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 date extraction on quoted posts

Browse Source
This commit is contained in:
JustAnotherArchivist
2020-10-17 02:13:27 +00:00
parent 5dc61d50ac
commit cd12500dbf
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
snscrape/modules/vkontakte.py
View File

@@ -95,7 +95,10 @@ class VKontakteUserScraper(snscrape.base.Scraper):
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'])
assert url.startswith('https://vk.com/wall') and '_' in url and url[-1] != '_' and url.rsplit('_', 1)[1].strip('0123456789') == ''
dateSpan = post.find('div', class_ = 'post_date' if not isCopy else 'copy_post_date').find('span', class_ = 'rel_date')
if not isCopy:
dateSpan = post.find('div', class_ = 'post_date').find('span', class_ = 'rel_date')
else:
dateSpan = post.find('div', class_ = 'copy_post_date').find('a', class_ = 'published_by_date')
textDiv = post.find('div', class_ = 'wall_post_text')
outlinks = [h for a in textDiv.find_all('a') if (h := self._away_a_to_url(a))] if textDiv else []
if (mediaLinkDiv := post.find('div', class_ = 'media_link')) and \