w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[xhamster] Add support for mobile URLs and fix thumbnail extraction

Browse source
This commit is contained in:
Windom 2017-12-05 19:08:31 +02:00 committed by Sergey M
parent d3f8b76b69
commit b271e33526
1 changed files with 11 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
youtube_dl/extractor/xhamster.py
View file

@ -75,6 +75,10 @@ class XHamsterIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, {
# mobile site
'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
'only_matching': True,
}, { }, {
'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
'only_matching': True, 'only_matching': True,
@ -93,7 +97,8 @@ class XHamsterIE(InfoExtractor):
video_id = mobj.group('id') or mobj.group('id_2') video_id = mobj.group('id') or mobj.group('id_2')
display_id = mobj.group('display_id') or mobj.group('display_id_2') display_id = mobj.group('display_id') or mobj.group('display_id_2')
webpage = self._download_webpage(url, video_id) desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
webpage = self._download_webpage(desktop_url, video_id)
error = self._html_search_regex( error = self._html_search_regex(
r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>', r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
@ -229,8 +234,8 @@ class XHamsterIE(InfoExtractor):
webpage, 'uploader', default='anonymous') webpage, 'uploader', default='anonymous')
thumbnail = self._search_regex( thumbnail = self._search_regex(
[r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''', [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''], r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
webpage, 'thumbnail', fatal=False, group='thumbnail') webpage, 'thumbnail', fatal=False, group='thumbnail')
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
@ -274,15 +279,16 @@ class XHamsterIE(InfoExtractor):
class XHamsterEmbedIE(InfoExtractor): class XHamsterEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)' _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://xhamster.com/xembed.php?video=3328539', 'url': 'http://xhamster.com/xembed.php?video=3328539',
'info_dict': { 'info_dict': {
'id': '3328539', 'id': '3328539',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Pen Masturbation', 'title': 'Pen Masturbation',
'timestamp': 1406581861,
'upload_date': '20140728', 'upload_date': '20140728',
'uploader_id': 'anonymous', 'uploader': 'ManyakisArt',
'duration': 5, 'duration': 5,
'age_limit': 18, 'age_limit': 18,
} }