mathdatech/twoot
1
0
Fork 0
mirror of https://gitlab.com/jeancf/twoot.git synced 2025-03-27 07:56:48 +00:00
Code Issues 1 Packages Projects Releases Wiki Activity

Extracted twit_account

Browse Source
This commit is contained in:
jeancf 2020-12-16 20:42:44 +01:00
parent 894c13d551
commit e2841535f6
1 changed files with 5 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
twoot.py
View File

@ -215,7 +215,7 @@ def main(argv):
# Verify that download worked # Verify that download worked
assert twit_account_page.status_code == 200,\ assert twit_account_page.status_code == 200,\
'The twitter page did not download correctly. Aborting' 'The nitter page did not download correctly. Aborting'
logging.info('Page downloaded successfully') logging.info('Page downloaded successfully')
@ -224,17 +224,14 @@ def main(argv):
of.write(twit_account_page.text) of.write(twit_account_page.text)
of.close() of.close()
exit(0)
# Make soup # Make soup
soup = BeautifulSoup(twit_account_page.text, 'html.parser') soup = BeautifulSoup(twit_account_page.text, 'html.parser')
# Verify that we now have the correct twitter page
body_classes = soup.body.get_attribute_list('class')
assert contains_class(body_classes, 'users-show-page'), 'This is not the correct twitter page. Quitting'
# Replace twit_account with version with correct capitalization # Replace twit_account with version with correct capitalization
twit_account = soup.find('span', class_='screen-name').get_text() ta = soup.find('meta', property='og:title').get('content')
twit_account = re.search('\(@(.+)\)', ta).group(1)
print(twit_account)
exit(0)
# Extract twitter timeline # Extract twitter timeline
timeline = soup.find_all('table', class_='tweet') timeline = soup.find_all('table', class_='tweet')