bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-06-12 20:38:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

added capability to extract the number of channel members when the the string in membersDiv has the word 'subscribers' rather than 'members'.

Browse Source
This commit is contained in:
Tristan Lee
2022-03-29 01:12:07 -05:00
parent de4ebed81f
commit ed829163a0
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
snscrape/modules/telegram.py
View File

@@ -177,8 +177,8 @@ class TelegramChannelScraper(snscrape.base.Scraper):
raise snscrape.base.ScraperException(f'Got status code {r.status_code}') raise snscrape.base.ScraperException(f'Got status code {r.status_code}')
soup = bs4.BeautifulSoup(r.text, 'lxml') soup = bs4.BeautifulSoup(r.text, 'lxml')
membersDiv = soup.find('div', class_ = 'tgme_page_extra') membersDiv = soup.find('div', class_ = 'tgme_page_extra')
if membersDiv.text.endswith(' members'): if membersDiv.text.endswith((' members', ' subscribers')):
kwargs['members'] = int(membersDiv.text[:-8].replace(' ', '')) kwargs['members'] = int(''.join(membersDiv.text.split(' ')[:-1]))
kwargs['photo'] = soup.find('img', class_ = 'tgme_page_photo_image').attrs['src'] kwargs['photo'] = soup.find('img', class_ = 'tgme_page_photo_image').attrs['src']
r, soup = self._initial_page() r, soup = self._initial_page()