bellingcat/snscrape
1
0
Fork 0
mirror of https://github.com/bellingcat/snscrape.git synced 2026-07-04 14:28:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix crash on photo reposts

Browse Source
This commit is contained in:
JustAnotherArchivist
2020-12-13 22:46:28 +00:00
parent fdc33d0dba
commit e3022628b6
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
snscrape/modules/vkontakte.py
View File

@@ -136,12 +136,12 @@ class VKontakteUserScraper(snscrape.base.Scraper):
if (match := re.match(r'^(?P<day>\d+)\s+(?P<month>' + '|'.join(months) + r')\s+(?P<year>\d{4})$', dateSpan.text)): if (match := re.match(r'^(?P<day>\d+)\s+(?P<month>' + '|'.join(months) + r')\s+(?P<year>\d{4})$', dateSpan.text)):
# Date only # Date only
return datetime.date(int(match.group('year')), months.index(match.group('month')) + 1, int(match.group('day'))) return datetime.date(int(match.group('year')), months.index(match.group('month')) + 1, int(match.group('day')))
if dateSpan.text != 'video': # Silently ignore video reposts which have no original date attached if dateSpan.text not in ('video', 'photo'): # Silently ignore video and photo reposts which have no original date attached
logger.warning(f'Could not parse date string: {dateSpan.text!r}') logger.warning(f'Could not parse date string: {dateSpan.text!r}')
def _post_div_to_item(self, post, isCopy = False): 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']) 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') or isCopy and url.startswith('https://vk.com/video')) and '_' in url and url[-1] != '_' and url.rsplit('_', 1)[1].strip('0123456789') == '' 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: if not isCopy:
dateSpan = post.find('div', class_ = 'post_date').find('span', class_ = 'rel_date') dateSpan = post.find('div', class_ = 'post_date').find('span', class_ = 'rel_date')
else: else: