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

Ignore branded content link on Facebook silently

Browse Source
This commit is contained in:
JustAnotherArchivist
2019-05-24 11:49:44 +00:00
parent 7989af27b5
commit 900eae54a6
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
snscrape/modules/facebook.py
View File

@@ -66,8 +66,13 @@ class FacebookUserScraper(snscrape.base.Scraper):
continue continue
href = entryA.get('href') href = entryA.get('href')
if not any(x in href for x in ('/posts/', '/photos/', '/videos/', '/permalink.php?', '/events/', '/notes/')): if not any(x in href for x in ('/posts/', '/photos/', '/videos/', '/permalink.php?', '/events/', '/notes/')):
if href != '#' or 'new photo' not in entry.text or 'to the album' not in entry.text: if href == '#' and 'new photo' in entry.text and 'to the album' in entry.text:
# Don't print a warning if it's a "User added 5 new photos to the album"-type entry, which doesn't have a permalink. # Don't print a warning if it's a "User added 5 new photos to the album"-type entry, which doesn't have a permalink.
pass
elif href.startswith('/business/help/788160621327601/?'):
# Skip the help article about branded content
pass
else:
logger.warning(f'Ignoring odd link: {href}') logger.warning(f'Ignoring odd link: {href}')
continue continue
dirtyUrl = urllib.parse.urljoin(baseUrl, href) dirtyUrl = urllib.parse.urljoin(baseUrl, href)