diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 300bd7a72..66a5b0093 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -66,6 +66,7 @@ from .extractor.vine import VineIE from .extractor.worldstarhiphop import WorldStarHipHopIE from .extractor.xnxx import XNXXIE +from .extractor.xhamster import XHamsterIE from .extractor.xvideos import XVideosIE from .extractor.yahoo import YahooIE, YahooSearchIE from .extractor.youjizz import YouJizzIE @@ -113,57 +114,6 @@ -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] - - video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', - webpage, u'title') - - # Can't see the description anywhere in the UI - # video_description = self._html_search_regex(r'Description: (?P[^<]+)', - # webpage, u'description', fatal=False) - # if video_description: video_description = unescapeHTML(video_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: - video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') - else: - video_upload_date = None - self._downloader.report_warning(u'Unable to extract upload date') - - video_uploader_id = self._html_search_regex(r']+>(?P[^<]+)', - webpage, u'uploader id', default=u'anonymous') - - video_thumbnail = self._search_regex(r'\'image\':\'(?P[^\']+)\'', - webpage, u'thumbnail', fatal=False) - - 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 - }] diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py new file mode 100644 index 000000000..001350926 --- /dev/null +++ b/youtube_dl/extractor/xhamster.py @@ -0,0 +1,61 @@ +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + + ExtractorError, +) + + +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] + + video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', + webpage, u'title') + + # Can't see the description anywhere in the UI + # video_description = self._html_search_regex(r'Description: (?P[^<]+)', + # webpage, u'description', fatal=False) + # if video_description: video_description = unescapeHTML(video_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: + video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') + else: + video_upload_date = None + self._downloader.report_warning(u'Unable to extract upload date') + + video_uploader_id = self._html_search_regex(r']+>(?P[^<]+)', + webpage, u'uploader id', default=u'anonymous') + + video_thumbnail = self._search_regex(r'\'image\':\'(?P[^\']+)\'', + webpage, u'thumbnail', fatal=False) + + 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 + }]