X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bc5059672e222ec4df4fe3983c399c0d0fca84d5..4d055bc6eb5dbe9a42216ec3e659d8ff1f2a1256:/youtube_dl/extractor/xhamster.py?ds=inline diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 279f75e..a5b94d2 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -1,111 +1,381 @@ +from __future__ import unicode_literals + +import itertools import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_urllib_parse, - unescapeHTML, + clean_html, determine_ext, + dict_get, + extract_attributes, ExtractorError, + int_or_none, + parse_duration, + try_get, + unified_strdate, + url_or_none, ) class XHamsterIE(InfoExtractor): - """Information Extractor for xHamster""" - _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' + _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)' + _VALID_URL = r'''(?x) + https?:// + (?:.+?\.)?%s/ + (?: + movies/(?P\d+)/(?P[^/]*)\.html| + videos/(?P[^/]*)-(?P\d+) + ) + ''' % _DOMAINS _TESTS = [{ - u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', - u'file': u'1509445.flv', - u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa', - u'info_dict': { - u"upload_date": u"20121014", - u"uploader_id": u"Ruseful2011", - u"title": u"FemaleAgent Shy beauty takes the bait", - u"age_limit": 18, - } - }, - { - u'url': u'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', - u'file': u'2221348.flv', - u'md5': u'970a94178ca4118c5aa3aaea21211b81', - u'info_dict': { - u"upload_date": u"20130914", - u"uploader_id": u"jojo747400", - u"title": u"Britney Spears Sexy Booty", - u"age_limit": 18, - } + 'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'md5': '98b4687efb1ffd331c4197854dc09e8f', + 'info_dict': { + 'id': '1509445', + 'display_id': 'femaleagent-shy-beauty-takes-the-bait', + 'ext': 'mp4', + 'title': 'FemaleAgent Shy beauty takes the bait', + 'timestamp': 1350194821, + 'upload_date': '20121014', + 'uploader': 'Ruseful2011', + 'duration': 893, + 'age_limit': 18, + }, + }, { + 'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=', + 'info_dict': { + 'id': '2221348', + 'display_id': 'britney-spears-sexy-booty', + 'ext': 'mp4', + 'title': 'Britney Spears Sexy Booty', + 'timestamp': 1379123460, + 'upload_date': '20130914', + 'uploader': 'jojo747400', + 'duration': 200, + 'age_limit': 18, + }, + 'params': { + 'skip_download': True, + }, + }, { + # empty seo, unavailable via new URL schema + 'url': 'http://xhamster.com/movies/5667973/.html', + 'info_dict': { + 'id': '5667973', + 'ext': 'mp4', + 'title': '....', + 'timestamp': 1454948101, + 'upload_date': '20160208', + 'uploader': 'parejafree', + 'duration': 72, + 'age_limit': 18, + }, + 'params': { + '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', + 'only_matching': True, + }, { + # This video is visible for marcoalfa123456's friends only + 'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html', + 'only_matching': True, + }, { + # new URL schema + 'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821', + 'only_matching': True, + }, { + 'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'only_matching': True, + }, { + 'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'only_matching': True, + }, { + 'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'only_matching': True, + }, { + 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', + 'only_matching': True, + }, { + 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', + 'only_matching': True, }] - 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(u'Unable to extract media URL') - if len(mobj.group('server')) == 0: - return compat_urllib_parse.unquote(mobj.group('file')) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') or mobj.group('id_2') + display_id = mobj.group('display_id') or mobj.group('display_id_2') + + desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) + webpage = self._download_webpage(desktop_url, video_id) + + error = self._html_search_regex( + r']+id=["\']videoClosed["\'][^>]*>(.+?)', + webpage, 'error', default=None) + if error: + raise ExtractorError(error, expected=True) + + age_limit = self._rta_search(webpage) + + def get_height(s): + return int_or_none(self._search_regex( + r'^(\d+)[pP]', s, 'height', default=None)) + + initials = self._parse_json( + self._search_regex( + r'window\.initials\s*=\s*({.+?})\s*;\s*\n', webpage, 'initials', + default='{}'), + video_id, fatal=False) + if initials: + video = initials['videoModel'] + title = video['title'] + formats = [] + for format_id, formats_dict in video['sources'].items(): + if not isinstance(formats_dict, dict): + continue + for quality, format_item in formats_dict.items(): + if format_id == 'download': + # Download link takes some time to be generated, + # skipping for now + continue + if not isinstance(format_item, dict): + continue + format_url = format_item.get('link') + filesize = int_or_none( + format_item.get('size'), invscale=1000000) + else: + format_url = format_item + filesize = None + format_url = url_or_none(format_url) + if not format_url: + continue + formats.append({ + 'format_id': '%s-%s' % (format_id, quality), + 'url': format_url, + 'ext': determine_ext(format_url, 'mp4'), + 'height': get_height(quality), + 'filesize': filesize, + }) + self._sort_formats(formats) + + categories_list = video.get('categories') + if isinstance(categories_list, list): + categories = [] + for c in categories_list: + if not isinstance(c, dict): + continue + c_name = c.get('name') + if isinstance(c_name, compat_str): + categories.append(c_name) else: - return mobj.group('server')+'/key='+mobj.group('file') + categories = None - def is_hd(webpage): - return webpage.find('
') != -1 + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': video.get('description'), + 'timestamp': int_or_none(video.get('created')), + 'uploader': try_get( + video, lambda x: x['author']['name'], compat_str), + 'thumbnail': video.get('thumbURL'), + 'duration': int_or_none(video.get('duration')), + 'view_count': int_or_none(video.get('views')), + 'like_count': int_or_none(try_get( + video, lambda x: x['rating']['likes'], int)), + 'dislike_count': int_or_none(try_get( + video, lambda x: x['rating']['dislikes'], int)), + 'comment_count': int_or_none(video.get('views')), + 'age_limit': age_limit, + 'categories': categories, + 'formats': formats, + } - mobj = re.match(self._VALID_URL, url) + # Old layout fallback + + title = self._html_search_regex( + [r']*>([^<]+)', + r']+itemprop=".*?caption.*?"[^>]+content="(.+?)"', + r']*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)'], + webpage, 'title') + + formats = [] + format_urls = set() - video_id = mobj.group('id') - seo = mobj.group('seo') - mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo) - webpage = self._download_webpage(mrss_url, video_id) + sources = self._parse_json( + self._search_regex( + r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources', + default='{}'), + video_id, fatal=False) + for format_id, format_url in sources.items(): + format_url = url_or_none(format_url) + if not format_url: + continue + if format_url in format_urls: + continue + format_urls.add(format_url) + formats.append({ + 'format_id': format_id, + 'url': format_url, + 'height': get_height(format_id), + }) - video_title = self._html_search_regex(r'(?P<title>.+?) - xHamster\.com', - webpage, u'title') + video_url = 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, 'video url', group='mp4', default=None) + if video_url and video_url not in format_urls: + formats.append({ + 'url': video_url, + }) + + self._sort_formats(formats) # Only a few videos have an description - mobj = re.search('Description: (?P[^<]+)', webpage) - if mobj: - video_description = unescapeHTML(mobj.group('description')) - else: - video_description = None + mobj = re.search(r'Description: ([^<]+)', webpage) + description = mobj.group(1) if mobj else None - 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') + upload_date = unified_strdate(self._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)) - video_uploader_id = self._html_search_regex(r']+>(?P[^<]+)', - webpage, u'uploader id', default=u'anonymous') + uploader = self._html_search_regex( + r']+itemprop=["\']author[^>]+>]+>]+>([^<]+)', + webpage, 'uploader', default='anonymous') - video_thumbnail = self._search_regex(r'\'image\':\'(?P[^\']+)\'', - webpage, u'thumbnail', fatal=False) + thumbnail = self._search_regex( + [r'''["']thumbUrl["']\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r''']+"poster"=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + webpage, 'thumbnail', fatal=False, group='thumbnail') - age_limit = self._rta_search(webpage) + duration = parse_duration(self._search_regex( + [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']', + r'Runtime:\s*\s*([\d:]+)'], webpage, + 'duration', fatal=False)) + + view_count = int_or_none(self._search_regex( + r'content=["\']User(?:View|Play)s:(\d+)', + webpage, 'view count', fatal=False)) + + 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) - video_url = extract_video_url(webpage) - hd = is_hd(webpage) - formats = [{ - 'url': video_url, - 'ext': determine_ext(video_url), - 'format': 'hd' if hd else 'sd', - 'format_id': 'hd' if hd else 'sd', - }] - if not hd: - webpage = self._download_webpage(mrss_url+'?hd', video_id) - if is_hd(webpage): - video_url = extract_video_url(webpage) - formats.append({ - 'url': video_url, - 'ext': determine_ext(video_url), - 'format': 'hd', - 'format_id': 'hd', - }) + mobj = re.search(r'Comments \((?P\d+)\)
', webpage) + comment_count = mobj.group('commentcount') if mobj else 0 + + categories_html = self._search_regex( + r'(?s)Categories:.+?)', webpage, + 'categories', default=None) + categories = [clean_html(category) for category in re.findall( + r']+>(.+?)', categories_html)] if categories_html else None return { 'id': video_id, - 'title': video_title, - 'formats': formats, - 'description': video_description, - 'upload_date': video_upload_date, - 'uploader_id': video_uploader_id, - 'thumbnail': video_thumbnail, + 'display_id': display_id, + 'title': title, + 'description': description, + 'upload_date': upload_date, + 'uploader': uploader, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'like_count': int_or_none(like_count), + 'dislike_count': int_or_none(dislike_count), + 'comment_count': int_or_none(comment_count), 'age_limit': age_limit, + 'categories': categories, + 'formats': formats, } + + +class XHamsterEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P\d+)' % XHamsterIE._DOMAINS + _TEST = { + 'url': 'http://xhamster.com/xembed.php?video=3328539', + 'info_dict': { + 'id': '3328539', + 'ext': 'mp4', + 'title': 'Pen Masturbation', + 'timestamp': 1406581861, + 'upload_date': '20140728', + 'uploader': 'ManyakisArt', + '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/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id), + webpage, 'xhamster url', default=None) + + if not video_url: + vars = self._parse_json( + self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'), + video_id) + video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl')) + + return self.url_result(video_url, 'XHamster') + + +class XHamsterUserIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P[^/?#&]+)' % XHamsterIE._DOMAINS + _TESTS = [{ + # Paginated user profile + 'url': 'https://xhamster.com/users/netvideogirls/videos', + 'info_dict': { + 'id': 'netvideogirls', + }, + 'playlist_mincount': 267, + }, { + # Non-paginated user profile + 'url': 'https://xhamster.com/users/firatkaan/videos', + 'info_dict': { + 'id': 'firatkaan', + }, + 'playlist_mincount': 1, + }] + + def _entries(self, user_id): + next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id + for pagenum in itertools.count(1): + page = self._download_webpage( + next_page_url, user_id, 'Downloading page %s' % pagenum) + for video_tag in re.findall( + r'(]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)', + page): + video = extract_attributes(video_tag) + video_url = url_or_none(video.get('href')) + if not video_url or not XHamsterIE.suitable(video_url): + continue + video_id = XHamsterIE._match_id(video_url) + yield self.url_result( + video_url, ie=XHamsterIE.ie_key(), video_id=video_id) + mobj = re.search(r']+data-page=["\']next[^>]+>', page) + if not mobj: + break + next_page = extract_attributes(mobj.group(0)) + next_page_url = url_or_none(next_page.get('href')) + if not next_page_url: + break + + def _real_extract(self, url): + user_id = self._match_id(url) + return self.playlist_result(self._entries(user_id), user_id)