R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #7 from aviperes/facebook-likes-shares-followers

Browse Source 
extract shares and likes.
This commit is contained in:
aviperes 2019-06-20 13:26:33 +03:00 committed by GitHub
commit d7617c4174
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 36 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
youtube_dl/extractor/facebook.py
View File

@ -460,18 +460,12 @@ class FacebookIE(InfoExtractor):
'uploader_id', default=None) or self._search_regex( 'uploader_id', default=None) or self._search_regex(
r'[\'\"]ownerid[\'\"]\s*:\s*[\'\"](\d+)[\'\"]', tahoe_data.secondary, r'[\'\"]ownerid[\'\"]\s*:\s*[\'\"](\d+)[\'\"]', tahoe_data.secondary,
'uploader_id', fatal=False) 'uploader_id', fatal=False)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
view_count = parse_count(self._search_regex( view_count = parse_count(self._extract_meta_count(['postViewCount', 'viewCount'], webpage, tahoe_data, 'likes'))
r'\bpostViewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count', likes_count = parse_count(self._extract_likes(webpage, tahoe_data))
default=None) or self._search_regex( shares_count = parse_count(self._extract_meta_count(['sharecount'], webpage, tahoe_data, 'shares'))
r'[\'\"]postViewCount[\'\"]\s*:\s*(\d+)', tahoe_data.secondary, 'view count',
default=None) or self._search_regex(
r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
default=None) or self._search_regex(
r'[\'\"]viewCount[\'\"]\s*:\s*(\d+)', tahoe_data.secondary, 'view count',
default=None)
)
info_dict = { info_dict = {
'id': video_id, 'id': video_id,
@ -483,11 +477,42 @@ class FacebookIE(InfoExtractor):
'view_count': view_count, 'view_count': view_count,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'is_live': is_live, 'is_live': is_live,
'live_status': live_status 'live_status': live_status,
'like_count': likes_count,
'share_count': shares_count
} }
return webpage, info_dict return webpage, info_dict
def _extract_meta_count(self, fields, webpage, tahoe_data, name, ):
value = None
for f in fields:
if value:
break
value = self._search_regex(
r'\b%s\s*:\s*["\']([\d,.]+)' % f, webpage, name,
default=None
)
if value:
break
value = self._search_regex(
r'[\'\"]%s[\'\"]\s*:\s*(\d+)' % f, tahoe_data.secondary, name,
default=None)
return value
def _extract_likes(self, webpage, tahoe_data):
values = re.findall(r'\blikecount\s*:\s*["\']([\d,.]+)', webpage)
if values:
return values[-1]
values = re.findall(r'[\'\"]\blikecount[\'\"]\s*:\s*(\d+)', tahoe_data.secondary)
if values:
return values[-1]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)