.fetch_urls(urls)
-
-    async def make_simple_requests(self, urls: list[str]) -> list[URLResponseInfo]:
-        async with ClientSession() as session:
-            tasks = [self.get_response(session, url) for url in urls]
-            results = await tqdm.gather(*tasks)
-            return results
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/url_response.py b/src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/url_response.py
deleted file mode 100644
index 8e17c078..00000000
--- a/src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/url_response.py
+++ /dev/null
@@ -1,12 +0,0 @@
-from http import HTTPStatus
-from typing import Optional
-
-from pydantic import BaseModel
-
-
-class URLResponseInfo(BaseModel):
-    success: bool
-    status: Optional[HTTPStatus] = None
-    html: Optional[str] = None
-    content_type: Optional[str] = None
-    exception: Optional[str] = None
diff --git a/src/core/tasks/url/operators/url_html/tdo.py b/src/core/tasks/url/operators/url_html/tdo.py
deleted file mode 100644
index 326412a3..00000000
--- a/src/core/tasks/url/operators/url_html/tdo.py
+++ /dev/null
@@ -1,14 +0,0 @@
-from typing import Optional
-
-from pydantic import BaseModel
-
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
-from src.db.models.instantiations.url.core.pydantic import URLInfo
-from src.core.tasks.url.operators.url_html.scraper.request_interface.dtos.url_response import URLResponseInfo
-
-
-class UrlHtmlTDO(BaseModel):
-    url_info: URLInfo
-    url_response_info: Optional[URLResponseInfo] = None
-    html_tag_info: Optional[ResponseHTMLInfo] = None
-
diff --git a/src/core/tasks/url/subtasks/miscellaneous_metadata/auto_googler.py b/src/core/tasks/url/subtasks/miscellaneous_metadata/auto_googler.py
index 0f183f78..e060d0d3 100644
--- a/src/core/tasks/url/subtasks/miscellaneous_metadata/auto_googler.py
+++ b/src/core/tasks/url/subtasks/miscellaneous_metadata/auto_googler.py
@@ -1,4 +1,4 @@
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 from src.core.tasks.url.subtasks.miscellaneous_metadata.base import \
     MiscellaneousMetadataSubtaskBase
 
diff --git a/src/core/tasks/url/subtasks/miscellaneous_metadata/base.py b/src/core/tasks/url/subtasks/miscellaneous_metadata/base.py
index 7b38504d..3ca7357b 100644
--- a/src/core/tasks/url/subtasks/miscellaneous_metadata/base.py
+++ b/src/core/tasks/url/subtasks/miscellaneous_metadata/base.py
@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 
 
 class MiscellaneousMetadataSubtaskBase(ABC):
diff --git a/src/core/tasks/url/subtasks/miscellaneous_metadata/ckan.py b/src/core/tasks/url/subtasks/miscellaneous_metadata/ckan.py
index 90512e2b..ef60b48c 100644
--- a/src/core/tasks/url/subtasks/miscellaneous_metadata/ckan.py
+++ b/src/core/tasks/url/subtasks/miscellaneous_metadata/ckan.py
@@ -1,4 +1,4 @@
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 from src.core.tasks.url.subtasks.miscellaneous_metadata.base import \
     MiscellaneousMetadataSubtaskBase
 
diff --git a/src/core/tasks/url/subtasks/miscellaneous_metadata/muckrock.py b/src/core/tasks/url/subtasks/miscellaneous_metadata/muckrock.py
index bb3eaadf..18a749b7 100644
--- a/src/core/tasks/url/subtasks/miscellaneous_metadata/muckrock.py
+++ b/src/core/tasks/url/subtasks/miscellaneous_metadata/muckrock.py
@@ -1,4 +1,4 @@
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 from src.core.tasks.url.subtasks.miscellaneous_metadata.base import \
     MiscellaneousMetadataSubtaskBase
 
diff --git a/src/db/client/async_.py b/src/db/client/async_.py
index d4368dd7..25b40852 100644
--- a/src/db/client/async_.py
+++ b/src/db/client/async_.py
@@ -77,19 +77,21 @@
     HasURLsWithoutAgencySuggestionsQueryBuilder
 from src.core.tasks.url.operators.auto_relevant.models.tdo import URLRelevantTDO
 from src.core.tasks.url.operators.auto_relevant.queries.get_tdos import GetAutoRelevantTDOsQueryBuilder
-from src.core.tasks.url.operators.submit_approved_url.queries.get import GetValidatedURLsQueryBuilder
-from src.core.tasks.url.operators.submit_approved_url.queries.has_validated import HasValidatedURLsQueryBuilder
-from src.core.tasks.url.operators.submit_approved_url.queries.mark_submitted import MarkURLsAsSubmittedQueryBuilder
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmitApprovedURLTDO, SubmittedURLInfo
-from src.core.tasks.url.operators.url_404_probe.tdo import URL404ProbeTDO
-from src.core.tasks.url.operators.url_duplicate.tdo import URLDuplicateTDO
-from src.core.tasks.url.operators.url_html.queries.get_pending_urls_without_html_data import \
+from src.core.tasks.url.operators.probe.queries.get_urls import GetURLsWithoutProbeQueryBuilder
+from src.core.tasks.url.operators.probe.queries.has_urls import HasURLsWithoutProbeQueryBuilder
+from src.core.tasks.url.operators.probe_404.tdo import URL404ProbeTDO
+from src.core.tasks.url.operators.submit_approved.queries.get import GetValidatedURLsQueryBuilder
+from src.core.tasks.url.operators.submit_approved.queries.has_validated import HasValidatedURLsQueryBuilder
+from src.core.tasks.url.operators.submit_approved.queries.mark_submitted import MarkURLsAsSubmittedQueryBuilder
+from src.core.tasks.url.operators.submit_approved.tdo import SubmitApprovedURLTDO, SubmittedURLInfo
+from src.core.tasks.url.operators.duplicate.tdo import URLDuplicateTDO
+from src.core.tasks.url.operators.html.queries.get import \
     GetPendingURLsWithoutHTMLDataQueryBuilder
-from src.core.tasks.url.operators.url_miscellaneous_metadata.queries.get_pending_urls_missing_miscellaneous_data import \
+from src.core.tasks.url.operators.misc_metadata.queries.get_pending_urls_missing_miscellaneous_data import \
     GetPendingURLsMissingMiscellaneousDataQueryBuilder
-from src.core.tasks.url.operators.url_miscellaneous_metadata.queries.has_pending_urls_missing_miscellaneous_data import \
+from src.core.tasks.url.operators.misc_metadata.queries.has_pending_urls_missing_miscellaneous_data import \
     HasPendingURsMissingMiscellaneousDataQueryBuilder
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 from src.db.client.helpers import add_standard_limit_and_offset
 from src.db.client.types import UserSuggestionModel
 from src.db.config_manager import ConfigManager
@@ -118,13 +120,13 @@
 from src.db.models.instantiations.task.core import Task
 from src.db.models.instantiations.task.error import TaskError
 from src.db.models.instantiations.url.checked_for_duplicate import URLCheckedForDuplicate
-from src.db.models.instantiations.url.compressed_html import URLCompressedHTML
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.models.instantiations.url.data_source.sqlalchemy import URLDataSource
 from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
 from src.db.models.instantiations.url.error_info.sqlalchemy import URLErrorInfo
-from src.db.models.instantiations.url.html_content import URLHTMLContent
+from src.db.models.instantiations.url.html.content.sqlalchemy import URLHTMLContent
 from src.db.models.instantiations.url.optional_data_source_metadata import URLOptionalDataSourceMetadata
 from src.db.models.instantiations.url.probed_for_404 import URLProbedFor404
 from src.db.models.instantiations.url.suggestion.agency.auto import AutomatedUrlAgencySuggestion
@@ -134,7 +136,8 @@
 from src.db.models.instantiations.url.suggestion.relevant.auto.pydantic.input import AutoRelevancyAnnotationInput
 from src.db.models.instantiations.url.suggestion.relevant.auto.sqlalchemy import AutoRelevantSuggestion
 from src.db.models.instantiations.url.suggestion.relevant.user import UserRelevantSuggestion
-from src.db.models.templates import Base
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from src.db.models.templates_.base import Base
 from src.db.queries.base.builder import QueryBuilderBase
 from src.db.queries.implementations.core.get.html_content_info import GetHTMLContentInfoQueryBuilder
 from src.db.queries.implementations.core.get.recent_batch_summaries.builder import GetRecentBatchSummariesQueryBuilder
@@ -142,11 +145,13 @@
     GetMetricsURLSAggregatedPendingQueryBuilder
 from src.db.statement_composer import StatementComposer
 from src.db.templates.markers.bulk.delete import BulkDeletableModel
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
 from src.db.templates.markers.bulk.upsert import BulkUpsertableModel
 from src.db.utils.compression import decompress_html, compress_html
 from src.external.pdap.dtos.sync.agencies import AgenciesSyncResponseInnerInfo
 from src.external.pdap.dtos.sync.data_sources import DataSourcesSyncResponseInnerInfo
 
+
 class AsyncDatabaseClient:
     def __init__(self, db_url: Optional[str] = None):
         if db_url is None:
@@ -184,7 +189,6 @@ async def wrapper(self, *args, **kwargs):
 
         return wrapper
 
-
     @session_manager
     async def execute(self, session: AsyncSession, statement):
         await session.execute(statement)
@@ -236,6 +240,15 @@ async def bulk_delete(
     ):
         return await sh.bulk_delete(session, models)
 
+    @session_manager
+    async def bulk_insert(
+        self,
+        session: AsyncSession,
+        models: list[BulkInsertableModel],
+        return_ids: bool = False
+    ) -> list[int] | None:
+        return await sh.bulk_insert(session, models=models, return_ids=return_ids)
+
     @session_manager
     async def scalar(self, session: AsyncSession, statement):
         """Fetch the first column of the first row."""
@@ -480,8 +493,8 @@ async def add_html_content_infos(self, session: AsyncSession, html_content_infos
         await self._add_models(session, URLHTMLContent, html_content_infos)
 
     @session_manager
-    async def has_pending_urls_without_html_data(self, session: AsyncSession) -> bool:
-        statement = self.statement_composer.pending_urls_without_html_data()
+    async def has_non_errored_urls_without_html_data(self, session: AsyncSession) -> bool:
+        statement = self.statement_composer.has_non_errored_urls_without_html_data()
         statement = statement.limit(1)
         scalar_result = await session.scalars(statement)
         return bool(scalar_result.first())
@@ -522,7 +535,7 @@ async def add_miscellaneous_metadata(self, session: AsyncSession, tdos: list[URL
             )
             session.add(metadata_object)
 
-    async def get_pending_urls_without_html_data(self) -> list[URLInfo]:
+    async def get_non_errored_urls_without_html_data(self) -> list[URLInfo]:
         return await self.run_query_builder(GetPendingURLsWithoutHTMLDataQueryBuilder())
 
     async def get_urls_with_html_data_and_without_models(
@@ -554,7 +567,6 @@ async def get_urls_with_html_data_and_without_auto_record_type_suggestion(
             model=AutoRecordTypeSuggestion
         )
 
-
     async def has_urls_with_html_data_and_without_models(
         self,
         session: AsyncSession,
@@ -596,7 +608,6 @@ async def get_all(
         """Get all records of a model. Used primarily in testing."""
         return await sh.get_all(session=session, model=model, order_by_attribute=order_by_attribute)
 
-
     @session_manager
     async def load_root_url_cache(self, session: AsyncSession) -> dict[str, str]:
         statement = select(RootURL)
@@ -620,7 +631,6 @@ async def get_urls(
             page=page, errors=errors
         ))
 
-
     @session_manager
     async def initiate_task(
         self,
@@ -732,7 +742,6 @@ async def get_urls_without_agency_suggestions(
         """Retrieve URLs without confirmed or suggested agencies."""
         return await self.run_query_builder(GetPendingURLsWithoutAgencySuggestionsQueryBuilder())
 
-
     async def get_next_url_agency_for_annotation(
         self,
         user_id: int,
@@ -743,7 +752,6 @@ async def get_next_url_agency_for_annotation(
             batch_id=batch_id
         ))
 
-
     @session_manager
     async def upsert_new_agencies(
         self,
@@ -765,7 +773,6 @@ async def upsert_new_agencies(
             agency.locality = suggestion.locality
             session.add(agency)
 
-
     @session_manager
     async def add_confirmed_agency_url_links(
         self,
@@ -865,7 +872,6 @@ async def reject_url(
             rejection_reason=rejection_reason
         ))
 
-
     @session_manager
     async def get_batch_by_id(self, session, batch_id: int) -> Optional[BatchSummary]:
         """Retrieve a batch by ID."""
@@ -886,7 +892,11 @@ async def get_urls_by_batch(self, batch_id: int, page: int = 1) -> list[URLInfo]
         ))
 
     @session_manager
-    async def insert_url(self, session: AsyncSession, url_info: URLInfo) -> int:
+    async def insert_url(
+        self,
+        session: AsyncSession,
+        url_info: URLInfo
+    ) -> int:
         """Insert a new URL into the database."""
         url_entry = URL(
             url=url_info.url,
@@ -905,21 +915,33 @@ async def insert_url(self, session: AsyncSession, url_info: URLInfo) -> int:
         return url_entry.id
 
     @session_manager
-    async def get_url_info_by_url(self, session: AsyncSession, url: str) -> Optional[URLInfo]:
+    async def get_url_info_by_url(
+        self,
+        session: AsyncSession,
+        url: str
+    ) -> URLInfo | None:
         query = Select(URL).where(URL.url == url)
         raw_result = await session.execute(query)
         url = raw_result.scalars().first()
         return URLInfo(**url.__dict__)
 
     @session_manager
-    async def get_url_info_by_id(self, session: AsyncSession, url_id: int) -> Optional[URLInfo]:
+    async def get_url_info_by_id(
+        self,
+        session: AsyncSession,
+        url_id: int
+    ) -> URLInfo | None:
         query = Select(URL).where(URL.id == url_id)
         raw_result = await session.execute(query)
         url = raw_result.scalars().first()
         return URLInfo(**url.__dict__)
 
     @session_manager
-    async def insert_logs(self, session, log_infos: List[LogInfo]):
+    async def insert_logs(
+        self,
+        session: AsyncSession,
+        log_infos: list[LogInfo]
+    ) -> None:
         for log_info in log_infos:
             log = Log(log=log_info.log, batch_id=log_info.batch_id)
             if log_info.created_at is not None:
@@ -927,7 +949,11 @@ async def insert_logs(self, session, log_infos: List[LogInfo]):
             session.add(log)
 
     @session_manager
-    async def insert_duplicates(self, session, duplicate_infos: list[DuplicateInsertInfo]):
+    async def insert_duplicates(
+        self,
+        session: AsyncSession,
+        duplicate_infos: list[DuplicateInsertInfo]
+    ) -> None:
         for duplicate_info in duplicate_infos:
             duplicate = Duplicate(
                 batch_id=duplicate_info.duplicate_batch_id,
@@ -936,7 +962,11 @@ async def insert_duplicates(self, session, duplicate_infos: list[DuplicateInsert
             session.add(duplicate)
 
     @session_manager
-    async def insert_batch(self, session: AsyncSession, batch_info: BatchInfo) -> int:
+    async def insert_batch(
+        self,
+        session: AsyncSession,
+        batch_info: BatchInfo
+    ) -> int:
         """Insert a new batch into the database and return its ID."""
         batch = Batch(
             strategy=batch_info.strategy,
@@ -956,7 +986,11 @@ async def insert_batch(self, session: AsyncSession, batch_info: BatchInfo) -> in
         await session.flush()
         return batch.id
 
-    async def insert_urls(self, url_infos: List[URLInfo], batch_id: int) -> InsertURLsInfo:
+    async def insert_urls(
+        self,
+        url_infos: list[URLInfo],
+        batch_id: int
+    ) -> InsertURLsInfo:
         url_mappings = []
         duplicates = []
         for url_info in url_infos:
@@ -984,14 +1018,14 @@ async def insert_urls(self, url_infos: List[URLInfo], batch_id: int) -> InsertUR
     @session_manager
     async def update_batch_post_collection(
         self,
-        session,
+        session: AsyncSession,
         batch_id: int,
         total_url_count: int,
         original_url_count: int,
         duplicate_url_count: int,
         batch_status: BatchStatus,
         compute_time: float = None,
-    ):
+    ) -> None:
 
         query = Select(Batch).where(Batch.id == batch_id)
         result = await session.execute(query)
@@ -1057,7 +1091,7 @@ async def delete_old_logs(self):
 
     async def get_next_url_for_all_annotations(
         self, batch_id: int | None = None
-        ) -> GetNextURLForAllAnnotationResponse:
+    ) -> GetNextURLForAllAnnotationResponse:
         return await self.run_query_builder(GetNextURLForAllAnnotationQueryBuilder(batch_id))
 
     @session_manager
@@ -1106,7 +1140,6 @@ async def upload_manual_batch(
             dto=dto
         ))
 
-
     @session_manager
     async def search_for_url(self, session: AsyncSession, url: str) -> SearchURLResponse:
         query = select(URL).where(URL.url == url)
@@ -1127,7 +1160,6 @@ async def get_batches_aggregated_metrics(self) -> GetMetricsBatchesAggregatedRes
             GetBatchesAggregatedMetricsQueryBuilder()
         )
 
-
     async def get_batches_breakdown_metrics(
         self,
         page: int
@@ -1414,6 +1446,8 @@ async def mark_all_as_duplicates(self, url_ids: List[int]):
     async def mark_all_as_404(self, url_ids: List[int]):
         query = update(URL).where(URL.id.in_(url_ids)).values(outcome=URLStatus.NOT_FOUND.value)
         await self.execute(query)
+        query = update(URLWebMetadata).where(URLWebMetadata.url_id.in_(url_ids)).values(status_code=404)
+        await self.execute(query)
 
     async def mark_all_as_recently_probed_for_404(
         self,
@@ -1571,3 +1605,13 @@ async def check_valid_urls_updated(self) -> bool:
 
     async def get_current_database_time(self) -> datetime:
         return await self.scalar(select(func.now()))
+
+    async def has_urls_without_probe(self) -> bool:
+        return await self.run_query_builder(
+            HasURLsWithoutProbeQueryBuilder()
+        )
+
+    async def get_urls_without_probe(self) -> list[URLMapping]:
+        return await self.run_query_builder(
+            GetURLsWithoutProbeQueryBuilder()
+        )
diff --git a/src/db/client/sync.py b/src/db/client/sync.py
index 866feb25..613c335b 100644
--- a/src/db/client/sync.py
+++ b/src/db/client/sync.py
@@ -11,16 +11,16 @@
 from src.db.models.instantiations.duplicate.pydantic.insert import DuplicateInsertInfo
 from src.db.dtos.url.insert import InsertURLsInfo
 from src.db.models.instantiations.log.pydantic.info import LogInfo
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.db.dtos.url.mapping import URLMapping
 from src.db.models.instantiations.link.batch_url import LinkBatchURL
-from src.db.models.templates import Base
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
+from src.db.models.templates_.base import Base
 from src.db.models.instantiations.duplicate.sqlalchemy import Duplicate
 from src.db.models.instantiations.log.sqlalchemy import Log
 from src.db.models.instantiations.url.data_source.sqlalchemy import URLDataSource
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.models.instantiations.batch.sqlalchemy import Batch
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmittedURLInfo
+from src.core.tasks.url.operators.submit_approved.tdo import SubmittedURLInfo
 from src.core.env_var_manager import EnvVarManager
 from src.core.enums import BatchStatus
 
diff --git a/src/db/dto_converter.py b/src/db/dto_converter.py
index ed2d361c..869b8978 100644
--- a/src/db/dto_converter.py
+++ b/src/db/dto_converter.py
@@ -5,15 +5,16 @@
 from src.api.endpoints.review.next.dto import FinalReviewAnnotationRelevantInfo, FinalReviewAnnotationRecordTypeInfo, \
     FinalReviewAnnotationAgencyAutoInfo, FinalReviewAnnotationAgencyInfo
 from src.core.enums import RecordType, SuggestionType
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
-from src.core.tasks.url.operators.url_html.scraper.parser.mapping import ENUM_TO_ATTRIBUTE_MAPPING
-from src.db.dtos.url.html_content import HTMLContentType, URLHTMLContentInfo
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.core.tasks.url.operators.html.scraper.parser.mapping import ENUM_TO_ATTRIBUTE_MAPPING
+from src.db.dtos.url.html_content import URLHTMLContentInfo
+from src.db.models.instantiations.url.html.content.enums import HTMLContentType
 from src.db.dtos.url.with_html import URLWithHTML
 from src.db.models.instantiations.link.url_agency.sqlalchemy import LinkURLAgency
 from src.db.models.instantiations.url.suggestion.agency.auto import AutomatedUrlAgencySuggestion
 from src.db.models.instantiations.url.suggestion.record_type.auto import AutoRecordTypeSuggestion
 from src.db.models.instantiations.url.suggestion.agency.user import UserUrlAgencySuggestion
-from src.db.models.instantiations.url.html_content import URLHTMLContent
+from src.db.models.instantiations.url.html.content.sqlalchemy import URLHTMLContent
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.models.instantiations.url.suggestion.record_type.user import UserRecordTypeSuggestion
 from src.db.models.instantiations.url.suggestion.relevant.auto.sqlalchemy import AutoRelevantSuggestion
diff --git a/src/db/dtos/url/html_content.py b/src/db/dtos/url/html_content.py
index f8b24eb0..1d3d67bf 100644
--- a/src/db/dtos/url/html_content.py
+++ b/src/db/dtos/url/html_content.py
@@ -1,21 +1,15 @@
-from enum import Enum
-from typing import Optional
+from src.db.models.instantiations.url.html.content.enums import HTMLContentType
+from src.db.models.instantiations.url.html.content.sqlalchemy import URLHTMLContent
+from src.db.models.templates_.base import Base
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
 
-from pydantic import BaseModel
 
-
-class HTMLContentType(Enum):
-    TITLE = "Title"
-    DESCRIPTION = "Description"
-    H1 = "H1"
-    H2 = "H2"
-    H3 = "H3"
-    H4 = "H4"
-    H5 = "H5"
-    H6 = "H6"
-    DIV = "Div"
-
-class URLHTMLContentInfo(BaseModel):
-    url_id: Optional[int] = None
+class URLHTMLContentInfo(BulkInsertableModel):
+    url_id: int | None = None
     content_type: HTMLContentType
-    content: str | list[str]
\ No newline at end of file
+    content: str | list[str]
+
+    @classmethod
+    def sa_model(cls) -> type[Base]:
+        """Defines the SQLAlchemy model."""
+        return URLHTMLContent
\ No newline at end of file
diff --git a/src/db/dtos/url/mapping.py b/src/db/dtos/url/mapping.py
index 38efbce4..18fc5be2 100644
--- a/src/db/dtos/url/mapping.py
+++ b/src/db/dtos/url/mapping.py
@@ -2,5 +2,6 @@
 
 
 class URLMapping(BaseModel):
+    """Mapping between url and url_id."""
     url: str
     url_id: int
diff --git a/src/db/enums.py b/src/db/enums.py
index 6c1d1496..c8ed9840 100644
--- a/src/db/enums.py
+++ b/src/db/enums.py
@@ -44,6 +44,7 @@ class TaskType(PyEnum):
     SYNC_AGENCIES = "Sync Agencies"
     SYNC_DATA_SOURCES = "Sync Data Sources"
     PUSH_TO_HUGGINGFACE = "Push to Hugging Face"
+    PROBE_URL = "URL Probe"
 
 class ChangeLogOperationType(PyEnum):
     INSERT = "INSERT"
diff --git a/src/db/helpers/session/parser.py b/src/db/helpers/session/parser.py
index bc822022..b580dcd1 100644
--- a/src/db/helpers/session/parser.py
+++ b/src/db/helpers/session/parser.py
@@ -1,5 +1,5 @@
 from src.db.helpers.session.types import BulkActionType
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 from src.db.templates.protocols.sa_correlated.core import SQLAlchemyCorrelatedProtocol
 from src.db.templates.protocols.sa_correlated.with_id import SQLAlchemyCorrelatedWithIDProtocol
 from src.db.utils.validate import validate_all_models_of_same_type
diff --git a/src/db/helpers/session/session_helper.py b/src/db/helpers/session/session_helper.py
index 2b3776c1..a616664f 100644
--- a/src/db/helpers/session/session_helper.py
+++ b/src/db/helpers/session/session_helper.py
@@ -11,7 +11,8 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from src.db.helpers.session.parser import BulkActionParser
-from src.db.models.templates import Base, StandardBase
+from src.db.models.templates_.with_id import WithIDBase
+from src.db.models.templates_.base import Base
 from src.db.templates.markers.bulk.delete import BulkDeletableModel
 from src.db.templates.markers.bulk.insert import BulkInsertableModel
 from src.db.templates.markers.bulk.update import BulkUpdatableModel
@@ -43,6 +44,10 @@ async def mappings(session: AsyncSession, query: sa.Select) -> Sequence[sa.RowMa
     raw_result = await session.execute(query)
     return raw_result.mappings().all()
 
+async def has_results(session: AsyncSession, query: sa.Select) -> bool:
+    raw_result = await session.execute(query)
+    return raw_result.first() is not None
+
 async def bulk_upsert(
     session: AsyncSession,
     models: list[BulkUpsertableModel],
@@ -88,7 +93,7 @@ async def add(
 
 async def add_all(
     session: AsyncSession,
-    models: list[StandardBase],
+    models: list[WithIDBase],
     return_ids: bool = False
 ) -> list[int] | None:
     session.add_all(models)
diff --git a/src/db/models/instantiations/agency/pydantic/upsert.py b/src/db/models/instantiations/agency/pydantic/upsert.py
index 9a869e84..1deeb6b5 100644
--- a/src/db/models/instantiations/agency/pydantic/upsert.py
+++ b/src/db/models/instantiations/agency/pydantic/upsert.py
@@ -1,7 +1,7 @@
 from datetime import datetime
 
 from src.db.models.instantiations.agency.sqlalchemy import Agency
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 from src.db.templates.markers.bulk.upsert import BulkUpsertableModel
 
 
diff --git a/src/db/models/instantiations/agency/sqlalchemy.py b/src/db/models/instantiations/agency/sqlalchemy.py
index 2ce3676f..8310eeac 100644
--- a/src/db/models/instantiations/agency/sqlalchemy.py
+++ b/src/db/models/instantiations/agency/sqlalchemy.py
@@ -6,13 +6,13 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import UpdatedAtMixin, CreatedAtMixin
-from src.db.models.templates import Base, StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
 class Agency(
     CreatedAtMixin, # When agency was added to database
     UpdatedAtMixin, # When agency was last updated in database
-    StandardBase
+    WithIDBase
 ):
     __tablename__ = "agencies"
 
diff --git a/src/db/models/instantiations/backlog_snapshot.py b/src/db/models/instantiations/backlog_snapshot.py
index 89645160..6b0982cd 100644
--- a/src/db/models/instantiations/backlog_snapshot.py
+++ b/src/db/models/instantiations/backlog_snapshot.py
@@ -1,10 +1,10 @@
 from sqlalchemy import Column, Integer
 
 from src.db.models.mixins import CreatedAtMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class BacklogSnapshot(CreatedAtMixin, StandardBase):
+class BacklogSnapshot(CreatedAtMixin, WithIDBase):
     __tablename__ = "backlog_snapshot"
 
     count_pending_total = Column(Integer, nullable=False)
diff --git a/src/db/models/instantiations/batch/sqlalchemy.py b/src/db/models/instantiations/batch/sqlalchemy.py
index b001dbac..0e6aa611 100644
--- a/src/db/models/instantiations/batch/sqlalchemy.py
+++ b/src/db/models/instantiations/batch/sqlalchemy.py
@@ -3,11 +3,11 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.helpers import CURRENT_TIME_SERVER_DEFAULT
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 from src.db.models.types import batch_status_enum
 
 
-class Batch(StandardBase):
+class Batch(WithIDBase):
     __tablename__ = 'batches'
 
     strategy = Column(
diff --git a/src/db/models/instantiations/change_log.py b/src/db/models/instantiations/change_log.py
index 975958ab..0cb74659 100644
--- a/src/db/models/instantiations/change_log.py
+++ b/src/db/models/instantiations/change_log.py
@@ -5,10 +5,10 @@
 
 from src.db.enums import ChangeLogOperationType
 from src.db.models.mixins import CreatedAtMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class ChangeLog(CreatedAtMixin, StandardBase):
+class ChangeLog(CreatedAtMixin, WithIDBase):
 
     __tablename__ = "change_log"
 
diff --git a/src/db/models/instantiations/duplicate/sqlalchemy.py b/src/db/models/instantiations/duplicate/sqlalchemy.py
index 67df3af5..03c492e3 100644
--- a/src/db/models/instantiations/duplicate/sqlalchemy.py
+++ b/src/db/models/instantiations/duplicate/sqlalchemy.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import BatchDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class Duplicate(BatchDependentMixin, StandardBase):
+class Duplicate(BatchDependentMixin, WithIDBase):
     """
     Identifies duplicates which occur within a batch
     """
diff --git a/src/db/models/instantiations/link/batch_url.py b/src/db/models/instantiations/link/batch_url.py
index d86b0703..8fb8f42e 100644
--- a/src/db/models/instantiations/link/batch_url.py
+++ b/src/db/models/instantiations/link/batch_url.py
@@ -1,7 +1,7 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import CreatedAtMixin, UpdatedAtMixin, BatchDependentMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
 class LinkBatchURL(
@@ -9,7 +9,7 @@ class LinkBatchURL(
     CreatedAtMixin,
     URLDependentMixin,
     BatchDependentMixin,
-    StandardBase
+    WithIDBase
 ):
     __tablename__ = "link_batch_urls"
 
diff --git a/src/db/models/instantiations/link/task_url.py b/src/db/models/instantiations/link/task_url.py
index 02ef02c3..2535d317 100644
--- a/src/db/models/instantiations/link/task_url.py
+++ b/src/db/models/instantiations/link/task_url.py
@@ -1,6 +1,6 @@
 from sqlalchemy import UniqueConstraint, Column, Integer, ForeignKey
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 class LinkTaskURL(Base):
diff --git a/src/db/models/instantiations/link/url_agency/sqlalchemy.py b/src/db/models/instantiations/link/url_agency/sqlalchemy.py
index 28e42924..f8d72065 100644
--- a/src/db/models/instantiations/link/url_agency/sqlalchemy.py
+++ b/src/db/models/instantiations/link/url_agency/sqlalchemy.py
@@ -3,10 +3,10 @@
 
 from src.db.models.helpers import get_agency_id_foreign_column
 from src.db.models.mixins import URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class LinkURLAgency(URLDependentMixin, StandardBase):
+class LinkURLAgency(URLDependentMixin, WithIDBase):
     __tablename__ = "link_urls_agencies"
 
     agency_id: Mapped[int] = get_agency_id_foreign_column()
diff --git a/src/db/models/instantiations/log/sqlalchemy.py b/src/db/models/instantiations/log/sqlalchemy.py
index 769391cf..60f17875 100644
--- a/src/db/models/instantiations/log/sqlalchemy.py
+++ b/src/db/models/instantiations/log/sqlalchemy.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import CreatedAtMixin, BatchDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class Log(CreatedAtMixin, BatchDependentMixin, StandardBase):
+class Log(CreatedAtMixin, BatchDependentMixin, WithIDBase):
     __tablename__ = 'logs'
 
     log = Column(Text, nullable=False)
diff --git a/src/db/models/instantiations/missing.py b/src/db/models/instantiations/missing.py
index 05665eba..6ad868df 100644
--- a/src/db/models/instantiations/missing.py
+++ b/src/db/models/instantiations/missing.py
@@ -3,10 +3,10 @@
 
 from src.db.models.helpers import get_created_at_column
 from src.db.models.mixins import BatchDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class Missing(BatchDependentMixin, StandardBase):
+class Missing(BatchDependentMixin, WithIDBase):
     __tablename__ = 'missing'
 
     place_id = Column(Integer, nullable=False)
diff --git a/src/db/models/instantiations/root_url_cache.py b/src/db/models/instantiations/root_url_cache.py
index 4ebadd50..f79e4b5c 100644
--- a/src/db/models/instantiations/root_url_cache.py
+++ b/src/db/models/instantiations/root_url_cache.py
@@ -1,10 +1,10 @@
 from sqlalchemy import UniqueConstraint, Column, String
 
 from src.db.models.mixins import UpdatedAtMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class RootURL(UpdatedAtMixin, StandardBase):
+class RootURL(UpdatedAtMixin, WithIDBase):
     __tablename__ = 'root_url_cache'
     __table_args__ = (
         UniqueConstraint(
diff --git a/src/db/models/instantiations/state/huggingface.py b/src/db/models/instantiations/state/huggingface.py
index 58e54cdc..d858dc0a 100644
--- a/src/db/models/instantiations/state/huggingface.py
+++ b/src/db/models/instantiations/state/huggingface.py
@@ -1,6 +1,6 @@
 from sqlalchemy import Column, Integer, DateTime
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 class HuggingFaceUploadState(Base):
diff --git a/src/db/models/instantiations/state/sync/agencies.py b/src/db/models/instantiations/state/sync/agencies.py
index 207a2936..7ee1babe 100644
--- a/src/db/models/instantiations/state/sync/agencies.py
+++ b/src/db/models/instantiations/state/sync/agencies.py
@@ -4,7 +4,7 @@
 
 from sqlalchemy import DateTime, Date, Integer, Column
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 class AgenciesSyncState(Base):
diff --git a/src/db/models/instantiations/state/sync/data_sources.py b/src/db/models/instantiations/state/sync/data_sources.py
index cf173860..333d0945 100644
--- a/src/db/models/instantiations/state/sync/data_sources.py
+++ b/src/db/models/instantiations/state/sync/data_sources.py
@@ -1,6 +1,6 @@
 from sqlalchemy import Integer, Column, DateTime, Date
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 class DataSourcesSyncState(Base):
diff --git a/src/db/models/instantiations/task/core.py b/src/db/models/instantiations/task/core.py
index 514301c8..291a5d0a 100644
--- a/src/db/models/instantiations/task/core.py
+++ b/src/db/models/instantiations/task/core.py
@@ -3,11 +3,11 @@
 
 from src.db.enums import PGEnum, TaskType
 from src.db.models.mixins import UpdatedAtMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 from src.db.models.types import batch_status_enum
 
 
-class Task(UpdatedAtMixin, StandardBase):
+class Task(UpdatedAtMixin, WithIDBase):
     __tablename__ = 'tasks'
 
     task_type = Column(
diff --git a/src/db/models/instantiations/task/error.py b/src/db/models/instantiations/task/error.py
index 03014904..c5a25e78 100644
--- a/src/db/models/instantiations/task/error.py
+++ b/src/db/models/instantiations/task/error.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import UpdatedAtMixin, TaskDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class TaskError(UpdatedAtMixin, TaskDependentMixin, StandardBase):
+class TaskError(UpdatedAtMixin, TaskDependentMixin, WithIDBase):
     __tablename__ = 'task_errors'
 
     error = Column(Text, nullable=False)
diff --git a/src/db/models/instantiations/url/checked_for_duplicate.py b/src/db/models/instantiations/url/checked_for_duplicate.py
index 9443d0ac..bb7cf666 100644
--- a/src/db/models/instantiations/url/checked_for_duplicate.py
+++ b/src/db/models/instantiations/url/checked_for_duplicate.py
@@ -1,10 +1,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URLCheckedForDuplicate(CreatedAtMixin, URLDependentMixin, StandardBase):
+class URLCheckedForDuplicate(CreatedAtMixin, URLDependentMixin, WithIDBase):
     __tablename__ = 'url_checked_for_duplicate'
 
     # Relationships
diff --git a/src/db/models/instantiations/url/core/pydantic.py b/src/db/models/instantiations/url/core/pydantic.py
deleted file mode 100644
index e409c32c..00000000
--- a/src/db/models/instantiations/url/core/pydantic.py
+++ /dev/null
@@ -1,17 +0,0 @@
-import datetime
-from typing import Optional
-
-from pydantic import BaseModel
-
-from src.collectors.enums import URLStatus
-
-
-class URLInfo(BaseModel):
-    id: Optional[int] = None
-    batch_id: Optional[int] = None
-    url: str
-    collector_metadata: Optional[dict] = None
-    outcome: URLStatus = URLStatus.PENDING
-    updated_at: Optional[datetime.datetime] = None
-    created_at: Optional[datetime.datetime] = None
-    name: Optional[str] = None
diff --git a/src/db/models/instantiations/url/core/pydantic/__init__.py b/src/db/models/instantiations/url/core/pydantic/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/core/pydantic/info.py b/src/db/models/instantiations/url/core/pydantic/info.py
new file mode 100644
index 00000000..6099db29
--- /dev/null
+++ b/src/db/models/instantiations/url/core/pydantic/info.py
@@ -0,0 +1,17 @@
+import datetime
+from typing import Optional
+
+from pydantic import BaseModel
+
+from src.collectors.enums import URLStatus
+
+
+class URLInfo(BaseModel):
+    id: int | None = None
+    batch_id: int | None= None
+    url: str
+    collector_metadata: dict | None = None
+    outcome: URLStatus = URLStatus.PENDING
+    updated_at: datetime.datetime | None = None
+    created_at: datetime.datetime | None = None
+    name: str | None = None
diff --git a/src/db/models/instantiations/url/core/pydantic/insert.py b/src/db/models/instantiations/url/core/pydantic/insert.py
new file mode 100644
index 00000000..e384416e
--- /dev/null
+++ b/src/db/models/instantiations/url/core/pydantic/insert.py
@@ -0,0 +1,19 @@
+from src.collectors.enums import URLStatus
+from src.core.enums import RecordType
+from src.db.models.instantiations.url.core.sqlalchemy import URL
+from src.db.models.templates_.base import Base
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
+
+
+class URLInsertModel(BulkInsertableModel):
+
+    @classmethod
+    def sa_model(cls) -> type[Base]:
+        """Defines the SQLAlchemy model."""
+        return URL
+
+    url: str
+    collector_metadata: dict | None = None
+    name: str
+    outcome: URLStatus
+    record_type: RecordType
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/core/sqlalchemy.py b/src/db/models/instantiations/url/core/sqlalchemy.py
index 8a476071..4b4c0159 100644
--- a/src/db/models/instantiations/url/core/sqlalchemy.py
+++ b/src/db/models/instantiations/url/core/sqlalchemy.py
@@ -1,16 +1,14 @@
-from sqlalchemy import Column, Integer, ForeignKey, Text, String, JSON, Enum
-from sqlalchemy.dialects import postgresql
+from sqlalchemy import Column, Text, String, JSON
 from sqlalchemy.orm import relationship
 
 from src.collectors.enums import URLStatus
 from src.core.enums import RecordType
 from src.db.models.helpers import enum_column
 from src.db.models.mixins import UpdatedAtMixin, CreatedAtMixin
-from src.db.models.templates import StandardBase
-from src.db.models.types import record_type_values
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URL(UpdatedAtMixin, CreatedAtMixin, StandardBase):
+class URL(UpdatedAtMixin, CreatedAtMixin, WithIDBase):
     __tablename__ = 'urls'
 
     # The batch this URL is associated with
@@ -84,4 +82,12 @@ class URL(UpdatedAtMixin, CreatedAtMixin, StandardBase):
         "URLCompressedHTML",
         uselist=False,
         back_populates="url"
+    )
+    scrape_info = relationship(
+        "URLScrapeInfo",
+        uselist=False,
+    )
+    web_metadata = relationship(
+        "URLWebMetadata",
+        uselist=False,
     )
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/data_source/sqlalchemy.py b/src/db/models/instantiations/url/data_source/sqlalchemy.py
index b5bdb40d..270ba7e3 100644
--- a/src/db/models/instantiations/url/data_source/sqlalchemy.py
+++ b/src/db/models/instantiations/url/data_source/sqlalchemy.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URLDataSource(CreatedAtMixin, URLDependentMixin, StandardBase):
+class URLDataSource(CreatedAtMixin, URLDependentMixin, WithIDBase):
     __tablename__ = "url_data_sources"
 
     data_source_id = Column(Integer, nullable=False)
diff --git a/src/db/models/instantiations/url/error_info/pydantic.py b/src/db/models/instantiations/url/error_info/pydantic.py
index 46f5b9fa..c8596a13 100644
--- a/src/db/models/instantiations/url/error_info/pydantic.py
+++ b/src/db/models/instantiations/url/error_info/pydantic.py
@@ -3,9 +3,17 @@
 
 from pydantic import BaseModel
 
+from src.db.models.instantiations.url.error_info.sqlalchemy import URLErrorInfo
+from src.db.models.templates_.base import Base
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
 
-class URLErrorPydanticInfo(BaseModel):
+
+class URLErrorPydanticInfo(BulkInsertableModel):
     task_id: int
     url_id: int
     error: str
-    updated_at: Optional[datetime.datetime] = None
\ No newline at end of file
+    updated_at: datetime.datetime = None
+
+    @classmethod
+    def sa_model(cls) -> type[Base]:
+        return URLErrorInfo
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/error_info/sqlalchemy.py b/src/db/models/instantiations/url/error_info/sqlalchemy.py
index 8825777f..59f6c263 100644
--- a/src/db/models/instantiations/url/error_info/sqlalchemy.py
+++ b/src/db/models/instantiations/url/error_info/sqlalchemy.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import UpdatedAtMixin, TaskDependentMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URLErrorInfo(UpdatedAtMixin, TaskDependentMixin, URLDependentMixin, StandardBase):
+class URLErrorInfo(UpdatedAtMixin, TaskDependentMixin, URLDependentMixin, WithIDBase):
     __tablename__ = 'url_error_info'
     __table_args__ = (UniqueConstraint(
         "url_id",
diff --git a/src/db/models/instantiations/url/html/__init__.py b/src/db/models/instantiations/url/html/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/html/compressed/__init__.py b/src/db/models/instantiations/url/html/compressed/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/html/compressed/pydantic.py b/src/db/models/instantiations/url/html/compressed/pydantic.py
new file mode 100644
index 00000000..b626b5c2
--- /dev/null
+++ b/src/db/models/instantiations/url/html/compressed/pydantic.py
@@ -0,0 +1,13 @@
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
+from src.db.models.templates_.base import Base
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
+
+
+class URLCompressedHTMLPydantic(BulkInsertableModel):
+    url_id: int
+    compressed_html: bytes
+
+    @classmethod
+    def sa_model(cls) -> type[Base]:
+        """Defines the SQLAlchemy model."""
+        return URLCompressedHTML
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/compressed_html.py b/src/db/models/instantiations/url/html/compressed/sqlalchemy.py
similarity index 86%
rename from src/db/models/instantiations/url/compressed_html.py
rename to src/db/models/instantiations/url/html/compressed/sqlalchemy.py
index 92e340a5..995c5b25 100644
--- a/src/db/models/instantiations/url/compressed_html.py
+++ b/src/db/models/instantiations/url/html/compressed/sqlalchemy.py
@@ -2,13 +2,13 @@
 from sqlalchemy.orm import relationship, Mapped
 
 from src.db.models.mixins import CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
 class URLCompressedHTML(
     CreatedAtMixin,
     URLDependentMixin,
-    StandardBase
+    WithIDBase
 ):
     __tablename__ = 'url_compressed_html'
 
diff --git a/src/db/models/instantiations/url/html/content/__init__.py b/src/db/models/instantiations/url/html/content/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/html/content/enums.py b/src/db/models/instantiations/url/html/content/enums.py
new file mode 100644
index 00000000..13820352
--- /dev/null
+++ b/src/db/models/instantiations/url/html/content/enums.py
@@ -0,0 +1,13 @@
+from enum import Enum
+
+
+class HTMLContentType(Enum):
+    TITLE = "Title"
+    DESCRIPTION = "Description"
+    H1 = "H1"
+    H2 = "H2"
+    H3 = "H3"
+    H4 = "H4"
+    H5 = "H5"
+    H6 = "H6"
+    DIV = "Div"
diff --git a/src/db/models/instantiations/url/html/content/pydantic.py b/src/db/models/instantiations/url/html/content/pydantic.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/html_content.py b/src/db/models/instantiations/url/html/content/sqlalchemy.py
similarity index 82%
rename from src/db/models/instantiations/url/html_content.py
rename to src/db/models/instantiations/url/html/content/sqlalchemy.py
index b23af35c..63e4da76 100644
--- a/src/db/models/instantiations/url/html_content.py
+++ b/src/db/models/instantiations/url/html/content/sqlalchemy.py
@@ -3,10 +3,14 @@
 
 from src.db.enums import PGEnum
 from src.db.models.mixins import UpdatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URLHTMLContent(UpdatedAtMixin, URLDependentMixin, StandardBase):
+class URLHTMLContent(
+    UpdatedAtMixin,
+    URLDependentMixin,
+    WithIDBase
+):
     __tablename__ = 'url_html_content'
     __table_args__ = (UniqueConstraint(
         "url_id",
diff --git a/src/db/models/instantiations/url/optional_data_source_metadata.py b/src/db/models/instantiations/url/optional_data_source_metadata.py
index fac99828..bb2a95e5 100644
--- a/src/db/models/instantiations/url/optional_data_source_metadata.py
+++ b/src/db/models/instantiations/url/optional_data_source_metadata.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URLOptionalDataSourceMetadata(URLDependentMixin, StandardBase):
+class URLOptionalDataSourceMetadata(URLDependentMixin, WithIDBase):
     __tablename__ = 'url_optional_data_source_metadata'
 
     record_formats = Column(ARRAY(String), nullable=True)
diff --git a/src/db/models/instantiations/url/probed_for_404.py b/src/db/models/instantiations/url/probed_for_404.py
index b795b628..478ce9de 100644
--- a/src/db/models/instantiations/url/probed_for_404.py
+++ b/src/db/models/instantiations/url/probed_for_404.py
@@ -2,10 +2,10 @@
 
 from src.db.models.helpers import get_created_at_column
 from src.db.models.mixins import URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class URLProbedFor404(URLDependentMixin, StandardBase):
+class URLProbedFor404(URLDependentMixin, WithIDBase):
     __tablename__ = 'url_probed_for_404'
 
     last_probed_at = get_created_at_column()
diff --git a/src/db/models/instantiations/url/reviewing_user.py b/src/db/models/instantiations/url/reviewing_user.py
index 938f86ab..9213a157 100644
--- a/src/db/models/instantiations/url/reviewing_user.py
+++ b/src/db/models/instantiations/url/reviewing_user.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class ReviewingUserURL(CreatedAtMixin, URLDependentMixin, StandardBase):
+class ReviewingUserURL(CreatedAtMixin, URLDependentMixin, WithIDBase):
     __tablename__ = 'reviewing_user_url'
     __table_args__ = (
         UniqueConstraint(
diff --git a/src/db/models/instantiations/url/scrape_info/__init__.py b/src/db/models/instantiations/url/scrape_info/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/scrape_info/enums.py b/src/db/models/instantiations/url/scrape_info/enums.py
new file mode 100644
index 00000000..3e16fff3
--- /dev/null
+++ b/src/db/models/instantiations/url/scrape_info/enums.py
@@ -0,0 +1,6 @@
+from enum import Enum
+
+
+class ScrapeStatus(Enum):
+    SUCCESS = "success"
+    ERROR = "error"
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/scrape_info/pydantic.py b/src/db/models/instantiations/url/scrape_info/pydantic.py
new file mode 100644
index 00000000..f41b1642
--- /dev/null
+++ b/src/db/models/instantiations/url/scrape_info/pydantic.py
@@ -0,0 +1,13 @@
+from src.db.models.instantiations.url.scrape_info.enums import ScrapeStatus
+from src.db.models.instantiations.url.scrape_info.sqlalchemy import URLScrapeInfo
+from src.db.models.templates_.base import Base
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
+
+
+class URLScrapeInfoInsertModel(BulkInsertableModel):
+    url_id: int
+    status: ScrapeStatus
+
+    @classmethod
+    def sa_model(cls) -> type[Base]:
+        return URLScrapeInfo
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/scrape_info/sqlalchemy.py b/src/db/models/instantiations/url/scrape_info/sqlalchemy.py
new file mode 100644
index 00000000..d97e0b93
--- /dev/null
+++ b/src/db/models/instantiations/url/scrape_info/sqlalchemy.py
@@ -0,0 +1,17 @@
+from src.db.models.helpers import enum_column
+from src.db.models.instantiations.url.scrape_info.enums import ScrapeStatus
+from src.db.models.mixins import URLDependentMixin
+from src.db.models.templates_.standard import StandardBase
+
+
+class URLScrapeInfo(
+    StandardBase,
+    URLDependentMixin
+):
+
+    __tablename__ = 'url_scrape_info'
+
+    status = enum_column(
+        enum_type=ScrapeStatus,
+        name='scrape_status',
+    )
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/suggestion/agency/auto.py b/src/db/models/instantiations/url/suggestion/agency/auto.py
index 01585535..5ecfdf0a 100644
--- a/src/db/models/instantiations/url/suggestion/agency/auto.py
+++ b/src/db/models/instantiations/url/suggestion/agency/auto.py
@@ -3,10 +3,10 @@
 
 from src.db.models.helpers import get_agency_id_foreign_column
 from src.db.models.mixins import URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class AutomatedUrlAgencySuggestion(URLDependentMixin, StandardBase):
+class AutomatedUrlAgencySuggestion(URLDependentMixin, WithIDBase):
     __tablename__ = "automated_url_agency_suggestions"
 
     agency_id = get_agency_id_foreign_column(nullable=True)
diff --git a/src/db/models/instantiations/url/suggestion/agency/user.py b/src/db/models/instantiations/url/suggestion/agency/user.py
index 5a54399f..7a338fd0 100644
--- a/src/db/models/instantiations/url/suggestion/agency/user.py
+++ b/src/db/models/instantiations/url/suggestion/agency/user.py
@@ -3,10 +3,10 @@
 
 from src.db.models.helpers import get_agency_id_foreign_column
 from src.db.models.mixins import URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class UserUrlAgencySuggestion(URLDependentMixin, StandardBase):
+class UserUrlAgencySuggestion(URLDependentMixin, WithIDBase):
     __tablename__ = "user_url_agency_suggestions"
 
     agency_id = get_agency_id_foreign_column(nullable=True)
diff --git a/src/db/models/instantiations/url/suggestion/record_type/auto.py b/src/db/models/instantiations/url/suggestion/record_type/auto.py
index 34faf6f3..2aaed526 100644
--- a/src/db/models/instantiations/url/suggestion/record_type/auto.py
+++ b/src/db/models/instantiations/url/suggestion/record_type/auto.py
@@ -3,7 +3,7 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import URLDependentMixin, UpdatedAtMixin, CreatedAtMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 from src.db.models.types import record_type_values
 
 
@@ -11,7 +11,7 @@ class AutoRecordTypeSuggestion(
     UpdatedAtMixin,
     CreatedAtMixin,
     URLDependentMixin,
-    StandardBase
+    WithIDBase
 ):
     __tablename__ = "auto_record_type_suggestions"
     record_type = Column(postgresql.ENUM(*record_type_values, name='record_type'), nullable=False)
diff --git a/src/db/models/instantiations/url/suggestion/record_type/user.py b/src/db/models/instantiations/url/suggestion/record_type/user.py
index 77954509..8fcc816b 100644
--- a/src/db/models/instantiations/url/suggestion/record_type/user.py
+++ b/src/db/models/instantiations/url/suggestion/record_type/user.py
@@ -3,11 +3,11 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import UpdatedAtMixin, CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 from src.db.models.types import record_type_values
 
 
-class UserRecordTypeSuggestion(UpdatedAtMixin, CreatedAtMixin, URLDependentMixin, StandardBase):
+class UserRecordTypeSuggestion(UpdatedAtMixin, CreatedAtMixin, URLDependentMixin, WithIDBase):
     __tablename__ = "user_record_type_suggestions"
 
     user_id = Column(Integer, nullable=False)
diff --git a/src/db/models/instantiations/url/suggestion/relevant/auto/sqlalchemy.py b/src/db/models/instantiations/url/suggestion/relevant/auto/sqlalchemy.py
index 982b4449..49dc7457 100644
--- a/src/db/models/instantiations/url/suggestion/relevant/auto/sqlalchemy.py
+++ b/src/db/models/instantiations/url/suggestion/relevant/auto/sqlalchemy.py
@@ -2,10 +2,10 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import UpdatedAtMixin, CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
-class AutoRelevantSuggestion(UpdatedAtMixin, CreatedAtMixin, URLDependentMixin, StandardBase):
+class AutoRelevantSuggestion(UpdatedAtMixin, CreatedAtMixin, URLDependentMixin, WithIDBase):
     __tablename__ = "auto_relevant_suggestions"
 
     relevant = Column(Boolean, nullable=True)
diff --git a/src/db/models/instantiations/url/suggestion/relevant/user.py b/src/db/models/instantiations/url/suggestion/relevant/user.py
index b087f71e..a0cfed44 100644
--- a/src/db/models/instantiations/url/suggestion/relevant/user.py
+++ b/src/db/models/instantiations/url/suggestion/relevant/user.py
@@ -3,14 +3,14 @@
 from sqlalchemy.orm import relationship
 
 from src.db.models.mixins import UpdatedAtMixin, CreatedAtMixin, URLDependentMixin
-from src.db.models.templates import StandardBase
+from src.db.models.templates_.with_id import WithIDBase
 
 
 class UserRelevantSuggestion(
     UpdatedAtMixin,
     CreatedAtMixin,
     URLDependentMixin,
-    StandardBase
+    WithIDBase
 ):
     __tablename__ = "user_relevant_suggestions"
 
diff --git a/src/db/models/instantiations/url/web_metadata/__init__.py b/src/db/models/instantiations/url/web_metadata/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/instantiations/url/web_metadata/pydantic.py b/src/db/models/instantiations/url/web_metadata/pydantic.py
new file mode 100644
index 00000000..c0460437
--- /dev/null
+++ b/src/db/models/instantiations/url/web_metadata/pydantic.py
@@ -0,0 +1,18 @@
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from src.db.models.templates_.base import Base
+from src.db.templates.markers.bulk.insert import BulkInsertableModel
+
+
+class URLWebMetadataPydantic(BulkInsertableModel):
+
+    @classmethod
+    def sa_model(cls) -> type[Base]:
+        """Defines the SQLAlchemy model."""
+        return URLWebMetadata
+
+
+    url_id: int
+    accessed: bool
+    status_code: int | None
+    content_type: str | None
+    error_message: str | None
\ No newline at end of file
diff --git a/src/db/models/instantiations/url/web_metadata/sqlalchemy.py b/src/db/models/instantiations/url/web_metadata/sqlalchemy.py
new file mode 100644
index 00000000..45f5233c
--- /dev/null
+++ b/src/db/models/instantiations/url/web_metadata/sqlalchemy.py
@@ -0,0 +1,33 @@
+from sqlalchemy import Column, Text, Boolean, Integer
+
+from src.db.models.mixins import URLDependentMixin, CreatedAtMixin, UpdatedAtMixin
+from src.db.models.templates_.with_id import WithIDBase
+
+
+class URLWebMetadata(
+    WithIDBase,
+    URLDependentMixin,
+    CreatedAtMixin,
+    UpdatedAtMixin
+):
+    """Contains information about the web page."""
+    __tablename__ = "url_web_metadata"
+
+    accessed = Column(
+        Boolean(),
+        nullable=False
+    )
+    status_code = Column(
+        Integer(),
+        nullable=True
+    )
+    content_type = Column(
+        Text(),
+        nullable=True
+    )
+    error_message = Column(
+        Text(),
+        nullable=True
+    )
+
+
diff --git a/src/db/models/templates.py b/src/db/models/templates.py
deleted file mode 100644
index 5e738fab..00000000
--- a/src/db/models/templates.py
+++ /dev/null
@@ -1,11 +0,0 @@
-from sqlalchemy import Integer, Column
-from sqlalchemy.orm import declarative_base
-
-# Base class for SQLAlchemy ORM models
-Base = declarative_base()
-
-class StandardBase(Base):
-    __abstract__ = True
-
-    id = Column(Integer, primary_key=True, autoincrement=True)
-
diff --git a/src/db/models/templates_/__init__.py b/src/db/models/templates_/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/db/models/templates_/base.py b/src/db/models/templates_/base.py
new file mode 100644
index 00000000..0ec5f68e
--- /dev/null
+++ b/src/db/models/templates_/base.py
@@ -0,0 +1,4 @@
+"""Base class for SQLAlchemy ORM models."""
+from sqlalchemy.orm import declarative_base
+
+Base = declarative_base()
diff --git a/src/db/models/templates_/standard.py b/src/db/models/templates_/standard.py
new file mode 100644
index 00000000..85a01941
--- /dev/null
+++ b/src/db/models/templates_/standard.py
@@ -0,0 +1,14 @@
+from sqlalchemy import Column, Integer
+
+from src.db.models.mixins import CreatedAtMixin, UpdatedAtMixin
+from src.db.models.templates_.base import Base
+
+
+class StandardBase(
+    Base,
+    CreatedAtMixin,
+    UpdatedAtMixin,
+):
+    __abstract__ = True
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
diff --git a/src/db/models/templates_/with_id.py b/src/db/models/templates_/with_id.py
new file mode 100644
index 00000000..e454f215
--- /dev/null
+++ b/src/db/models/templates_/with_id.py
@@ -0,0 +1,11 @@
+from sqlalchemy import Integer, Column
+
+from src.db.models.templates_.base import Base
+
+
+
+class WithIDBase(Base):
+    __abstract__ = True
+
+    id = Column(Integer, primary_key=True, autoincrement=True)
+
diff --git a/src/db/queries/implementations/core/get/html_content_info.py b/src/db/queries/implementations/core/get/html_content_info.py
index fb26a527..d647acc1 100644
--- a/src/db/queries/implementations/core/get/html_content_info.py
+++ b/src/db/queries/implementations/core/get/html_content_info.py
@@ -2,7 +2,7 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from src.db.dtos.url.html_content import URLHTMLContentInfo
-from src.db.models.instantiations.url.html_content import URLHTMLContent
+from src.db.models.instantiations.url.html.content.sqlalchemy import URLHTMLContent
 from src.db.queries.base.builder import QueryBuilderBase
 
 
diff --git a/src/db/statement_composer.py b/src/db/statement_composer.py
index 518aafc2..2e9a69e8 100644
--- a/src/db/statement_composer.py
+++ b/src/db/statement_composer.py
@@ -1,3 +1,4 @@
+from http import HTTPStatus
 from typing import Any
 
 from sqlalchemy import Select, select, exists, func, Subquery, and_, not_, ColumnElement
@@ -11,11 +12,13 @@
 from src.db.models.instantiations.link.task_url import LinkTaskURL
 from src.db.models.instantiations.link.url_agency.sqlalchemy import LinkURLAgency
 from src.db.models.instantiations.task.core import Task
-from src.db.models.instantiations.url.html_content import URLHTMLContent
+from src.db.models.instantiations.url.html.content.sqlalchemy import URLHTMLContent
 from src.db.models.instantiations.url.optional_data_source_metadata import URLOptionalDataSourceMetadata
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.models.instantiations.batch.sqlalchemy import Batch
+from src.db.models.instantiations.url.scrape_info.sqlalchemy import URLScrapeInfo
 from src.db.models.instantiations.url.suggestion.agency.auto import AutomatedUrlAgencySuggestion
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
 from src.db.types import UserSuggestionType
 
 
@@ -25,7 +28,7 @@ class StatementComposer:
     """
 
     @staticmethod
-    def pending_urls_without_html_data() -> Select:
+    def has_non_errored_urls_without_html_data() -> Select:
         exclude_subquery = (
             select(1).
             select_from(LinkTaskURL).
@@ -35,11 +38,15 @@ def pending_urls_without_html_data() -> Select:
             where(Task.task_status == BatchStatus.READY_TO_LABEL.value)
          )
         query = (
-            select(URL).
-            outerjoin(URLHTMLContent).
-            where(URLHTMLContent.id == None).
-            where(~exists(exclude_subquery)).
-            where(URL.outcome == URLStatus.PENDING.value)
+            select(URL)
+            .join(URLWebMetadata)
+            .outerjoin(URLScrapeInfo)
+            .where(
+                URLScrapeInfo.id == None,
+                ~exists(exclude_subquery),
+                URLWebMetadata.status_code == HTTPStatus.OK.value,
+                URLWebMetadata.content_type.like("%html%"),
+            )
             .options(
                 selectinload(URL.batch)
             )
diff --git a/src/db/templates/protocols/sa_correlated/core.py b/src/db/templates/protocols/sa_correlated/core.py
index 6b77c835..82475e60 100644
--- a/src/db/templates/protocols/sa_correlated/core.py
+++ b/src/db/templates/protocols/sa_correlated/core.py
@@ -1,7 +1,7 @@
 from abc import abstractmethod
 from typing import Protocol, runtime_checkable
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 @runtime_checkable
diff --git a/src/db/templates/protocols/sa_correlated/with_id.py b/src/db/templates/protocols/sa_correlated/with_id.py
index 4e3609e1..7e920e76 100644
--- a/src/db/templates/protocols/sa_correlated/with_id.py
+++ b/src/db/templates/protocols/sa_correlated/with_id.py
@@ -1,7 +1,7 @@
 from abc import abstractmethod
 from typing import Protocol, runtime_checkable
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 @runtime_checkable
diff --git a/src/external/pdap/client.py b/src/external/pdap/client.py
index 1447ae87..ee442600 100644
--- a/src/external/pdap/client.py
+++ b/src/external/pdap/client.py
@@ -4,7 +4,7 @@
 
 from src.core.tasks.scheduled.sync.agency.dtos.parameters import AgencySyncParameters
 from src.core.tasks.scheduled.sync.data_sources.params import DataSourcesSyncParameters
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmitApprovedURLTDO, SubmittedURLInfo
+from src.core.tasks.url.operators.submit_approved.tdo import SubmitApprovedURLTDO, SubmittedURLInfo
 from src.external.pdap.dtos.sync.agencies import AgenciesSyncResponseInnerInfo, AgenciesSyncResponseInfo
 from src.external.pdap.dtos.match_agency.post import MatchAgencyInfo
 from src.external.pdap.dtos.match_agency.response import MatchAgencyResponse
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/README.md b/src/external/url_request/README.md
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/request_interface/README.md
rename to src/external/url_request/README.md
diff --git a/src/external/url_request/__init__.py b/src/external/url_request/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/constants.py b/src/external/url_request/constants.py
similarity index 100%
rename from src/core/tasks/url/operators/url_html/scraper/request_interface/constants.py
rename to src/external/url_request/constants.py
diff --git a/src/external/url_request/core.py b/src/external/url_request/core.py
new file mode 100644
index 00000000..d17164d7
--- /dev/null
+++ b/src/external/url_request/core.py
@@ -0,0 +1,21 @@
+from aiohttp import ClientSession, ClientTimeout
+
+from src.external.url_request.dtos.url_response import URLResponseInfo
+from src.external.url_request.probe.core import URLProbeManager
+from src.external.url_request.probe.model import URLProbeResponse
+from src.external.url_request.request import fetch_urls
+
+
+class URLRequestInterface:
+
+    @staticmethod
+    async def make_requests_with_html(
+        urls: list[str],
+    ) -> list[URLResponseInfo]:
+        return await fetch_urls(urls)
+
+    @staticmethod
+    async def probe_urls(urls: list[str]) -> list[URLProbeResponse]:
+        async with ClientSession(timeout=ClientTimeout(total=30)) as session:
+            manager = URLProbeManager(session=session)
+            return await manager.probe_urls(urls=urls)
diff --git a/src/external/url_request/dtos/__init__.py b/src/external/url_request/dtos/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/request_resources.py b/src/external/url_request/dtos/request_resources.py
similarity index 74%
rename from src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/request_resources.py
rename to src/external/url_request/dtos/request_resources.py
index 62ad714a..01a5365f 100644
--- a/src/core/tasks/url/operators/url_html/scraper/request_interface/dtos/request_resources.py
+++ b/src/external/url_request/dtos/request_resources.py
@@ -4,7 +4,7 @@
 from aiohttp import ClientSession
 from playwright.async_api import async_playwright
 
-from src.core.tasks.url.operators.url_html.scraper.request_interface.constants import MAX_CONCURRENCY
+from src.external.url_request.constants import MAX_CONCURRENCY
 
 
 @dataclass
diff --git a/src/external/url_request/dtos/url_response.py b/src/external/url_request/dtos/url_response.py
new file mode 100644
index 00000000..57303a7c
--- /dev/null
+++ b/src/external/url_request/dtos/url_response.py
@@ -0,0 +1,12 @@
+from http import HTTPStatus
+from typing import Optional
+
+from pydantic import BaseModel
+
+
+class URLResponseInfo(BaseModel):
+    success: bool
+    status: HTTPStatus | None = None
+    html: str | None = None
+    content_type: str | None = None
+    exception: str | None = None
diff --git a/src/external/url_request/probe/__init__.py b/src/external/url_request/probe/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/src/external/url_request/probe/core.py b/src/external/url_request/probe/core.py
new file mode 100644
index 00000000..0b5bb934
--- /dev/null
+++ b/src/external/url_request/probe/core.py
@@ -0,0 +1,43 @@
+import asyncio
+
+from aiohttp import ClientSession, ClientResponseError
+
+from src.external.url_request.probe.format import format_client_response, format_client_response_error, format_error
+from src.external.url_request.probe.model import URLProbeResponse
+from tqdm.asyncio import tqdm_asyncio
+
+class URLProbeManager:
+
+    def __init__(
+        self,
+        session: ClientSession
+    ):
+        self.session = session
+
+    async def probe_urls(self, urls: list[str]) -> list[URLProbeResponse]:
+        return await tqdm_asyncio.gather(*[self.probe_url(url) for url in urls])
+
+    async def probe_url(self, url: str) -> URLProbeResponse:
+        result = await self.head(url)
+        if result.error is None:
+            return result
+        return await self.get(url)
+
+
+    async def head(self, url: str) -> URLProbeResponse:
+        try:
+            async with self.session.head(url) as response:
+                return format_client_response(url, response=response)
+        except ClientResponseError as e:
+            return format_client_response_error(url, error=e)
+        except Exception as e:
+            return format_error(url, error=e)
+
+    async def get(self, url: str) -> URLProbeResponse:
+        try:
+            async with self.session.get(url) as response:
+                return format_client_response(url, response=response)
+        except ClientResponseError as e:
+            return format_client_response_error(url, error=e)
+        except Exception as e:
+            return format_error(url, error=e)
\ No newline at end of file
diff --git a/src/external/url_request/probe/format.py b/src/external/url_request/probe/format.py
new file mode 100644
index 00000000..65430c1e
--- /dev/null
+++ b/src/external/url_request/probe/format.py
@@ -0,0 +1,32 @@
+from aiohttp import ClientResponse, ClientResponseError
+
+from src.external.url_request.probe.model import URLProbeResponse
+
+
+def format_content_type(content_type: str) -> str:
+    return content_type.split(";")[0].strip()
+
+def format_client_response(url: str, response: ClientResponse) -> URLProbeResponse:
+    return URLProbeResponse(
+        url=url,
+        status_code=response.status,
+        content_type=format_content_type(
+            response.headers.get("content-type")
+        )
+    )
+
+def format_client_response_error(url: str, error: ClientResponseError) -> URLProbeResponse:
+    return URLProbeResponse(
+        url=url,
+        status_code=error.status,
+        content_type=None,
+        error=str(error)
+    )
+
+def format_error(url: str, error: Exception) -> URLProbeResponse:
+    return URLProbeResponse(
+        url=url,
+        status_code=None,
+        content_type=None,
+        error=str(error)
+    )
\ No newline at end of file
diff --git a/src/external/url_request/probe/model.py b/src/external/url_request/probe/model.py
new file mode 100644
index 00000000..27caa680
--- /dev/null
+++ b/src/external/url_request/probe/model.py
@@ -0,0 +1,22 @@
+from pydantic import BaseModel, model_validator
+
+
+class URLProbeResponse(BaseModel):
+    url: str
+    status_code: int | None
+    content_type: str | None
+    error: str | None = None
+
+    @model_validator(mode='after')
+    def check_error_mutually_exclusive_with_content(self):
+        if self.error is None:
+            if self.content_type is None:
+                raise ValueError('Content type required if no error')
+            if self.status_code is None:
+                raise ValueError('Status code required if no error')
+            return self
+
+        if self.content_type is not None:
+            raise ValueError('Content type mutually exclusive with error')
+
+        return self
diff --git a/src/external/url_request/request.py b/src/external/url_request/request.py
new file mode 100644
index 00000000..40fc2dd6
--- /dev/null
+++ b/src/external/url_request/request.py
@@ -0,0 +1,91 @@
+"""Functions for making HTTP requests."""
+from http import HTTPStatus
+
+from aiohttp import ClientSession, ClientResponseError
+from playwright.async_api import async_playwright
+from tqdm.asyncio import tqdm
+
+from src.external.url_request.constants import HTML_CONTENT_TYPE
+from src.external.url_request.dtos.request_resources import RequestResources
+
+from src.external.url_request.dtos.url_response import URLResponseInfo
+
+
+async def execute_get(
+    session: ClientSession,
+    url: str
+) -> URLResponseInfo:
+    try:
+        async with session.get(url, timeout=20) as response:
+            response.raise_for_status()
+            text = await response.text()
+            return URLResponseInfo(
+                success=True,
+                html=text,
+                content_type=response.headers.get("content-type"),
+                status=HTTPStatus(response.status)
+            )
+    except ClientResponseError as e:
+        return URLResponseInfo(success=False, status=HTTPStatus(e.status), exception=str(e))
+
+
+async def get_response(session: ClientSession, url: str) -> URLResponseInfo:
+    try:
+        return await execute_get(session, url)
+    except Exception as e:
+        print(f"An error occurred while fetching {url}: {e}")
+        return URLResponseInfo(success=False, exception=str(e))
+
+
+async def make_simple_requests(urls: list[str]) -> list[URLResponseInfo]:
+    async with ClientSession() as session:
+        tasks = [get_response(session, url) for url in urls]
+        results = await tqdm.gather(*tasks)
+        return results
+
+
+async def get_dynamic_html_content(
+    rr: RequestResources,
+    url: str
+) -> URLResponseInfo | None:
+    # For HTML responses, attempt to load the page to check for dynamic html content
+    async with rr.semaphore:
+        page = await rr.browser.new_page()
+        try:
+            await page.goto(url)
+            await page.wait_for_load_state("networkidle")
+            html_content = await page.content()
+            return URLResponseInfo(
+                success=True,
+                html=html_content,
+                content_type=HTML_CONTENT_TYPE,
+                status=HTTPStatus.OK
+            )
+        except Exception as e:
+            return URLResponseInfo(success=False, exception=str(e))
+        finally:
+            await page.close()
+
+
+async def fetch_and_render(
+    rr: RequestResources,
+    url: str
+) -> URLResponseInfo | None:
+    simple_response = await get_response(rr.session, url)
+    if not simple_response.success:
+        return simple_response
+
+    if simple_response.content_type != HTML_CONTENT_TYPE:
+        return simple_response
+
+    return await get_dynamic_html_content(rr, url)
+
+
+async def fetch_urls(urls: list[str]) -> list[URLResponseInfo]:
+    async with ClientSession() as session:
+        async with async_playwright() as playwright:
+            browser = await playwright.chromium.launch(headless=True)
+            request_resources = RequestResources(session=session, browser=browser)
+            tasks = [fetch_and_render(request_resources, url) for url in urls]
+            results = await tqdm.gather(*tasks)
+            return results
diff --git a/src/util/alembic_helpers.py b/src/util/alembic_helpers.py
index 3eb18773..13327bfd 100644
--- a/src/util/alembic_helpers.py
+++ b/src/util/alembic_helpers.py
@@ -61,7 +61,8 @@ def id_column() -> sa.Column:
         sa.Integer(),
         primary_key=True,
         autoincrement=True,
-        nullable=False
+        nullable=False,
+        comment='The primary identifier for the row.'
     )
 
 def created_at_column() -> sa.Column:
@@ -70,7 +71,8 @@ def created_at_column() -> sa.Column:
         'created_at',
         sa.DateTime(),
         server_default=sa.text('now()'),
-        nullable=False
+        nullable=False,
+        comment='The time the row was created.'
     )
 
 def updated_at_column() -> sa.Column:
@@ -80,7 +82,8 @@ def updated_at_column() -> sa.Column:
         sa.DateTime(),
         server_default=sa.text('now()'),
         server_onupdate=sa.text('now()'),
-        nullable=False
+        nullable=False,
+        comment='The last time the row was updated.'
     )
 
 def url_id_column() -> sa.Column:
@@ -91,7 +94,8 @@ def url_id_column() -> sa.Column:
             'urls.id',
             ondelete='CASCADE'
         ),
-        nullable=False
+        nullable=False,
+        comment='A foreign key to the `urls` table.'
     )
 
 def batch_id_column(nullable=False) -> sa.Column:
@@ -102,5 +106,6 @@ def batch_id_column(nullable=False) -> sa.Column:
             'batches.id',
             ondelete='CASCADE'
         ),
-        nullable=nullable
+        nullable=nullable,
+        comment='A foreign key to the `batches` table.'
     )
\ No newline at end of file
diff --git a/start_mirrored_local_app.py b/start_mirrored_local_app.py
index 5199fba2..9190fece 100644
--- a/start_mirrored_local_app.py
+++ b/start_mirrored_local_app.py
@@ -27,15 +27,8 @@ def main():
     # Check cache if exists and
     checker = TimestampChecker()
     data_dump_container = docker_manager.run_container(data_dumper_docker_info)
-    if checker.last_run_within_24_hours():
-        print("Last run within 24 hours, skipping dump...")
-    else:
-        data_dump_container.run_command(
-            DUMP_SH_DOCKER_PATH,
-        )
-    data_dump_container.run_command(
-        RESTORE_SH_DOCKER_PATH,
-    )
+    _run_dump_if_longer_than_24_hours(checker, data_dump_container)
+    _run_database_restore(data_dump_container)
     print("Stopping datadumper container")
     data_dump_container.stop()
     checker.set_last_run_time()
@@ -44,6 +37,10 @@ def main():
     apply_migrations()
 
     # Run `fastapi dev main.py`
+    _run_fast_api(docker_manager)
+
+
+def _run_fast_api(docker_manager: DockerManager) -> None:
     try:
         uvicorn.run(
             "src.api.main:app",
@@ -59,8 +56,22 @@ def main():
         print("Containers stopped.")
 
 
+def _run_database_restore(data_dump_container) -> None:
+    data_dump_container.run_command(
+        RESTORE_SH_DOCKER_PATH,
+    )
 
 
+def _run_dump_if_longer_than_24_hours(
+    checker: TimestampChecker,
+    data_dump_container
+) -> None:
+    if checker.last_run_within_24_hours():
+        print("Last run within 24 hours, skipping dump...")
+        return
+    data_dump_container.run_command(
+        DUMP_SH_DOCKER_PATH,
+    )
 
 
 if __name__ == "__main__":
diff --git a/tests/automated/integration/api/test_annotate.py b/tests/automated/integration/api/test_annotate.py
index 690b83e4..78dd0f55 100644
--- a/tests/automated/integration/api/test_annotate.py
+++ b/tests/automated/integration/api/test_annotate.py
@@ -9,7 +9,7 @@
 from src.api.endpoints.annotate.dtos.record_type.response import GetNextRecordTypeAnnotationResponseOuterInfo
 from src.api.endpoints.annotate.relevance.get.dto import GetNextRelevanceAnnotationResponseOuterInfo
 from src.api.endpoints.annotate.relevance.post.dto import RelevanceAnnotationPostInfo
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
 from src.db.dtos.url.insert import InsertURLsInfo
 from src.db.dtos.url.mapping import URLMapping
 from src.db.models.instantiations.url.suggestion.agency.user import UserUrlAgencySuggestion
diff --git a/tests/automated/integration/db/client/test_delete_url_updated_at.py b/tests/automated/integration/db/client/test_delete_url_updated_at.py
index 620e0318..f0bebaaf 100644
--- a/tests/automated/integration/db/client/test_delete_url_updated_at.py
+++ b/tests/automated/integration/db/client/test_delete_url_updated_at.py
@@ -1,4 +1,4 @@
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from tests.helpers.data_creator.core import DBDataCreator
 
 
diff --git a/tests/automated/integration/db/client/test_insert_urls.py b/tests/automated/integration/db/client/test_insert_urls.py
index 9fd65eed..28a2483d 100644
--- a/tests/automated/integration/db/client/test_insert_urls.py
+++ b/tests/automated/integration/db/client/test_insert_urls.py
@@ -3,7 +3,7 @@
 from src.core.enums import BatchStatus
 from src.db.models.instantiations.batch.pydantic import BatchInfo
 from src.db.models.instantiations.link.batch_url import LinkBatchURL
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 
 
diff --git a/tests/automated/integration/db/structure/testers/table.py b/tests/automated/integration/db/structure/testers/table.py
index aed5d3a5..a91c0837 100644
--- a/tests/automated/integration/db/structure/testers/table.py
+++ b/tests/automated/integration/db/structure/testers/table.py
@@ -7,7 +7,7 @@
 from sqlalchemy.exc import DataError
 
 from src.db.helpers.connect import get_postgres_connection_string
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 from tests.automated.integration.db.structure.testers.models.column import ColumnTester
 from tests.automated.integration.db.structure.types import ConstraintTester, SATypes
 
diff --git a/tests/automated/integration/html_tag_collector/test_root_url_cache.py b/tests/automated/integration/html_tag_collector/test_root_url_cache.py
index 151985cf..0add726e 100644
--- a/tests/automated/integration/html_tag_collector/test_root_url_cache.py
+++ b/tests/automated/integration/html_tag_collector/test_root_url_cache.py
@@ -1,7 +1,7 @@
 import pytest
 
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.core import RootURLCache
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.dtos.response import RootURLCacheResponseInfo
+from src.core.tasks.url.operators.html.scraper.root_url_cache.core import RootURLCache
+from src.core.tasks.url.operators.html.scraper.root_url_cache.dtos.response import RootURLCacheResponseInfo
 
 
 async def mock_get_request(url: str) -> RootURLCacheResponseInfo:
diff --git a/tests/automated/integration/tasks/scheduled/huggingface/setup/queries/setup.py b/tests/automated/integration/tasks/scheduled/huggingface/setup/queries/setup.py
index dc0a3452..8e345d51 100644
--- a/tests/automated/integration/tasks/scheduled/huggingface/setup/queries/setup.py
+++ b/tests/automated/integration/tasks/scheduled/huggingface/setup/queries/setup.py
@@ -1,6 +1,6 @@
 from sqlalchemy.ext.asyncio import AsyncSession
 
-from src.db.models.instantiations.url.compressed_html import URLCompressedHTML
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.db.queries.base.builder import QueryBuilderBase
 from src.db.utils.compression import compress_html
diff --git a/tests/automated/integration/tasks/url/agency_identification/happy_path/test_happy_path.py b/tests/automated/integration/tasks/url/agency_identification/happy_path/test_happy_path.py
index 5cae5a26..7eb5a7f9 100644
--- a/tests/automated/integration/tasks/url/agency_identification/happy_path/test_happy_path.py
+++ b/tests/automated/integration/tasks/url/agency_identification/happy_path/test_happy_path.py
@@ -26,7 +26,6 @@ async def test_agency_identification_task(
 ):
     """Test full flow of AgencyIdentificationTaskOperator"""
 
-
     # Confirm does not yet meet prerequisites
     assert not await operator.meets_task_prerequisites()
 
diff --git a/tests/automated/integration/tasks/url/duplicate/test_url_duplicate_task.py b/tests/automated/integration/tasks/url/duplicate/test_url_duplicate_task.py
index bd66e409..2f4e64b5 100644
--- a/tests/automated/integration/tasks/url/duplicate/test_url_duplicate_task.py
+++ b/tests/automated/integration/tasks/url/duplicate/test_url_duplicate_task.py
@@ -3,7 +3,7 @@
 
 import pytest
 
-from src.core.tasks.url.operators.url_duplicate.core import URLDuplicateTaskOperator
+from src.core.tasks.url.operators.duplicate.core import URLDuplicateTaskOperator
 from src.db.dtos.url.mapping import URLMapping
 from src.db.models.instantiations.url.checked_for_duplicate import URLCheckedForDuplicate
 from src.db.models.instantiations.url.core.sqlalchemy import URL
diff --git a/tests/automated/integration/tasks/url/html/asserts.py b/tests/automated/integration/tasks/url/html/asserts.py
deleted file mode 100644
index 9ca241cd..00000000
--- a/tests/automated/integration/tasks/url/html/asserts.py
+++ /dev/null
@@ -1,52 +0,0 @@
-from src.api.endpoints.task.by_id.dto import TaskInfo
-from src.collectors.enums import URLStatus
-from src.core.tasks.base.run_info import TaskOperatorRunInfo
-from src.db.client.async_ import AsyncDatabaseClient
-from src.db.enums import TaskType
-from tests.automated.integration.tasks.url.html.mocks.constants import MOCK_HTML_CONTENT
-
-
-async def assert_success_url_has_two_html_content_entries(
-    adb: AsyncDatabaseClient,
-    run_info,
-    url_id: int
-):
-    await adb.link_urls_to_task(task_id=run_info.task_id, url_ids=run_info.linked_url_ids)
-    hci = await adb.get_html_content_info(url_id=url_id)
-    assert len(hci) == 2
-
-async def assert_url_has_one_compressed_html_content_entry(
-    adb: AsyncDatabaseClient,
-    url_id: int
-):
-    html = await adb.get_html_for_url(url_id=url_id)
-    assert html == MOCK_HTML_CONTENT
-
-async def assert_success_url_has_one_compressed_html_content_entry(
-    adb: AsyncDatabaseClient,
-    run_info,
-    url_id: int
-):
-    await adb.link_urls_to_task(task_id=run_info.task_id, url_ids=run_info.linked_url_ids)
-    hci = await adb.get_html_content_info(url_id=url_id)
-    assert len(hci) == 1
-
-async def assert_404_url_has_404_status(
-    adb: AsyncDatabaseClient,
-    url_id: int
-):
-    url_info_404 = await adb.get_url_info_by_id(url_id=url_id)
-    assert url_info_404.outcome == URLStatus.NOT_FOUND
-
-
-def assert_task_has_one_url_error(task_info):
-    assert len(task_info.url_errors) == 1
-    assert task_info.url_errors[0].error == "test error"
-
-
-def assert_task_type_is_html(task_info):
-    assert task_info.task_type == TaskType.HTML
-
-
-def assert_html_task_ran_without_error(task_info: TaskInfo):
-    assert task_info.error_info is None
diff --git a/tests/automated/integration/tasks/url/html/check/__init__.py b/tests/automated/integration/tasks/url/html/check/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/html/check/manager.py b/tests/automated/integration/tasks/url/html/check/manager.py
new file mode 100644
index 00000000..71a48b42
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/check/manager.py
@@ -0,0 +1,68 @@
+from src.db.client.async_ import AsyncDatabaseClient
+from src.db.models.instantiations.url.core.sqlalchemy import URL
+from src.db.models.instantiations.url.html.compressed.sqlalchemy import URLCompressedHTML
+from src.db.models.instantiations.url.scrape_info.sqlalchemy import URLScrapeInfo
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from tests.automated.integration.tasks.url.html.setup.models.record import TestURLHTMLTaskSetupRecord
+
+
+class TestURLHTMLTaskCheckManager:
+
+    def __init__(
+        self,
+        adb_client: AsyncDatabaseClient,
+        records: list[TestURLHTMLTaskSetupRecord]
+    ):
+        self.adb_client = adb_client
+        self.records = records
+        self._id_to_entry = {record.url_id: record.entry for record in records}
+
+    async def check(self):
+        await self._check_has_html()
+        await self._check_scrape_status()
+        await self._check_has_same_url_status()
+        await self._check_marked_as_404()
+
+    async def _check_has_html(self) -> None:
+        urls_with_html = [
+            record.url_id
+            for record in self.records
+            if record.entry.expected_result.has_html
+        ]
+
+        compressed_html_list: list[URLCompressedHTML] = await self.adb_client.get_all(URLCompressedHTML)
+        assert len(compressed_html_list) == len(urls_with_html)
+        for compressed_html in compressed_html_list:
+            assert compressed_html.url_id in urls_with_html
+
+    async def _check_scrape_status(self) -> None:
+        urls_with_scrape_status = [
+            record.url_id
+            for record in self.records
+            if record.entry.expected_result.scrape_status is not None
+        ]
+
+        url_scrape_info_list: list[URLScrapeInfo] = await self.adb_client.get_all(URLScrapeInfo)
+        assert len(url_scrape_info_list) == len(urls_with_scrape_status)
+        for url_scrape_info in url_scrape_info_list:
+            assert url_scrape_info.url_id in urls_with_scrape_status
+            entry = self._id_to_entry[url_scrape_info.url_id]
+            expected_scrape_status = entry.expected_result.scrape_status
+            assert url_scrape_info.status == expected_scrape_status
+
+    async def _check_has_same_url_status(self):
+        urls: list[URL] = await self.adb_client.get_all(URL)
+        for url in urls:
+            entry = self._id_to_entry[url.id]
+            if entry.expected_result.web_metadata_status_marked_404:
+                continue
+            assert url.outcome == entry.url_info.status, f"URL {url.url} has outcome {url.outcome} instead of {entry.url_info.status}"
+
+    async def _check_marked_as_404(self):
+        web_metadata_list: list[URLWebMetadata] = await self.adb_client.get_all(
+            URLWebMetadata
+        )
+        for web_metadata in web_metadata_list:
+            entry = self._id_to_entry[web_metadata.url_id]
+            if entry.expected_result.web_metadata_status_marked_404:
+                assert web_metadata.status_code == 404, f"URL {entry.url_info.url} has status code {web_metadata.status_code} instead of 404"
diff --git a/tests/automated/integration/tasks/url/html/mocks/constants.py b/tests/automated/integration/tasks/url/html/mocks/constants.py
deleted file mode 100644
index 0b60341d..00000000
--- a/tests/automated/integration/tasks/url/html/mocks/constants.py
+++ /dev/null
@@ -1,3 +0,0 @@
-
-MOCK_HTML_CONTENT = "<html></html>"
-MOCK_CONTENT_TYPE = "text/html"
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/html/mocks/methods.py b/tests/automated/integration/tasks/url/html/mocks/methods.py
index dd623ee8..d6799eea 100644
--- a/tests/automated/integration/tasks/url/html/mocks/methods.py
+++ b/tests/automated/integration/tasks/url/html/mocks/methods.py
@@ -1,55 +1,9 @@
-from http import HTTPStatus
 from typing import Optional
 
-from aiohttp import ClientResponseError, RequestInfo
-
-from src.core.tasks.url.operators.url_html.scraper.parser.dtos.response_html import ResponseHTMLInfo
-from src.core.tasks.url.operators.url_html.scraper.request_interface.dtos.url_response import URLResponseInfo
-from tests.automated.integration.tasks.url.html.mocks.constants import MOCK_CONTENT_TYPE, MOCK_HTML_CONTENT
-
-
-async def mock_make_requests(self, urls: list[str]) -> list[URLResponseInfo]:
-    results = []
-    for idx, url in enumerate(urls):
-        # Second result should produce a 404
-        if idx == 1:
-            results.append(
-                URLResponseInfo(
-                    success=False,
-                    content_type=MOCK_CONTENT_TYPE,
-                    exception=str(ClientResponseError(
-                        request_info=RequestInfo(
-                            url=url,
-                            method="GET",
-                            real_url=url,
-                            headers={},
-                        ),
-                        code=HTTPStatus.NOT_FOUND.value,
-                        history=(None,),
-                    )),
-                    status=HTTPStatus.NOT_FOUND
-                )
-            )
-            continue
-
-        if idx == 2:
-            # 3rd result should produce an error
-            results.append(
-                URLResponseInfo(
-                    success=False,
-                    exception=str(ValueError("test error")),
-                    content_type=MOCK_CONTENT_TYPE
-                ))
-        else:
-            # All other results should succeed
-            results.append(URLResponseInfo(
-                html=MOCK_HTML_CONTENT, success=True, content_type=MOCK_CONTENT_TYPE))
-    return results
+from src.core.tasks.url.operators.html.scraper.parser.dtos.response_html import ResponseHTMLInfo
 
 
 async def mock_parse(self, url: str, html_content: str, content_type: str) -> ResponseHTMLInfo:
-    assert html_content == MOCK_HTML_CONTENT
-    assert content_type == MOCK_CONTENT_TYPE
     return ResponseHTMLInfo(
         url=url,
         title="fake title",
diff --git a/tests/automated/integration/tasks/url/html/mocks/url_request_interface/__init__.py b/tests/automated/integration/tasks/url/html/mocks/url_request_interface/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/html/mocks/url_request_interface/core.py b/tests/automated/integration/tasks/url/html/mocks/url_request_interface/core.py
new file mode 100644
index 00000000..a8dde5b5
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/mocks/url_request_interface/core.py
@@ -0,0 +1,11 @@
+from src.external.url_request.dtos.url_response import URLResponseInfo
+from tests.automated.integration.tasks.url.html.mocks.url_request_interface.setup import setup_url_to_response_info
+
+
+class MockURLRequestInterface:
+
+    def __init__(self):
+        self._url_to_response_info: dict[str, URLResponseInfo] = setup_url_to_response_info()
+
+    async def make_requests_with_html(self, urls: list[str]) -> list[URLResponseInfo]:
+        return [self._url_to_response_info[url] for url in urls]
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/html/mocks/url_request_interface/setup.py b/tests/automated/integration/tasks/url/html/mocks/url_request_interface/setup.py
new file mode 100644
index 00000000..cff46013
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/mocks/url_request_interface/setup.py
@@ -0,0 +1,45 @@
+from http import HTTPStatus
+
+from src.external.url_request.dtos.url_response import URLResponseInfo
+from tests.automated.integration.tasks.url.html.setup.data import TEST_ENTRIES
+from tests.automated.integration.tasks.url.html.setup.models.entry import TestURLHTMLTaskSetupEntry, TestErrorType
+from tests.helpers.simple_test_data_functions import generate_test_html
+
+
+def _get_success(
+    entry: TestURLHTMLTaskSetupEntry
+) -> bool:
+    if entry.give_error is not None:
+        return False
+    return True
+
+def get_http_status(
+    entry: TestURLHTMLTaskSetupEntry
+) -> HTTPStatus:
+    if entry.give_error is None:
+        return HTTPStatus.OK
+    if entry.give_error == TestErrorType.HTTP_404:
+        return HTTPStatus.NOT_FOUND
+    return HTTPStatus.INTERNAL_SERVER_ERROR
+
+def _get_content_type(
+    entry: TestURLHTMLTaskSetupEntry
+) -> str | None:
+    if entry.give_error is not None:
+        return None
+    return "text/html"
+
+
+def setup_url_to_response_info(
+) -> dict[str, URLResponseInfo]:
+    d = {}
+    for entry in TEST_ENTRIES:
+        response_info = URLResponseInfo(
+            success=_get_success(entry),
+            status=get_http_status(entry),
+            html=generate_test_html() if _get_success(entry) else None,
+            content_type=_get_content_type(entry),
+            exception=None if _get_success(entry) else "Error"
+        )
+        d[entry.url_info.url] = response_info
+    return d
diff --git a/tests/automated/integration/tasks/url/html/setup.py b/tests/automated/integration/tasks/url/html/setup.py
deleted file mode 100644
index e6a4de81..00000000
--- a/tests/automated/integration/tasks/url/html/setup.py
+++ /dev/null
@@ -1,41 +0,0 @@
-import types
-
-from src.core.tasks.url.operators.url_html.core import URLHTMLTaskOperator
-from src.core.tasks.url.operators.url_html.scraper.parser.core import HTMLResponseParser
-
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.core import RootURLCache
-from src.db.client.async_ import AsyncDatabaseClient
-from tests.automated.integration.tasks.url.html.mocks.methods import mock_make_requests, mock_get_from_cache, mock_parse
-
-
-async def setup_mocked_url_request_interface() -> URLRequestInterface:
-    url_request_interface = URLRequestInterface()
-    url_request_interface.make_requests_with_html = types.MethodType(mock_make_requests, url_request_interface)
-    return url_request_interface
-
-
-async def setup_mocked_root_url_cache() -> RootURLCache:
-    mock_root_url_cache = RootURLCache()
-    mock_root_url_cache.get_from_cache = types.MethodType(mock_get_from_cache, mock_root_url_cache)
-    return mock_root_url_cache
-
-
-async def setup_urls(db_data_creator) -> list[int]:
-    batch_id = db_data_creator.batch()
-    url_mappings = db_data_creator.urls(batch_id=batch_id, url_count=3).url_mappings
-    url_ids = [url_info.url_id for url_info in url_mappings]
-    return url_ids
-
-
-async def setup_operator() -> URLHTMLTaskOperator:
-    html_parser = HTMLResponseParser(
-        root_url_cache=await setup_mocked_root_url_cache()
-    )
-    html_parser.parse = types.MethodType(mock_parse, html_parser)
-    operator = URLHTMLTaskOperator(
-        adb_client=AsyncDatabaseClient(),
-        url_request_interface=await setup_mocked_url_request_interface(),
-        html_parser=html_parser
-    )
-    return operator
diff --git a/tests/automated/integration/tasks/url/html/setup/__init__.py b/tests/automated/integration/tasks/url/html/setup/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/html/setup/data.py b/tests/automated/integration/tasks/url/html/setup/data.py
new file mode 100644
index 00000000..9c488484
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/setup/data.py
@@ -0,0 +1,94 @@
+from http import HTTPStatus
+
+from src.collectors.enums import URLStatus
+from src.db.models.instantiations.url.scrape_info.enums import ScrapeStatus
+from tests.automated.integration.tasks.url.html.setup.models.entry import TestURLHTMLTaskSetupEntry, TestURLInfo, \
+    TestWebMetadataInfo, ExpectedResult, TestErrorType
+
+TEST_ENTRIES = [
+    # URLs that give 200s should be updated with the appropriate scrape status
+    #  and their html should be stored
+    TestURLHTMLTaskSetupEntry(
+        url_info=TestURLInfo(
+            url="https://happy-path.com/pending",
+            status=URLStatus.PENDING
+        ),
+        web_metadata_info=TestWebMetadataInfo(
+            accessed=True,
+            content_type="text/html",
+            response_code=HTTPStatus.OK,
+            error_message=None
+        ),
+        expected_result=ExpectedResult(
+            has_html=True,  # Test for both compressed HTML and content metadata
+            scrape_status=ScrapeStatus.SUCCESS
+        )
+    ),
+    # URLs that give 404s should be updated with the appropriate scrape status
+    #  and their web metadata status should be updated to 404
+    TestURLHTMLTaskSetupEntry(
+        url_info=TestURLInfo(
+            url="https://not-found-path.com/submitted",
+            status=URLStatus.ERROR
+        ),
+        web_metadata_info=TestWebMetadataInfo(
+            accessed=True,
+            content_type="text/html",
+            response_code=HTTPStatus.OK,
+            error_message=None
+        ),
+        give_error=TestErrorType.HTTP_404,
+        expected_result=ExpectedResult(
+            has_html=False,
+            scrape_status=ScrapeStatus.ERROR,
+            web_metadata_status_marked_404=True
+        )
+    ),
+    # URLs that give errors should be updated with the appropriate scrape status
+    TestURLHTMLTaskSetupEntry(
+        url_info=TestURLInfo(
+            url="https://error-path.com/submitted",
+            status=URLStatus.ERROR
+        ),
+        web_metadata_info=TestWebMetadataInfo(
+            accessed=True,
+            content_type="text/html",
+            response_code=HTTPStatus.OK,
+            error_message=None
+        ),
+        give_error=TestErrorType.SCRAPER,
+        expected_result=ExpectedResult(
+            has_html=False,
+            scrape_status=ScrapeStatus.ERROR
+        )
+    ),
+    # URLs with non-200 web metadata should not be processed
+    TestURLHTMLTaskSetupEntry(
+        url_info=TestURLInfo(
+            url="https://not-200-path.com/submitted",
+            status=URLStatus.PENDING
+        ),
+        web_metadata_info=TestWebMetadataInfo(
+            accessed=True,
+            content_type="text/html",
+            response_code=HTTPStatus.PERMANENT_REDIRECT,
+            error_message=None
+        ),
+        expected_result=ExpectedResult(
+            has_html=False,
+            scrape_status=None
+        )
+    ),
+    # URLs with no web metadata should not be processed
+    TestURLHTMLTaskSetupEntry(
+        url_info=TestURLInfo(
+            url="https://no-web-metadata.com/submitted",
+            status=URLStatus.PENDING
+        ),
+        web_metadata_info=None,
+        expected_result=ExpectedResult(
+            has_html=False,
+            scrape_status=None
+        )
+    )
+]
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/html/setup/manager.py b/tests/automated/integration/tasks/url/html/setup/manager.py
new file mode 100644
index 00000000..8e679a57
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/setup/manager.py
@@ -0,0 +1,87 @@
+import types
+
+from src.core.enums import RecordType
+from src.core.tasks.url.operators.html.core import URLHTMLTaskOperator
+from src.core.tasks.url.operators.html.scraper.parser.core import HTMLResponseParser
+from src.core.tasks.url.operators.html.scraper.root_url_cache.core import RootURLCache
+from src.db.client.async_ import AsyncDatabaseClient
+from src.db.models.instantiations.url.core.pydantic.insert import URLInsertModel
+from src.db.models.instantiations.url.web_metadata.pydantic import URLWebMetadataPydantic
+from tests.automated.integration.tasks.url.html.mocks.methods import mock_get_from_cache, mock_parse
+from tests.automated.integration.tasks.url.html.mocks.url_request_interface.core import MockURLRequestInterface
+from tests.automated.integration.tasks.url.html.setup.data import TEST_ENTRIES
+from tests.automated.integration.tasks.url.html.setup.models.record import TestURLHTMLTaskSetupRecord
+
+
+class TestURLHTMLTaskSetupManager:
+
+    def __init__(self, adb_client: AsyncDatabaseClient):
+        self.adb_client = adb_client
+
+
+    async def setup(self) -> list[TestURLHTMLTaskSetupRecord]:
+
+        records = await self._setup_urls()
+        await self.setup_web_metadata(records)
+        return records
+
+    async def _setup_urls(self) -> list[TestURLHTMLTaskSetupRecord]:
+        url_insert_models: list[URLInsertModel] = []
+        for entry in TEST_ENTRIES:
+            url_insert_model = URLInsertModel(
+                outcome=entry.url_info.status,
+                url=entry.url_info.url,
+                name=f"Test for {entry.url_info.url}",
+                record_type=RecordType.RESOURCES
+            )
+            url_insert_models.append(url_insert_model)
+        url_ids = await self.adb_client.bulk_insert(url_insert_models, return_ids=True)
+
+        records = []
+        for url_id, entry in zip(url_ids, TEST_ENTRIES):
+            record = TestURLHTMLTaskSetupRecord(
+                url_id=url_id,
+                entry=entry
+            )
+            records.append(record)
+        return records
+
+    async def setup_web_metadata(
+        self,
+        records: list[TestURLHTMLTaskSetupRecord]
+    ) -> None:
+        models = []
+        for record in records:
+            entry = record.entry
+            web_metadata_info = entry.web_metadata_info
+            if web_metadata_info is None:
+                continue
+            model = URLWebMetadataPydantic(
+                url_id=record.url_id,
+                accessed=web_metadata_info.accessed,
+                status_code=web_metadata_info.response_code.value,
+                content_type=web_metadata_info.content_type,
+                error_message=web_metadata_info.error_message
+            )
+            models.append(model)
+        await self.adb_client.bulk_insert(models)
+
+
+
+async def setup_mocked_root_url_cache() -> RootURLCache:
+    mock_root_url_cache = RootURLCache()
+    mock_root_url_cache.get_from_cache = types.MethodType(mock_get_from_cache, mock_root_url_cache)
+    return mock_root_url_cache
+
+
+async def setup_operator() -> URLHTMLTaskOperator:
+    html_parser = HTMLResponseParser(
+        root_url_cache=await setup_mocked_root_url_cache()
+    )
+    html_parser.parse = types.MethodType(mock_parse, html_parser)
+    operator = URLHTMLTaskOperator(
+        adb_client=AsyncDatabaseClient(),
+        url_request_interface=MockURLRequestInterface(),
+        html_parser=html_parser
+    )
+    return operator
diff --git a/tests/automated/integration/tasks/url/html/setup/models/__init__.py b/tests/automated/integration/tasks/url/html/setup/models/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/html/setup/models/entry.py b/tests/automated/integration/tasks/url/html/setup/models/entry.py
new file mode 100644
index 00000000..8cc2a8ad
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/setup/models/entry.py
@@ -0,0 +1,34 @@
+from enum import Enum
+from http import HTTPStatus
+
+from pydantic import BaseModel
+
+from src.collectors.enums import URLStatus
+from src.db.models.instantiations.url.scrape_info.enums import ScrapeStatus
+
+
+class TestErrorType(Enum):
+    SCRAPER = "scraper"
+    HTTP_404 = "http-404"
+
+
+class TestWebMetadataInfo(BaseModel):
+    accessed: bool
+    content_type: str | None
+    response_code: HTTPStatus
+    error_message: str | None
+
+class TestURLInfo(BaseModel):
+    url: str
+    status: URLStatus
+
+class ExpectedResult(BaseModel):
+    has_html: bool
+    scrape_status: ScrapeStatus | None  # Does not have scrape info if none
+    web_metadata_status_marked_404: bool = False
+
+class TestURLHTMLTaskSetupEntry(BaseModel):
+    url_info: TestURLInfo
+    web_metadata_info: TestWebMetadataInfo | None
+    give_error: TestErrorType | None = None
+    expected_result: ExpectedResult
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/html/setup/models/record.py b/tests/automated/integration/tasks/url/html/setup/models/record.py
new file mode 100644
index 00000000..7902dd81
--- /dev/null
+++ b/tests/automated/integration/tasks/url/html/setup/models/record.py
@@ -0,0 +1,8 @@
+from pydantic import BaseModel
+
+from tests.automated.integration.tasks.url.html.setup.models.entry import TestURLHTMLTaskSetupEntry
+
+
+class TestURLHTMLTaskSetupRecord(BaseModel):
+    url_id: int
+    entry: TestURLHTMLTaskSetupEntry
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/html/test_task.py b/tests/automated/integration/tasks/url/html/test_task.py
index 2592713f..fe059838 100644
--- a/tests/automated/integration/tasks/url/html/test_task.py
+++ b/tests/automated/integration/tasks/url/html/test_task.py
@@ -1,41 +1,34 @@
 import pytest
 
+from src.db.client.async_ import AsyncDatabaseClient
 from src.db.enums import TaskType
-from tests.automated.integration.tasks.url.html.asserts import assert_success_url_has_two_html_content_entries, assert_404_url_has_404_status, assert_task_has_one_url_error, \
-    assert_task_type_is_html, assert_html_task_ran_without_error, assert_url_has_one_compressed_html_content_entry
-from tests.automated.integration.tasks.asserts import assert_prereqs_not_met, assert_url_task_has_expected_run_info
-from tests.automated.integration.tasks.url.html.setup import setup_urls, setup_operator
-from tests.helpers.data_creator.core import DBDataCreator
+from tests.automated.integration.tasks.asserts import assert_prereqs_not_met, assert_prereqs_met, \
+    assert_task_ran_without_error
+from tests.automated.integration.tasks.url.html.check.manager import TestURLHTMLTaskCheckManager
+from tests.automated.integration.tasks.url.html.setup.manager import setup_operator, \
+    TestURLHTMLTaskSetupManager
 
 
 @pytest.mark.asyncio
-async def test_url_html_task(db_data_creator: DBDataCreator):
+async def test_url_html_task(adb_client_test: AsyncDatabaseClient):
+    setup = TestURLHTMLTaskSetupManager(adb_client_test)
 
     operator = await setup_operator()
 
     # No URLs were created, the prereqs should not be met
     await assert_prereqs_not_met(operator)
 
-    url_ids = await setup_urls(db_data_creator)
-    success_url_id = url_ids[0]
-    not_found_url_id = url_ids[1]
+    records = await setup.setup()
+    await assert_prereqs_met(operator)
 
-    task_id = await db_data_creator.adb_client.initiate_task(task_type=TaskType.HTML)
+    task_id = await adb_client_test.initiate_task(task_type=TaskType.HTML)
     run_info = await operator.run_task(task_id)
-    assert_url_task_has_expected_run_info(run_info, url_ids)
+    assert_task_ran_without_error(run_info)
 
-
-    task_info = await db_data_creator.adb_client.get_task_info(
-        task_id=operator.task_id
+    checker = TestURLHTMLTaskCheckManager(
+        adb_client=adb_client_test,
+        records=records
     )
+    await checker.check()
 
-    assert_html_task_ran_without_error(task_info)
-    assert_task_type_is_html(task_info)
-    assert_task_has_one_url_error(task_info)
-
-    adb = db_data_creator.adb_client
-    await assert_success_url_has_two_html_content_entries(adb, run_info, success_url_id)
-    await assert_url_has_one_compressed_html_content_entry(adb, success_url_id)
-    await assert_404_url_has_404_status(adb, not_found_url_id)
-
-
+    await assert_prereqs_not_met(operator)
diff --git a/tests/automated/integration/tasks/url/probe/__init__.py b/tests/automated/integration/tasks/url/probe/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/probe/conftest.py b/tests/automated/integration/tasks/url/probe/conftest.py
new file mode 100644
index 00000000..b8836a4b
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/conftest.py
@@ -0,0 +1,15 @@
+import pytest_asyncio
+
+from src.core.tasks.url.operators.probe.core import URLProbeTaskOperator
+from src.external.url_request.core import URLRequestInterface
+from tests.automated.integration.tasks.url.probe.constants import PATCH_ROOT
+from tests.automated.integration.tasks.url.probe.setup.mocks.probe_manager import MockURLProbeManager
+
+
+@pytest_asyncio.fixture
+async def operator(adb_client_test, monkeypatch):
+    monkeypatch.setattr(PATCH_ROOT, MockURLProbeManager)
+    yield URLProbeTaskOperator(
+        adb_client=adb_client_test,
+        url_request_interface=URLRequestInterface()
+    )
diff --git a/tests/automated/integration/tasks/url/probe/constants.py b/tests/automated/integration/tasks/url/probe/constants.py
new file mode 100644
index 00000000..6bc307e5
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/constants.py
@@ -0,0 +1,3 @@
+
+
+PATCH_ROOT = "src.external.url_request.core.URLProbeManager"
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/probe/setup/__init__.py b/tests/automated/integration/tasks/url/probe/setup/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/probe/setup/core.py b/tests/automated/integration/tasks/url/probe/setup/core.py
new file mode 100644
index 00000000..1884798b
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/core.py
@@ -0,0 +1,22 @@
+from src.core.enums import RecordType
+from src.db.client.async_ import AsyncDatabaseClient
+from src.db.models.instantiations.url.core.pydantic.insert import URLInsertModel
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from tests.automated.integration.tasks.url.probe.setup.data import SETUP_ENTRIES
+
+
+async def create_urls_in_db(
+    adb_client: AsyncDatabaseClient,
+) -> None:
+    record_types = [rt for rt in RecordType]
+    urls = []
+    for idx, entry in enumerate(SETUP_ENTRIES):
+        url = URLInsertModel(
+            url=entry.url,
+            outcome=entry.url_status,
+            name=f"test-url-probe-task-url-{idx}",
+            record_type=record_types[idx]
+        )
+        urls.append(url)
+    await adb_client.bulk_insert(urls)
+
diff --git a/tests/automated/integration/tasks/url/probe/setup/data.py b/tests/automated/integration/tasks/url/probe/setup/data.py
new file mode 100644
index 00000000..85ad2547
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/data.py
@@ -0,0 +1,36 @@
+from src.collectors.enums import URLStatus
+from tests.automated.integration.tasks.url.probe.setup.models.entry import TestURLProbeTaskEntry
+from tests.automated.integration.tasks.url.probe.setup.models.planned_response import URLProbePlannedResponse
+
+SETUP_ENTRIES: list[TestURLProbeTaskEntry] = [
+    TestURLProbeTaskEntry(
+        url="https://pending.com",
+        url_status=URLStatus.PENDING,
+        url_probe_response=URLProbePlannedResponse(
+            status_code=200,
+            content_type="text/html",
+            error=None
+        ),
+        expected_accessed=True
+    ),
+    TestURLProbeTaskEntry(
+        url="https://submitted.com",
+        url_status=URLStatus.SUBMITTED,
+        url_probe_response=URLProbePlannedResponse(
+            status_code=500,
+            content_type=None,
+            error="test error"
+        ),
+        expected_accessed=True
+    ),
+    TestURLProbeTaskEntry(
+        url="https://failure.com",
+        url_status=URLStatus.ERROR,
+        url_probe_response=URLProbePlannedResponse(
+            status_code=None,
+            content_type=None,
+            error="URL not found"
+        ),
+        expected_accessed=False
+    )
+]
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/probe/setup/format.py b/tests/automated/integration/tasks/url/probe/setup/format.py
new file mode 100644
index 00000000..8cb2fdb0
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/format.py
@@ -0,0 +1,24 @@
+from src.external.url_request.probe.model import URLProbeResponse
+from tests.automated.integration.tasks.url.probe.setup.data import SETUP_ENTRIES
+from tests.automated.integration.tasks.url.probe.setup.models.entry import TestURLProbeTaskEntry
+
+
+def build_url_to_probe_response_map(
+) -> dict[str, URLProbeResponse]:
+    d = {}
+    for entry in SETUP_ENTRIES:
+        probe_response = URLProbeResponse(
+            url=entry.url,
+            status_code=entry.url_probe_response.status_code,
+            content_type=entry.url_probe_response.content_type,
+            error=entry.url_probe_response.error
+        )
+        d[entry.url] = probe_response
+    return d
+
+def build_url_to_entry_map(
+) -> dict[str, TestURLProbeTaskEntry]:
+    d = {}
+    for entry in SETUP_ENTRIES:
+        d[entry.url] = entry
+    return d
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/probe/setup/mocks/__init__.py b/tests/automated/integration/tasks/url/probe/setup/mocks/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/probe/setup/mocks/probe_manager.py b/tests/automated/integration/tasks/url/probe/setup/mocks/probe_manager.py
new file mode 100644
index 00000000..ac65ea9b
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/mocks/probe_manager.py
@@ -0,0 +1,20 @@
+from aiohttp import ClientSession
+
+from src.external.url_request.probe.model import URLProbeResponse
+from tests.automated.integration.tasks.url.probe.setup.format import build_url_to_probe_response_map
+
+
+class MockURLProbeManager:
+
+    def __init__(
+        self,
+        session: ClientSession
+    ):
+        self.session = session
+        self._url_to_probe_response: dict[str, URLProbeResponse] = build_url_to_probe_response_map()
+
+    async def probe_urls(self, urls: list[str]) -> list[URLProbeResponse]:
+        return [
+            self._url_to_probe_response[url]
+            for url in urls
+        ]
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/probe/setup/models/__init__.py b/tests/automated/integration/tasks/url/probe/setup/models/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/probe/setup/models/entry.py b/tests/automated/integration/tasks/url/probe/setup/models/entry.py
new file mode 100644
index 00000000..6432de9c
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/models/entry.py
@@ -0,0 +1,11 @@
+from pydantic import BaseModel
+
+from src.collectors.enums import URLStatus
+from tests.automated.integration.tasks.url.probe.setup.models.planned_response import URLProbePlannedResponse
+
+
+class TestURLProbeTaskEntry(BaseModel):
+    url: str
+    url_status: URLStatus
+    url_probe_response: URLProbePlannedResponse
+    expected_accessed: bool
diff --git a/tests/automated/integration/tasks/url/probe/setup/models/planned_response.py b/tests/automated/integration/tasks/url/probe/setup/models/planned_response.py
new file mode 100644
index 00000000..41f17883
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/models/planned_response.py
@@ -0,0 +1,7 @@
+from pydantic import BaseModel
+
+
+class URLProbePlannedResponse(BaseModel):
+    status_code: int | None
+    content_type: str | None
+    error: str | None
\ No newline at end of file
diff --git a/tests/automated/integration/tasks/url/probe/setup/queries/__init__.py b/tests/automated/integration/tasks/url/probe/setup/queries/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/automated/integration/tasks/url/probe/setup/queries/check.py b/tests/automated/integration/tasks/url/probe/setup/queries/check.py
new file mode 100644
index 00000000..988efffc
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/setup/queries/check.py
@@ -0,0 +1,43 @@
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from src.db.helpers.session import session_helper as sh
+from src.db.models.instantiations.url.core.sqlalchemy import URL
+from src.db.models.instantiations.url.web_metadata.sqlalchemy import URLWebMetadata
+from src.db.queries.base.builder import QueryBuilderBase
+from tests.automated.integration.tasks.url.probe.setup.data import SETUP_ENTRIES
+from tests.automated.integration.tasks.url.probe.setup.format import build_url_to_entry_map
+from tests.automated.integration.tasks.url.probe.setup.models.entry import TestURLProbeTaskEntry
+
+
+class CheckURLsInDBForURLProbeTaskQueryBuilder(QueryBuilderBase):
+
+    def __init__(self):
+        super().__init__()
+        self._entries = SETUP_ENTRIES
+        self._url_to_entry_map: dict[
+            str, TestURLProbeTaskEntry
+        ] = build_url_to_entry_map()
+
+    async def run(self, session: AsyncSession) -> None:
+
+        query = (
+            select(
+                URL.url,
+                URLWebMetadata.accessed,
+                URLWebMetadata.status_code,
+                URLWebMetadata.content_type,
+                URLWebMetadata.error_message
+            )
+            .join(URLWebMetadata, URL.id == URLWebMetadata.url_id)
+        )
+        mappings = await sh.mappings(session, query=query)
+        assert len(mappings) == len(self._entries)
+        for mapping in mappings:
+            url = mapping["url"]
+            entry = self._url_to_entry_map[url]
+            assert entry.expected_accessed == mapping["accessed"]
+            assert entry.url_probe_response.status_code == mapping["status_code"]
+            assert entry.url_probe_response.content_type == mapping["content_type"]
+            assert entry.url_probe_response.error == mapping["error_message"]
+
diff --git a/tests/automated/integration/tasks/url/probe/test_core.py b/tests/automated/integration/tasks/url/probe/test_core.py
new file mode 100644
index 00000000..ee3fe50c
--- /dev/null
+++ b/tests/automated/integration/tasks/url/probe/test_core.py
@@ -0,0 +1,33 @@
+import pytest
+
+from src.core.tasks.url.operators.probe.core import URLProbeTaskOperator
+from tests.automated.integration.tasks.asserts import assert_task_ran_without_error
+from tests.automated.integration.tasks.url.probe.setup.core import create_urls_in_db
+from tests.automated.integration.tasks.url.probe.setup.queries.check import CheckURLsInDBForURLProbeTaskQueryBuilder
+
+
+@pytest.mark.asyncio
+async def test_url_probe_task(
+    operator: URLProbeTaskOperator
+):
+    adb_client = operator.adb_client
+    # Check task does not yet meet pre-requisites
+    assert not await operator.meets_task_prerequisites()
+
+    # Set up URLs
+    await create_urls_in_db(adb_client=adb_client)
+
+    # Check task meets pre-requisites
+    assert await operator.meets_task_prerequisites()
+
+    # Run task
+    run_info = await operator.run_task(1)
+    assert_task_ran_without_error(run_info)
+
+    # Check task no longer meets pre-requisites
+    assert not await operator.meets_task_prerequisites()
+
+    # Check results as expected
+    await adb_client.run_query_builder(
+        CheckURLsInDBForURLProbeTaskQueryBuilder()
+    )
diff --git a/tests/automated/integration/tasks/url/submit_approved/test_submit_approved_url_task.py b/tests/automated/integration/tasks/url/submit_approved/test_submit_approved_url_task.py
index 8e27908b..ce9861e0 100644
--- a/tests/automated/integration/tasks/url/submit_approved/test_submit_approved_url_task.py
+++ b/tests/automated/integration/tasks/url/submit_approved/test_submit_approved_url_task.py
@@ -1,7 +1,7 @@
 import pytest
 from deepdiff import DeepDiff
 
-from src.core.tasks.url.operators.submit_approved_url.core import SubmitApprovedURLTaskOperator
+from src.core.tasks.url.operators.submit_approved.core import SubmitApprovedURLTaskOperator
 from src.db.enums import TaskType
 from src.db.models.instantiations.url.error_info.sqlalchemy import URLErrorInfo
 from src.db.models.instantiations.url.data_source.sqlalchemy import URLDataSource
diff --git a/tests/automated/integration/tasks/url/test_url_404_probe.py b/tests/automated/integration/tasks/url/test_url_404_probe.py
index 54592640..2022a8f3 100644
--- a/tests/automated/integration/tasks/url/test_url_404_probe.py
+++ b/tests/automated/integration/tasks/url/test_url_404_probe.py
@@ -5,13 +5,13 @@
 import pytest
 from aiohttp import ClientResponseError, RequestInfo
 
-from src.core.tasks.url.operators.url_404_probe.core import URL404ProbeTaskOperator
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
+from src.core.tasks.url.operators.probe_404.core import URL404ProbeTaskOperator
+from src.external.url_request.core import URLRequestInterface
 from src.db.models.instantiations.url.probed_for_404 import URLProbedFor404
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.collectors.enums import URLStatus
 from src.core.tasks.url.enums import TaskOperatorOutcome
-from src.core.tasks.url.operators.url_html.scraper.request_interface.dtos.url_response import URLResponseInfo
+from src.external.url_request.dtos.url_response import URLResponseInfo
 from tests.helpers.data_creator.core import DBDataCreator
 from tests.helpers.batch_creation_parameters.url_creation_parameters import TestURLCreationParameters
 from tests.helpers.batch_creation_parameters.core import TestBatchCreationParameters
diff --git a/tests/automated/integration/tasks/url/test_url_miscellaneous_metadata_task.py b/tests/automated/integration/tasks/url/test_url_miscellaneous_metadata_task.py
index ed7f1336..6e95fccb 100644
--- a/tests/automated/integration/tasks/url/test_url_miscellaneous_metadata_task.py
+++ b/tests/automated/integration/tasks/url/test_url_miscellaneous_metadata_task.py
@@ -2,7 +2,7 @@
 
 import pytest
 
-from src.core.tasks.url.operators.url_miscellaneous_metadata.core import URLMiscellaneousMetadataTaskOperator
+from src.core.tasks.url.operators.misc_metadata.core import URLMiscellaneousMetadataTaskOperator
 from src.db.models.instantiations.url.optional_data_source_metadata import URLOptionalDataSourceMetadata
 from src.db.models.instantiations.url.core.sqlalchemy import URL
 from src.collectors.enums import CollectorType
diff --git a/tests/automated/unit/source_collectors/test_autogoogler_collector.py b/tests/automated/unit/source_collectors/test_autogoogler_collector.py
index 2cc91449..20ddc362 100644
--- a/tests/automated/unit/source_collectors/test_autogoogler_collector.py
+++ b/tests/automated/unit/source_collectors/test_autogoogler_collector.py
@@ -5,9 +5,9 @@
 from src.collectors.source_collectors.auto_googler.dtos.query_results import GoogleSearchQueryResultsInnerDTO
 from src.collectors.source_collectors.auto_googler.dtos.input import AutoGooglerInputDTO
 from src.db.client.async_ import AsyncDatabaseClient
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.core.logger import AsyncCoreLogger
 from src.collectors.source_collectors.auto_googler.collector import AutoGooglerCollector
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 @pytest.fixture
diff --git a/tests/automated/unit/source_collectors/test_common_crawl_collector.py b/tests/automated/unit/source_collectors/test_common_crawl_collector.py
index 94c3fde6..622da31b 100644
--- a/tests/automated/unit/source_collectors/test_common_crawl_collector.py
+++ b/tests/automated/unit/source_collectors/test_common_crawl_collector.py
@@ -4,9 +4,9 @@
 
 from src.collectors.source_collectors.common_crawler.input import CommonCrawlerInputDTO
 from src.db.client.async_ import AsyncDatabaseClient
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.core.logger import AsyncCoreLogger
 from src.collectors.source_collectors.common_crawler.collector import CommonCrawlerCollector
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 
 @pytest.fixture
diff --git a/tests/automated/unit/source_collectors/test_muckrock_collectors.py b/tests/automated/unit/source_collectors/test_muckrock_collectors.py
index 672936e0..a8afe591 100644
--- a/tests/automated/unit/source_collectors/test_muckrock_collectors.py
+++ b/tests/automated/unit/source_collectors/test_muckrock_collectors.py
@@ -6,11 +6,11 @@
 from src.collectors.source_collectors.muckrock.collectors.county.core import MuckrockCountyLevelSearchCollector
 from src.collectors.source_collectors.muckrock.collectors.simple.core import MuckrockSimpleSearchCollector
 from src.db.client.async_ import AsyncDatabaseClient
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.core.logger import AsyncCoreLogger
 from src.collectors.source_collectors.muckrock.collectors.county.dto import MuckrockCountySearchCollectorInputDTO
 from src.collectors.source_collectors.muckrock.collectors.simple.dto import MuckrockSimpleSearchCollectorInputDTO
 from src.collectors.source_collectors.muckrock.fetch_requests.foia import FOIAFetchRequest
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 
 PATCH_ROOT = "src.collectors.source_collectors.muckrock"
 
diff --git a/tests/conftest.py b/tests/conftest.py
index f26249cd..3d9cebc6 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -127,7 +127,7 @@ def db_data_creator(
     db_data_creator = DBDataCreator(db_client=db_client_test)
     yield db_data_creator
 
-@pytest.fixture
+@pytest_asyncio.fixture
 async def test_client_session() -> AsyncGenerator[ClientSession, Any]:
     async with ClientSession() as session:
         yield session
diff --git a/tests/helpers/data_creator/commands/impl/html_data.py b/tests/helpers/data_creator/commands/impl/html_data.py
index 6c9e95e3..dd947d65 100644
--- a/tests/helpers/data_creator/commands/impl/html_data.py
+++ b/tests/helpers/data_creator/commands/impl/html_data.py
@@ -1,5 +1,8 @@
-from src.db.dtos.url.html_content import URLHTMLContentInfo, HTMLContentType
+from src.db.dtos.url.html_content import URLHTMLContentInfo
+from src.db.models.instantiations.url.html.content.enums import HTMLContentType
 from src.db.dtos.url.raw_html import RawHTMLInfo
+from src.db.models.instantiations.url.scrape_info.enums import ScrapeStatus
+from src.db.models.instantiations.url.scrape_info.pydantic import URLScrapeInfoInsertModel
 from tests.helpers.data_creator.commands.base import DBDataCreatorCommandBase
 from tests.helpers.data_creator.models.clients import DBDataCreatorClientContainer
 
@@ -16,6 +19,7 @@ def __init__(
     async def run(self) -> None:
         html_content_infos = []
         raw_html_info_list = []
+        scraper_info_list = []
         for url_id in self.url_ids:
             html_content_infos.append(
                 URLHTMLContentInfo(
@@ -36,6 +40,11 @@ async def run(self) -> None:
                 html="<html></html>"
             )
             raw_html_info_list.append(raw_html_info)
+            scraper_info = URLScrapeInfoInsertModel(
+                url_id=url_id,
+                status=ScrapeStatus.SUCCESS,
+            )
+            scraper_info_list.append(scraper_info)
 
         await self.adb_client.add_raw_html(raw_html_info_list)
         await self.adb_client.add_html_content_infos(html_content_infos)
diff --git a/tests/helpers/data_creator/commands/impl/url_metadata.py b/tests/helpers/data_creator/commands/impl/url_metadata.py
new file mode 100644
index 00000000..9d3cf4ff
--- /dev/null
+++ b/tests/helpers/data_creator/commands/impl/url_metadata.py
@@ -0,0 +1,31 @@
+from http import HTTPStatus
+
+from src.db.models.instantiations.url.web_metadata.pydantic import URLWebMetadataPydantic
+from tests.helpers.data_creator.commands.base import DBDataCreatorCommandBase
+
+
+class URLMetadataCommand(DBDataCreatorCommandBase):
+
+    def __init__(
+        self,
+        url_ids: list[int],
+        content_type: str = "text/html",
+        status_code: int = HTTPStatus.OK.value
+    ):
+        super().__init__()
+        self.url_ids = url_ids
+        self.content_type = content_type
+        self.status_code = status_code
+
+    async def run(self) -> None:
+        url_metadata_infos = []
+        for url_id in self.url_ids:
+            url_metadata = URLWebMetadataPydantic(
+                url_id=url_id,
+                accessed=True,
+                status_code=self.status_code,
+                content_type=self.content_type,
+                error_message=None
+            )
+            url_metadata_infos.append(url_metadata)
+        await self.adb_client.bulk_insert(url_metadata_infos)
\ No newline at end of file
diff --git a/tests/helpers/data_creator/commands/impl/urls.py b/tests/helpers/data_creator/commands/impl/urls.py
index daec2445..e4602dee 100644
--- a/tests/helpers/data_creator/commands/impl/urls.py
+++ b/tests/helpers/data_creator/commands/impl/urls.py
@@ -1,9 +1,9 @@
 from datetime import datetime
 
 from src.collectors.enums import URLStatus
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmittedURLInfo
+from src.core.tasks.url.operators.submit_approved.tdo import SubmittedURLInfo
 from src.db.dtos.url.insert import InsertURLsInfo
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic.info import URLInfo
 from tests.helpers.data_creator.commands.base import DBDataCreatorCommandBase
 from tests.helpers.simple_test_data_functions import generate_test_urls
 
diff --git a/tests/helpers/data_creator/core.py b/tests/helpers/data_creator/core.py
index f86e9a25..fed9c970 100644
--- a/tests/helpers/data_creator/core.py
+++ b/tests/helpers/data_creator/core.py
@@ -1,33 +1,22 @@
-from collections import defaultdict
 from datetime import datetime
-from random import randint
-from typing import List, Optional, Any
+from http import HTTPStatus
+from typing import Optional, Any
 
 from src.api.endpoints.annotate.agency.post.dto import URLAgencyAnnotationPostInfo
-from src.api.endpoints.review.approve.dto import FinalReviewApprovalInfo
-from src.api.endpoints.review.enums import RejectionReason
 from src.core.tasks.url.operators.agency_identification.dtos.suggestion import URLAgencySuggestionInfo
 from src.db.client.async_ import AsyncDatabaseClient
-from src.db.models.instantiations.batch.pydantic import BatchInfo
 from src.db.models.instantiations.duplicate.pydantic.insert import DuplicateInsertInfo
-from src.db.models.instantiations.url.suggestion.relevant.auto.pydantic.input import AutoRelevancyAnnotationInput
 from src.db.dtos.url.insert import InsertURLsInfo
 from src.db.models.instantiations.url.error_info.pydantic import URLErrorPydanticInfo
-from src.db.dtos.url.html_content import URLHTMLContentInfo, HTMLContentType
-from src.db.models.instantiations.url.core.pydantic import URLInfo
 from src.db.client.sync import DatabaseClient
-from src.db.dtos.url.raw_html import RawHTMLInfo
 from src.db.enums import TaskType
 from src.collectors.enums import CollectorType, URLStatus
-from src.core.tasks.url.operators.submit_approved_url.tdo import SubmittedURLInfo
-from src.core.tasks.url.operators.url_miscellaneous_metadata.tdo import URLMiscellaneousMetadataTDO
+from src.core.tasks.url.operators.misc_metadata.tdo import URLMiscellaneousMetadataTDO
 from src.core.enums import BatchStatus, SuggestionType, RecordType, SuggestedStatus
-from tests.helpers.batch_creation_parameters.annotation_info import AnnotationInfo
 from tests.helpers.batch_creation_parameters.core import TestBatchCreationParameters
 from tests.helpers.batch_creation_parameters.url_creation_parameters import TestURLCreationParameters
 from tests.helpers.data_creator.commands.base import DBDataCreatorCommandBase
 from tests.helpers.data_creator.commands.impl.agency import AgencyCommand
-from tests.helpers.data_creator.commands.impl.annotate import AnnotateCommand
 from tests.helpers.data_creator.commands.impl.batch import DBDataCreatorBatchCommand
 from tests.helpers.data_creator.commands.impl.batch_v2 import BatchV2Command
 from tests.helpers.data_creator.commands.impl.html_data import HTMLDataCreatorCommand
@@ -38,14 +27,13 @@
 from tests.helpers.data_creator.commands.impl.suggestion.user.agency import AgencyUserSuggestionsCommand
 from tests.helpers.data_creator.commands.impl.suggestion.user.record_type import UserRecordTypeSuggestionCommand
 from tests.helpers.data_creator.commands.impl.suggestion.user.relevant import UserRelevantSuggestionCommand
+from tests.helpers.data_creator.commands.impl.url_metadata import URLMetadataCommand
 from tests.helpers.data_creator.commands.impl.urls import URLsDBDataCreatorCommand
 from tests.helpers.data_creator.commands.impl.urls_v2.core import URLsV2Command
 from tests.helpers.data_creator.commands.impl.urls_v2.response import URLsV2Response
 from tests.helpers.data_creator.models.clients import DBDataCreatorClientContainer
 from tests.helpers.data_creator.models.creation_info.batch.v1 import BatchURLCreationInfo
 from tests.helpers.data_creator.models.creation_info.batch.v2 import BatchURLCreationInfoV2
-from tests.helpers.data_creator.models.creation_info.url import URLCreationInfo
-from tests.helpers.simple_test_data_functions import generate_test_urls
 
 
 class DBDataCreator:
@@ -366,3 +354,17 @@ async def agency_user_suggestions(
                 agency_annotation_info=agency_annotation_info
             )
         )
+
+    async def url_metadata(
+            self,
+            url_ids: list[int],
+            content_type: str = "text/html",
+            status_code: int = HTTPStatus.OK.value
+    ) -> None:
+        await self.run_command(
+            URLMetadataCommand(
+                url_ids=url_ids,
+                content_type=content_type,
+                status_code=status_code
+            )
+        )
diff --git a/tests/helpers/setup/wipe.py b/tests/helpers/setup/wipe.py
index 2145bcf1..630d0f71 100644
--- a/tests/helpers/setup/wipe.py
+++ b/tests/helpers/setup/wipe.py
@@ -1,6 +1,6 @@
 from sqlalchemy import create_engine
 
-from src.db.models.templates import Base
+from src.db.models.templates_.base import Base
 
 
 def wipe_database(connection_string: str) -> None:
diff --git a/tests/helpers/simple_test_data_functions.py b/tests/helpers/simple_test_data_functions.py
index d5f2c313..df455e0e 100644
--- a/tests/helpers/simple_test_data_functions.py
+++ b/tests/helpers/simple_test_data_functions.py
@@ -12,3 +12,17 @@ def generate_test_urls(count: int) -> list[str]:
         results.append(url)
 
     return results
+
+def generate_test_html() -> str:
+    return """
+    <!DOCTYPE html>
+    <html>
+      <head>
+        <title>Example HTML</title>
+      </head>
+      <body>
+        <h1>Example HTML</h1>
+        <p>This is an example of HTML content.</p>
+      </body>
+    </html>
+    """
\ No newline at end of file
diff --git a/tests/manual/core/tasks/test_url_html_task_operator.py b/tests/manual/core/tasks/test_url_html_task_operator.py
index f4cc36d6..b6031d77 100644
--- a/tests/manual/core/tasks/test_url_html_task_operator.py
+++ b/tests/manual/core/tasks/test_url_html_task_operator.py
@@ -1,12 +1,10 @@
-from unittest.mock import patch
-
 import pytest
 
 from src.api.endpoints.collector.dtos.manual_batch.post import ManualBatchInputDTO, ManualBatchInnerInputDTO
-from src.core.tasks.url.operators.url_html.core import URLHTMLTaskOperator
-from src.core.tasks.url.operators.url_html.scraper.parser.core import HTMLResponseParser
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.core import RootURLCache
+from src.core.tasks.url.operators.html.core import URLHTMLTaskOperator
+from src.core.tasks.url.operators.html.scraper.parser.core import HTMLResponseParser
+from src.external.url_request.core import URLRequestInterface
+from src.core.tasks.url.operators.html.scraper.root_url_cache.core import RootURLCache
 
 
 @pytest.mark.asyncio
diff --git a/tests/manual/external/url_request/__init__.py b/tests/manual/external/url_request/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/manual/external/url_request/test_url_probe.py b/tests/manual/external/url_request/test_url_probe.py
new file mode 100644
index 00000000..d13d0f80
--- /dev/null
+++ b/tests/manual/external/url_request/test_url_probe.py
@@ -0,0 +1,22 @@
+import pytest
+
+from src.external.url_request.probe.core import URLProbeManager
+
+URLS = [
+    "https://www.google.com",
+    "https://www.example.com",
+    "https://www.example.org",
+    "https://www.nonexistent.com",
+]
+
+@pytest.mark.asyncio
+async def test_url_probe_head(test_client_session):
+    manager = URLProbeManager(session=test_client_session)
+    result = await manager.head(url=URLS[0])
+    print(result)
+
+@pytest.mark.asyncio
+async def test_url_probe(test_client_session):
+    manager = URLProbeManager(session=test_client_session)
+    results = await manager.probe_urls(urls=URLS)
+    print(results)
\ No newline at end of file
diff --git a/tests/manual/html_collector/test_html_tag_collector_integration.py b/tests/manual/html_collector/test_html_tag_collector_integration.py
index ef8f0df3..d7942b4a 100644
--- a/tests/manual/html_collector/test_html_tag_collector_integration.py
+++ b/tests/manual/html_collector/test_html_tag_collector_integration.py
@@ -1,11 +1,11 @@
 import pytest
 
-from src.core.tasks.url.operators.url_html.core import URLHTMLTaskOperator
-from src.core.tasks.url.operators.url_html.scraper.parser.core import HTMLResponseParser
-from src.core.tasks.url.operators.url_html.scraper.request_interface.core import URLRequestInterface
-from src.core.tasks.url.operators.url_html.scraper.root_url_cache.core import RootURLCache
+from src.core.tasks.url.operators.html.core import URLHTMLTaskOperator
+from src.core.tasks.url.operators.html.scraper.parser.core import HTMLResponseParser
+from src.external.url_request.core import URLRequestInterface
+from src.core.tasks.url.operators.html.scraper.root_url_cache.core import RootURLCache
 from src.db.client.async_ import AsyncDatabaseClient
-from src.db.models.instantiations.url.core.pydantic import URLInfo
+from src.db.models.instantiations.url.core.pydantic_.info import URLInfo
 from tests.helpers.data_creator.core import DBDataCreator
 
 URLS = [
diff --git a/tests/manual/llm_api_logic/test_deepseek_record_classifier.py b/tests/manual/llm_api_logic/test_deepseek_record_classifier.py
index 612e7425..f3050d7b 100644
--- a/tests/manual/llm_api_logic/test_deepseek_record_classifier.py
+++ b/tests/manual/llm_api_logic/test_deepseek_record_classifier.py
@@ -6,7 +6,7 @@
 
 @pytest.mark.asyncio
 async def test_deepseek_record_classifier():
-    from src.db.dtos.url.html_content import HTMLContentType as hct
+    from src.db.models.instantiations.url.html.content.enums import HTMLContentType as hct
 
     d = {
         hct.TITLE: "Oath of Office for Newly Promoted Corporal Lumpkin with Acworth Police – City of Acworth, GA",
diff --git a/tests/manual/llm_api_logic/test_openai_record_classifier.py b/tests/manual/llm_api_logic/test_openai_record_classifier.py
index 7f3cb67e..b0105437 100644
--- a/tests/manual/llm_api_logic/test_openai_record_classifier.py
+++ b/tests/manual/llm_api_logic/test_openai_record_classifier.py
@@ -6,7 +6,7 @@
 
 @pytest.mark.asyncio
 async def test_openai_record_classifier():
-    from src.db.dtos.url.html_content import HTMLContentType as hct
+    from src.db.models.instantiations.url.html.content.enums import HTMLContentType as hct
 
     d = {
         hct.TITLE: "Oath of Office for Newly Promoted Corporal Lumpkin with Acworth Police – City of Acworth, GA",