diff --git a/README.md b/README.md
index 33440d64..0b9d167c 100644
--- a/README.md
+++ b/README.md
@@ -7,11 +7,11 @@ name | description of purpose
 .github/workflows | Scheduling and automation
 agency_identifier | Matches URLs with an agency from the PDAP database
 annotation_pipeline | Automated pipeline for generating training data in our ML data source identification models. Manages common crawl, HTML tag collection, and Label Studio import/export
-common_crawler | Interfaces with the Common Crawl dataset to extract urls, creating batches to identify or annotate
 html_tag_collector | Collects HTML header, meta, and title tags and appends them to a JSON file. The idea is to make a richer dataset for algorithm training and data labeling.
 hugging_face | Utilities for interacting with our machine learning space at [Hugging Face](https://huggingface.co/PDAP)
 identification_pipeline.py | The core python script uniting this modular pipeline. More details below.
 openai-playground | Scripts for accessing the openai API on PDAP's shared account
+source_collectors| Tools for extracting metadata from different sources, including CKAN data portals and Common Crawler
 
 ## How to use
 
diff --git a/source_collectors/README.md b/source_collectors/README.md
new file mode 100644
index 00000000..1b02215c
--- /dev/null
+++ b/source_collectors/README.md
@@ -0,0 +1,11 @@
+# Source Collectors
+
+The Source Collectors are tools that collect URLs from various sources for the purposes of storing as batches.
+
+Each tool is intended to be used in conjunction with the other tools in this repo.
+
+Currently, the following tools are available:
+- Common Crawler: Interfaces with the Common Crawl dataset to extract urls
+- Auto-Googler: A tool for automating the process of fetching URLs from Google Search and processing them for source collection.
+- CKAN Scraper: A tool for retrieving packages from CKAN data portals and parsing relevant information
+- MuckRock Scraper: A tool for retrieving FOIA requests from MuckRock and parsing relevant information
\ No newline at end of file
diff --git a/source_collectors/auto_googler/AutoGoogler.py b/source_collectors/auto_googler/AutoGoogler.py
new file mode 100644
index 00000000..0141ce23
--- /dev/null
+++ b/source_collectors/auto_googler/AutoGoogler.py
@@ -0,0 +1,28 @@
+from source_collectors.auto_googler.GoogleSearcher import GoogleSearcher
+from source_collectors.auto_googler.SearchConfig import SearchConfig
+
+
+class AutoGoogler:
+    """
+    The AutoGoogler orchestrates the process of fetching urls from Google Search
+     and processing them for source collection
+
+    """
+    def __init__(self, search_config: SearchConfig, google_searcher: GoogleSearcher):
+        self.search_config = search_config
+        self.google_searcher = google_searcher
+        self.data = {query : [] for query in search_config.queries}
+
+    def run(self) -> str:
+        """
+        Runs the AutoGoogler
+        Yields status messages
+        """
+        for query in self.search_config.queries:
+            yield f"Searching for '{query}' ..."
+            results = self.google_searcher.search(query)
+            yield f"Found {len(results)} results for '{query}'."
+            if results is not None:
+                self.data[query] = results
+        yield "Done."
+
diff --git a/source_collectors/auto_googler/GoogleSearcher.py b/source_collectors/auto_googler/GoogleSearcher.py
new file mode 100644
index 00000000..6638770a
--- /dev/null
+++ b/source_collectors/auto_googler/GoogleSearcher.py
@@ -0,0 +1,65 @@
+from typing import Union
+
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+
+class QuotaExceededError(Exception):
+    pass
+
+class GoogleSearcher:
+    """
+    A class that provides a GoogleSearcher object for performing searches using the Google Custom Search API.
+
+    Attributes:
+        api_key (str): The API key required for accessing the Google Custom Search API.
+        cse_id (str): The CSE (Custom Search Engine) ID required for identifying the specific search engine to use.
+        service (Google API service): The Google API service object for performing the search.
+
+    Methods:
+        __init__(api_key: str, cse_id: str)
+            Initializes a GoogleSearcher object with the provided API key and CSE ID. Raises a RuntimeError if either
+            the API key or CSE ID is None.
+
+        search(query: str) -> Union[list[dict], None]
+            Performs a search using the Google Custom Search API with the provided query string. Returns a list of
+            search results as dictionaries or None if the daily quota for the API has been exceeded. Raises a RuntimeError
+            if any other error occurs during the search.
+    """
+    GOOGLE_SERVICE_NAME = "customsearch"
+    GOOGLE_SERVICE_VERSION = "v1"
+
+    def __init__(
+            self,
+            api_key: str,
+            cse_id: str
+    ):
+        if api_key is None or cse_id is None:
+            raise RuntimeError("Custom search API key and CSE ID cannot be None.")
+        self.api_key = api_key
+        self.cse_id = cse_id
+
+        self.service = build(self.GOOGLE_SERVICE_NAME,
+                             self.GOOGLE_SERVICE_VERSION,
+                             developerKey=self.api_key)
+
+    def search(self, query: str) -> Union[list[dict], None]:
+        """
+        Searches for results using the specified query.
+
+        Args:
+            query (str): The query to search for.
+
+        Returns: Union[list[dict], None]: A list of dictionaries representing the search results.
+            If the daily quota is exceeded, None is returned.
+        """
+        try:
+            res = self.service.cse().list(q=query, cx=self.cse_id).execute()
+            if "items" not in res:
+                return None
+            return res['items']
+            # Process your results
+        except HttpError as e:
+            if "Quota exceeded" in str(e):
+                raise QuotaExceededError("Quota exceeded for the day")
+            else:
+                raise RuntimeError(f"An error occurred: {str(e)}")
\ No newline at end of file
diff --git a/source_collectors/auto_googler/README.md b/source_collectors/auto_googler/README.md
new file mode 100644
index 00000000..99cc96dc
--- /dev/null
+++ b/source_collectors/auto_googler/README.md
@@ -0,0 +1,13 @@
+The Auto-Googler is a tool that automates the process of fetching URLs from Google Search and processing them for source collection.
+
+Auto-Googler logic consists of:
+
+1. `GoogleSearcher`, the class that interfaces with the Google Search API.
+2. `AutoGoogler`, the class that orchestrates the search process.
+3. `SearchConfig`, the class that holds the configuration for the search queries.
+
+The following environment variables must be set in an `.env` file in the root directory:
+
+- GOOGLE_API_KEY: The API key required for accessing the Google Custom Search API.
+
+The Auto-Googler is intended to be used in conjunction with the other tools in this repo.
diff --git a/source_collectors/auto_googler/SearchConfig.py b/source_collectors/auto_googler/SearchConfig.py
new file mode 100644
index 00000000..b2daf8fd
--- /dev/null
+++ b/source_collectors/auto_googler/SearchConfig.py
@@ -0,0 +1,24 @@
+from typing import Annotated
+
+from pydantic import BaseModel, Field
+
+
+class SearchConfig(BaseModel):
+    """
+    A class that holds the configuration for the AutoGoogler
+    Simple now, but might be extended in the future
+    """
+    urls_per_result: Annotated[
+        int,
+        "Maximum number of URLs returned per result. Minimum is 1. Default is 10"
+    ] = Field(
+        default=10,
+        ge=1
+    )
+    queries: Annotated[
+        list[str],
+        "List of queries to search for."
+    ] = Field(
+        min_length=1
+    )
+
diff --git a/source_collectors/auto_googler/__init__.py b/source_collectors/auto_googler/__init__.py
new file mode 100644
index 00000000..e69de29b