mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2025-01-31 05:33:45 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Extracted author, author_account, time_string, timestamp

Browse Source
This commit is contained in:
jeancf 2020-12-16 22:15:27 +01:00
parent 19d988dfcb
commit e6e24cbfd5
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
twoot.py
View File

@ -263,20 +263,21 @@ def main(argv):
# Do we need to handle reply-to tweets? # Do we need to handle reply-to tweets?
if tweets_and_replies: if tweets_and_replies:
# TODO Capture user name being replied to # TODO Capture user name being replied to
pass
else: else:
# Skip this tweet # Skip this tweet
logging.debug("Tweet is a reply-to and we don't want that. Skipping.") logging.debug("Tweet is a reply-to and we don't want that. Skipping.")
continue continue
# extract author # extract author
author = tmt.find('div', class_='fullname').a.strong.get_text() author = status.find('a', class_='fullname').get('title')
# Extract user name # Extract user name
author_account = str(tmt.find('span', class_='username').span.next_sibling).strip('\n ') author_account = status.find('a', class_='username').get('title').lstrip('@')
# Extract time stamp # Extract time stamp
time_string = tmt.find('div', class_='metadata').a.get_text() time_string = status.find('span', class_='tweet-date').a.get('title')
timestamp = datetime.datetime.strptime(time_string, '%I:%M %p - %d %b %Y').timestamp() timestamp = datetime.datetime.strptime(time_string, '%d/%m/%Y, %H:%M:%S').timestamp()
# extract iterator over tweet text contents # extract iterator over tweet text contents
tt_iter = tmt.find('div', class_='tweet-text').div.children tt_iter = tmt.find('div', class_='tweet-text').div.children