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

Print contents when ignoring a link-less entry

Browse Source
This commit is contained in:
JustAnotherArchivist
2019-07-01 01:35:00 +00:00
parent 64b293bd9e
commit 628074d6fc
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
snscrape/modules/facebook.py
View File

@@ -84,7 +84,7 @@ class FacebookCommonScraper(snscrape.base.Scraper):
entryA = entry.find('a', class_ = '_5pcq') # There can be more than one, e.g. when a post is shared by another user, but the first one is always the one of this entry. entryA = entry.find('a', class_ = '_5pcq') # There can be more than one, e.g. when a post is shared by another user, but the first one is always the one of this entry.
mediaSetA = entry.find('a', class_ = '_17z-') mediaSetA = entry.find('a', class_ = '_17z-')
if not mediaSetA and not entryA: if not mediaSetA and not entryA:
logger.warning(f'Ignoring link-less entry after {cleanUrl}') logger.warning(f'Ignoring link-less entry after {cleanUrl}: {entry.text!r}')
continue continue
if mediaSetA and (not entryA or entryA['href'] == '#'): if mediaSetA and (not entryA or entryA['href'] == '#'):
href = mediaSetA['href'] href = mediaSetA['href']