X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxhamster.py;h=97315750fd59198022a72eca53482efdd8d98e75;hb=55801fc76e2813de9a84eaa830d70ed73cb44463;hp=f6c515f7f8a5ad9b038b7f417800c3c833fb8ac3;hpb=d55433bbfd9b7237bd7a52f2dc1ca7bd991a1367;p=youtube-dl diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index f6c515f7f..97315750f 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -4,53 +4,53 @@ import re from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, - ExtractorError, + unified_strdate, + str_to_int, + int_or_none, + parse_duration, ) class XHamsterIE(InfoExtractor): - """Information Extractor for xHamster""" - _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' - _TESTS = [{ - 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', - 'file': '1509445.mp4', - 'md5': '8281348b8d3c53d39fffb377d24eac4e', - 'info_dict': { - "upload_date": "20121014", - "uploader_id": "Ruseful2011", - "title": "FemaleAgent Shy beauty takes the bait", - "age_limit": 18, - } - }, - { - 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', - 'file': '2221348.flv', - 'md5': 'e767b9475de189320f691f49c679c4c7', - 'info_dict': { - "upload_date": "20130914", - "uploader_id": "jojo747400", - "title": "Britney Spears Sexy Booty", - "age_limit": 18, - } - }] - - def _real_extract(self,url): - def extract_video_url(webpage): - mobj = re.search(r'\'srv\': \'(?P[^\']*)\',\s*\'file\': \'(?P[^\']+)\',', webpage) - if mobj is None: - raise ExtractorError('Unable to extract media URL') - if len(mobj.group('server')) == 0: - return compat_urllib_parse.unquote(mobj.group('file')) - else: - return mobj.group('server')+'/key='+mobj.group('file') - - def extract_mp4_video_url(webpage): - mp4 = re.search(r'https?)://(?:.+?\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' + _TESTS = [ + { + 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', + 'info_dict': { + 'id': '1509445', + 'ext': 'mp4', + 'title': 'FemaleAgent Shy beauty takes the bait', + 'upload_date': '20121014', + 'uploader': 'Ruseful2011', + 'duration': 893, + 'age_limit': 18, + } + }, + { + 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', + 'info_dict': { + 'id': '2221348', + 'ext': 'mp4', + 'title': 'Britney Spears Sexy Booty', + 'upload_date': '20130914', + 'uploader': 'jojo747400', + 'duration': 200, + 'age_limit': 18, + } + }, + { + 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + def extract_video_url(webpage, name): + return self._search_regex( + [r'''file\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r'''["'])(?P.+?)(?P=q)\s+class=["']mp4Thumb''', + r''']+file=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + webpage, name, group='mp4') def is_hd(webpage): return '
(?P.+?) - xHamster\.com', webpage, 'title') + title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', webpage, 'title') # Only a few videos have an description mobj = re.search(r'Description: ([^<]+)', webpage) - video_description = mobj.group(1) if mobj else None + description = mobj.group(1) if mobj else None + + upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'', + webpage, 'upload date', fatal=False) + if upload_date: + upload_date = unified_strdate(upload_date) - 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('Unable to extract upload date') + uploader = self._html_search_regex( + r"]+>(?P[^<]+)", + webpage, 'uploader', default='anonymous') - video_uploader_id = self._html_search_regex( - r']+>(?P[^<]+)', - webpage, 'uploader id', default='anonymous') + thumbnail = self._search_regex( + [r'''thumb\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r''']+poster=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + webpage, 'thumbnail', fatal=False, group='thumbnail') - video_thumbnail = self._search_regex( - r'\'image\':\'(?P[^\']+)\'', - webpage, 'thumbnail', fatal=False) + duration = parse_duration(self._html_search_regex(r'Runtime: (\d+:\d+)
', + webpage, 'duration', fatal=False)) + + view_count = self._html_search_regex(r'Views: ([^<]+)', webpage, 'view count', fatal=False) + if view_count: + view_count = str_to_int(view_count) + + mobj = re.search(r"hint='(?P\d+) Likes / (?P\d+) Dislikes'", webpage) + (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None) + + mobj = re.search(r'Comments \((?P\d+)\)', webpage) + comment_count = mobj.group('commentcount') if mobj else 0 age_limit = self._rta_search(webpage) hd = is_hd(webpage) - video_url = extract_video_url(webpage) + + format_id = 'hd' if hd else 'sd' + + video_url = extract_video_url(webpage, format_id) formats = [{ 'url': video_url, 'format_id': 'hd' if hd else 'sd', - 'preference': 0, + 'preference': 1, }] - video_mp4_url = extract_mp4_video_url(webpage) - if video_mp4_url is not None: - formats.append({ - 'url': video_mp4_url, - 'ext': 'mp4', - 'format_id': 'mp4-hd' if hd else 'mp4-sd', - 'preference': 1, - }) - if not hd: - webpage = self._download_webpage( - mrss_url + '?hd', video_id, note='Downloading HD webpage') + mrss_url = self._search_regex(r'\d+)' + _TEST = { + 'url': 'http://xhamster.com/xembed.php?video=3328539', + 'info_dict': { + 'id': '3328539', + 'ext': 'mp4', + 'title': 'Pen Masturbation', + 'upload_date': '20140728', + 'uploader_id': 'anonymous', + 'duration': 5, + 'age_limit': 18, } + } + + @staticmethod + def _extract_urls(webpage): + return [url for _, url in re.findall( + r']+?src=(["\'])(?P(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1', + webpage)] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_url = self._search_regex( + r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id, + webpage, 'xhamster url') + + return self.url_result(video_url, 'XHamster')