mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 12:01:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

[pornhub] Fix thumbnail and duration extraction (Closes #8604)

Browse source
This commit is contained in:
Sergey M․ 2016-02-19 21:42:46 +06:00
parent 88641243ab
commit ed8648a322
1 changed files with 24 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

31
youtube_dl/extractor/pornhub.py
View file

@ -11,6 +11,7 @@
)
from ..utils import (
ExtractorError,
int_or_none,
sanitized_Request,
str_to_int,
)
@ -23,13 +24,18 @@ class PornHubIE(InfoExtractor):
_VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
'md5': '882f488fa1f0026f023f33576004a2ed',
'md5': '1e19b41231a02eba417839222ac9d58e',
'info_dict': {
'id': '648719015',
'ext': 'mp4',
'uploader': 'Babes',
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
'age_limit': 18
'uploader': 'Babes',
'duration': 361,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'age_limit': 18,
}
}, {
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
@ -67,13 +73,23 @@ def _real_extract(self, url):
'PornHub said: %s' % error_msg,
expected=True, video_id=video_id)
video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
flashvars = self._parse_json(
self._search_regex(
r'var\s+flashv1ars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
video_id)
if flashvars:
video_title = flashvars.get('video_title')
thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration'))
else:
video_title, thumbnail, duration = [None] * 3
if not video_title:
video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|span class="username)[^>]+>(.+?)<',
webpage, 'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
if thumbnail:
thumbnail = compat_urllib_parse_unquote(thumbnail)
view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
@ -120,6 +136,7 @@ def _real_extract(self, url):
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,