diff --git a/test/tests.json b/test/tests.json index f57ebf1c9a..dc2671daa6 100644 --- a/test/tests.json +++ b/test/tests.json @@ -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" + } } ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 37f9c1449d..a6294e1e18 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -4425,6 +4425,63 @@ class TeamcocoIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, }] + +class XHamsterIE(InfoExtractor): + """Information Extractor for xHamster""" + _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P[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[^\']*)\',\s*\'file\': \'(?P[^\']+)\',', 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'(?P<title>.+?) - xHamster\.com', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract title') + video_title = unescapeHTML(mobj.group('title')) + + mobj = re.search(r'Description: (?P[^<]+)', webpage) + if mobj is None: + video_description = u'' + else: + video_description = unescapeHTML(mobj.group('description')) + + mobj = re.search(r'hint=\'(?P[0-9]{4})-(?P[0-9]{2})-(?P[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']+>(?P[^>]+)', webpage) + if mobj is None: + video_uploader_id = u'anonymous' + else: + video_uploader_id = mobj.group('uploader_id') + + mobj = re.search(r'\'image\':\'(?P[^\']+)\'', 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. @@ -4487,6 +4544,7 @@ def gen_extractors(): VineIE(), FlickrIE(), TeamcocoIE(), + XHamsterIE(), GenericIE() ]