X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/4231113a7be907539052ce59df44e23c54d21d38..20205e79eb4216762c923790b27dbe38f945293a:/youtube_dl/extractor/xhamster.py diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index be3624e..76aeaf9 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -1,75 +1,84 @@ from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( clean_html, + determine_ext, dict_get, + extract_attributes, ExtractorError, int_or_none, parse_duration, + try_get, unified_strdate, + url_or_none, ) class XHamsterIE(InfoExtractor): + _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)' _VALID_URL = r'''(?x) https?:// - (?:.+?\.)?xhamster\.com/ + (?:.+?\.)?%s/ (?: - movies/(?P\d+)/(?P[^/]*)\.html| - videos/(?P[^/]*)-(?P\d+) + movies/(?P[\dA-Za-z]+)/(?P[^/]*)\.html| + videos/(?P[^/]*)-(?P[\dA-Za-z]+) ) - ''' - + ''' % _DOMAINS _TESTS = [{ - 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', - 'md5': '8281348b8d3c53d39fffb377d24eac4e', + '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', + '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, - 'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'], }, }, { - 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', + 'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=', 'info_dict': { 'id': '2221348', - 'display_id': 'britney_spears_sexy_booty', + '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, - 'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'], }, 'params': { 'skip_download': True, }, }, { - # empty seo + # 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, - 'categories': ['Amateur', 'Blowjobs'], }, '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, @@ -81,6 +90,30 @@ class XHamsterIE(InfoExtractor): # 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': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'only_matching': True, + }, { + 'url': 'https://xhamster26.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, + }, { + 'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx', + 'only_matching': True, }] def _real_extract(self, url): @@ -88,7 +121,8 @@ class XHamsterIE(InfoExtractor): video_id = mobj.group('id') or mobj.group('id_2') display_id = mobj.group('display_id') or mobj.group('display_id_2') - webpage = self._download_webpage(url, video_id) + desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) + webpage, urlh = self._download_webpage_handle(desktop_url, video_id) error = self._html_search_regex( r']+id=["\']videoClosed["\'][^>]*>(.+?)', @@ -96,6 +130,88 @@ class XHamsterIE(InfoExtractor): 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*', + r'window\.initials\s*=\s*({.+?})\s*;'), 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, + 'http_headers': { + 'Referer': urlh.geturl(), + }, + }) + 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: + categories = None + + 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, + } + + # Old layout fallback + title = self._html_search_regex( [r']*>([^<]+)', r']+itemprop=".*?caption.*?"[^>]+content="(.+?)"', @@ -111,7 +227,8 @@ class XHamsterIE(InfoExtractor): default='{}'), video_id, fatal=False) for format_id, format_url in sources.items(): - if not isinstance(format_url, compat_str): + format_url = url_or_none(format_url) + if not format_url: continue if format_url in format_urls: continue @@ -119,8 +236,7 @@ class XHamsterIE(InfoExtractor): formats.append({ 'format_id': format_id, 'url': format_url, - 'height': int_or_none(self._search_regex( - r'^(\d+)[pP]', format_id, 'height', default=None)) + 'height': get_height(format_id), }) video_url = self._search_regex( @@ -148,8 +264,8 @@ class XHamsterIE(InfoExtractor): webpage, 'uploader', default='anonymous') thumbnail = self._search_regex( - [r'''thumb\s*:\s*(?P["'])(?P.+?)(?P=q)''', - r''']+poster=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + [r'''["']thumbUrl["']\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r''']+"poster"=(?P["'])(?P.+?)(?P=q)[^>]*>'''], webpage, 'thumbnail', fatal=False, group='thumbnail') duration = parse_duration(self._search_regex( @@ -167,8 +283,6 @@ class XHamsterIE(InfoExtractor): mobj = re.search(r'Comments \((?P\d+)\)', webpage) comment_count = mobj.group('commentcount') if mobj else 0 - age_limit = self._rta_search(webpage) - categories_html = self._search_regex( r'(?s)Categories:.+?)', webpage, 'categories', default=None) @@ -195,15 +309,16 @@ class XHamsterIE(InfoExtractor): class XHamsterEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P\d+)' + _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_id': 'anonymous', + 'uploader': 'ManyakisArt', 'duration': 5, 'age_limit': 18, } @@ -231,3 +346,49 @@ class XHamsterEmbedIE(InfoExtractor): 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)