bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-06-08 02:28:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix crash on reposts of hidden profiles

Browse Source
This commit is contained in:
JustAnotherArchivist
2020-12-13 23:22:17 +00:00
parent e3022628b6
commit 892941b609
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
snscrape/modules/vkontakte.py
View File

@@ -140,7 +140,11 @@ class VKontakteUserScraper(snscrape.base.Scraper):
logger.warning(f'Could not parse date string: {dateSpan.text!r}')
def _post_div_to_item(self, post, isCopy = False):
url = urllib.parse.urljoin(self._baseUrl, post.find('a', class_ = 'post_link' if not isCopy else 'published_by_date')['href'])
postLink = post.find('a', class_ = 'post_link' if not isCopy else 'published_by_date')
if not postLink:
logger.warning(f'Skipping post without link: {str(post)[:200]!r}')
return
url = urllib.parse.urljoin(self._baseUrl, postLink['href'])
assert (url.startswith('https://vk.com/wall') or (isCopy and (url.startswith('https://vk.com/video') or url.startswith('https://vk.com/photo')))) and '_' in url and url[-1] != '_' and url.rsplit('_', 1)[1].strip('0123456789') == ''
if not isCopy:
dateSpan = post.find('div', class_ = 'post_date').find('span', class_ = 'rel_date')