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

Merge pull request #866 from yasoob/master

Browse source 
Added support for XHamster - closes #841
This commit is contained in:
Filippo Valsorda 2013-06-04 10:39:31 -07:00
parent 1142d31164 c978a96c02
commit 951b9dfd94
2 changed files with 67 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
test/tests.json
View file

@ -482,5 +482,14 @@
"title": "Louis C.K. Interview Pt. 1 11/3/11",
"description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
}
},
{
"name": "XHamster",
"url": "http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html",
"file": "1509445.flv",
"md5": "9f48e0e8d58e3076bb236ff412ab62fa",
"info_dict":{
"title":"FemaleAgent Shy beauty takes the bait"
}
}
]

58
youtube_dl/InfoExtractors.py
View file

@ -4426,6 +4426,63 @@ def _real_extract(self, url):
'description': description,
}]
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
mrss_url='http://xhamster.com/movies/%s/.html' % video_id
webpage = self._download_webpage(mrss_url, video_id)
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
if len(mobj.group('server')) == 0:
video_url = compat_urllib_parse.unquote(mobj.group('file'))
else:
video_url = mobj.group('server')+'/key='+mobj.group('file')
video_extension = video_url.split('.')[-1]
mobj = re.search(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract title')
video_title = unescapeHTML(mobj.group('title'))
mobj = re.search(r'<span>Description: </span>(?P<description>[^<]+)', webpage)
if mobj is None:
video_description = u''
else:
video_description = unescapeHTML(mobj.group('description'))
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract upload date')
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
mobj = re.search(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^>]+)', webpage)
if mobj is None:
video_uploader_id = u'anonymous'
else:
video_uploader_id = mobj.group('uploader_id')
mobj = re.search(r'\'image\':\'(?P<thumbnail>[^\']+)\'', webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract thumbnail URL')
video_thumbnail = mobj.group('thumbnail')
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'title': video_title,
'description': video_description,
'upload_date': video_upload_date,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail
}]
def gen_extractors():
""" Return a list of an instance of every supported extractor.
The order does matter; the first extractor matched is the one handling the URL.
@ -4487,6 +4544,7 @@ def gen_extractors():
VineIE(),
FlickrIE(),
TeamcocoIE(),
XHamsterIE(),
GenericIE()
]