Skip to content

Added cleaned text as ParseResult #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vinyll wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added cleaned text as ParseResult #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions ttp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,13 +96,14 @@ class ParseResult(object):

'''

def __init__(self, urls, users, reply, lists, tags, html):
def __init__(self, urls, users, reply, lists, tags, html, text):
self.urls = list(set(urls)) if urls else [] #fixes dups
self.users = list(set(users)) if users else []
self.lists = list(set(lists)) if lists else []
self.reply = list(set(reply)) if reply else []
self.tags = list(set(tags)) if tags else []
self.html = html
self.text = text


class Parser(object):
Expand All @@ -122,16 +123,18 @@ def parse(self, text, html=True):
reply = reply.groups(0)[0] if reply is not None else None

parsed_html = self._html(text) if html else self._text(text)
parsed_text = self._text(text)
return ParseResult(self._urls, self._users, reply,
self._lists, self._tags, parsed_html)
self._lists, self._tags, parsed_html,
parsed_text)

def _text(self, text):
'''Parse a Tweet without generating HTML.'''
URL_REGEX.sub(self._parse_urls, text)
USERNAME_REGEX.sub(self._parse_users, text)
LIST_REGEX.sub(self._parse_lists, text)
HASHTAG_REGEX.sub(self._parse_tags, text)
return None
text = URL_REGEX.sub(self._parse_urls, text)
text = USERNAME_REGEX.sub('', text)
text = LIST_REGEX.sub(self._parse_lists, text)
text = HASHTAG_REGEX.sub(self._parse_tags, text)
return text

def _html(self, text):
'''Parse a Tweet and generate HTML.'''
Expand Down