kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[pornhub] Fix comment count extraction (Closes #5320)

Browse source
This commit is contained in:
Sergey M․ 2015-03-30 19:41:04 +06:00
parent 72b249bf1f
commit 7700207ec7
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/pornhub.py
View file

@ -33,10 +33,8 @@ class PornHubIE(InfoExtractor):
} }
def _extract_count(self, pattern, webpage, name): def _extract_count(self, pattern, webpage, name):
count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False) return str_to_int(self._search_regex(
if count: pattern, webpage, '%s count' % name, fatal=False))
count = str_to_int(count)
return count
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -62,11 +60,14 @@ class PornHubIE(InfoExtractor):
if thumbnail: if thumbnail:
thumbnail = compat_urllib_parse.unquote(thumbnail) thumbnail = compat_urllib_parse.unquote(thumbnail)
view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view') view_count = self._extract_count(
like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like') r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike') like_count = self._extract_count(
r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
dislike_count = self._extract_count(
r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
comment_count = self._extract_count( comment_count = self._extract_count(
r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment') r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1: if webpage.find('"encrypted":true') != -1: