logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

xhamster.py (19539B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. import itertools
  5. import re
  7. from .common import InfoExtractor
  8. from ..compat import compat_str
  9. from ..utils import (
  10.     clean_html,
  11.     determine_ext,
  12.     dict_get,
  13.     extract_attributes,
  14.     ExtractorError,
  15.     float_or_none,
  16.     int_or_none,
  17.     parse_duration,
  18.     str_or_none,
  19.     try_get,
  20.     unified_strdate,
  21.     url_or_none,
  22.     urljoin,
  23. )
  26. class XHamsterIE(InfoExtractor):
  27.     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
  28.     _VALID_URL = r'''(?x)
  29.                     https?://
  30.                         (?:.+?\.)?%s/
  31.                         (?:
  32.                             movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
  33.                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
  34.                         )
  35.                     ''' % _DOMAINS
  36.     _TESTS = [{
  37.         'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  38.         'md5': '34e1ab926db5dc2750fed9e1f34304bb',
  39.         'info_dict': {
  40.             'id': '1509445',
  41.             'display_id': 'femaleagent-shy-beauty-takes-the-bait',
  42.             'ext': 'mp4',
  43.             'title': 'FemaleAgent Shy beauty takes the bait',
  44.             'timestamp': 1350194821,
  45.             'upload_date': '20121014',
  46.             'uploader': 'Ruseful2011',
  47.             'uploader_id': 'ruseful2011',
  48.             'duration': 893,
  49.             'age_limit': 18,
  50.         },
  51.     }, {
  52.         'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
  53.         'info_dict': {
  54.             'id': '2221348',
  55.             'display_id': 'britney-spears-sexy-booty',
  56.             'ext': 'mp4',
  57.             'title': 'Britney Spears  Sexy Booty',
  58.             'timestamp': 1379123460,
  59.             'upload_date': '20130914',
  60.             'uploader': 'jojo747400',
  61.             'duration': 200,
  62.             'age_limit': 18,
  63.         },
  64.         'params': {
  65.             'skip_download': True,
  66.         },
  67.     }, {
  68.         # empty seo, unavailable via new URL schema
  69.         'url': 'http://xhamster.com/movies/5667973/.html',
  70.         'info_dict': {
  71.             'id': '5667973',
  72.             'ext': 'mp4',
  73.             'title': '....',
  74.             'timestamp': 1454948101,
  75.             'upload_date': '20160208',
  76.             'uploader': 'parejafree',
  77.             'uploader_id': 'parejafree',
  78.             'duration': 72,
  79.             'age_limit': 18,
  80.         },
  81.         'params': {
  82.             'skip_download': True,
  83.         },
  84.     }, {
  85.         # mobile site
  86.         'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
  87.         'only_matching': True,
  88.     }, {
  89.         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
  90.         'only_matching': True,
  91.     }, {
  92.         # This video is visible for marcoalfa123456's friends only
  93.         'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
  94.         'only_matching': True,
  95.     }, {
  96.         # new URL schema
  97.         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
  98.         'only_matching': True,
  99.     }, {
  100.         'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  101.         'only_matching': True,
  102.     }, {
  103.         'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  104.         'only_matching': True,
  105.     }, {
  106.         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  107.         'only_matching': True,
  108.     }, {
  109.         'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  110.         'only_matching': True,
  111.     }, {
  112.         'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
  113.         'only_matching': True,
  114.     }, {
  115.         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
  116.         'only_matching': True,
  117.     }, {
  118.         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
  119.         'only_matching': True,
  120.     }, {
  121.         'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
  122.         'only_matching': True,
  123.     }, {
  124.         'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
  125.         'only_matching': True,
  126.     }, {
  127.         'url': 'https://xhvid.com/videos/lk-mm-xhc6wn6',
  128.         'only_matching': True,
  129.     }]
  131.     def _real_extract(self, url):
  132.         mobj = re.match(self._VALID_URL, url)
  133.         video_id = mobj.group('id') or mobj.group('id_2')
  134.         display_id = mobj.group('display_id') or mobj.group('display_id_2')
  136.         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
  137.         webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
  139.         error = self._html_search_regex(
  140.             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
  141.             webpage, 'error', default=None)
  142.         if error:
  143.             raise ExtractorError(error, expected=True)
  145.         age_limit = self._rta_search(webpage)
  147.         def get_height(s):
  148.             return int_or_none(self._search_regex(
  149.                 r'^(\d+)[pP]', s, 'height', default=None))
  151.         initials = self._parse_json(
  152.             self._search_regex(
  153.                 (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
  154.                  r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
  155.                 default='{}'),
  156.             video_id, fatal=False)
  157.         if initials:
  158.             video = initials['videoModel']
  159.             title = video['title']
  160.             formats = []
  161.             format_urls = set()
  162.             format_sizes = {}
  163.             sources = try_get(video, lambda x: x['sources'], dict) or {}
  164.             for format_id, formats_dict in sources.items():
  165.                 if not isinstance(formats_dict, dict):
  166.                     continue
  167.                 download_sources = try_get(sources, lambda x: x['download'], dict) or {}
  168.                 for quality, format_dict in download_sources.items():
  169.                     if not isinstance(format_dict, dict):
  170.                         continue
  171.                     format_sizes[quality] = float_or_none(format_dict.get('size'))
  172.                 for quality, format_item in formats_dict.items():
  173.                     if format_id == 'download':
  174.                         # Download link takes some time to be generated,
  175.                         # skipping for now
  176.                         continue
  177.                     format_url = format_item
  178.                     format_url = url_or_none(format_url)
  179.                     if not format_url or format_url in format_urls:
  180.                         continue
  181.                     format_urls.add(format_url)
  182.                     formats.append({
  183.                         'format_id': '%s-%s' % (format_id, quality),
  184.                         'url': format_url,
  185.                         'ext': determine_ext(format_url, 'mp4'),
  186.                         'height': get_height(quality),
  187.                         'filesize': format_sizes.get(quality),
  188.                         'http_headers': {
  189.                             'Referer': urlh.geturl(),
  190.                         },
  191.                     })
  192.             xplayer_sources = try_get(
  193.                 initials, lambda x: x['xplayerSettings']['sources'], dict)
  194.             if xplayer_sources:
  195.                 hls_sources = xplayer_sources.get('hls')
  196.                 if isinstance(hls_sources, dict):
  197.                     for hls_format_key in ('url', 'fallback'):
  198.                         hls_url = hls_sources.get(hls_format_key)
  199.                         if not hls_url:
  200.                             continue
  201.                         hls_url = urljoin(url, hls_url)
  202.                         if not hls_url or hls_url in format_urls:
  203.                             continue
  204.                         format_urls.add(hls_url)
  205.                         formats.extend(self._extract_m3u8_formats(
  206.                             hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
  207.                             m3u8_id='hls', fatal=False))
  208.                 standard_sources = xplayer_sources.get('standard')
  209.                 if isinstance(standard_sources, dict):
  210.                     for format_id, formats_list in standard_sources.items():
  211.                         if not isinstance(formats_list, list):
  212.                             continue
  213.                         for standard_format in formats_list:
  214.                             if not isinstance(standard_format, dict):
  215.                                 continue
  216.                             for standard_format_key in ('url', 'fallback'):
  217.                                 standard_url = standard_format.get(standard_format_key)
  218.                                 if not standard_url:
  219.                                     continue
  220.                                 standard_url = urljoin(url, standard_url)
  221.                                 if not standard_url or standard_url in format_urls:
  222.                                     continue
  223.                                 format_urls.add(standard_url)
  224.                                 ext = determine_ext(standard_url, 'mp4')
  225.                                 if ext == 'm3u8':
  226.                                     formats.extend(self._extract_m3u8_formats(
  227.                                         standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
  228.                                         m3u8_id='hls', fatal=False))
  229.                                     continue
  230.                                 quality = (str_or_none(standard_format.get('quality'))
  231.                                            or str_or_none(standard_format.get('label'))
  232.                                            or '')
  233.                                 formats.append({
  234.                                     'format_id': '%s-%s' % (format_id, quality),
  235.                                     'url': standard_url,
  236.                                     'ext': ext,
  237.                                     'height': get_height(quality),
  238.                                     'filesize': format_sizes.get(quality),
  239.                                     'http_headers': {
  240.                                         'Referer': standard_url,
  241.                                     },
  242.                                 })
  243.             self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
  245.             categories_list = video.get('categories')
  246.             if isinstance(categories_list, list):
  247.                 categories = []
  248.                 for c in categories_list:
  249.                     if not isinstance(c, dict):
  250.                         continue
  251.                     c_name = c.get('name')
  252.                     if isinstance(c_name, compat_str):
  253.                         categories.append(c_name)
  254.             else:
  255.                 categories = None
  257.             uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
  258.             return {
  259.                 'id': video_id,
  260.                 'display_id': display_id,
  261.                 'title': title,
  262.                 'description': video.get('description'),
  263.                 'timestamp': int_or_none(video.get('created')),
  264.                 'uploader': try_get(
  265.                     video, lambda x: x['author']['name'], compat_str),
  266.                 'uploader_url': uploader_url,
  267.                 'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
  268.                 'thumbnail': video.get('thumbURL'),
  269.                 'duration': int_or_none(video.get('duration')),
  270.                 'view_count': int_or_none(video.get('views')),
  271.                 'like_count': int_or_none(try_get(
  272.                     video, lambda x: x['rating']['likes'], int)),
  273.                 'dislike_count': int_or_none(try_get(
  274.                     video, lambda x: x['rating']['dislikes'], int)),
  275.                 'comment_count': int_or_none(video.get('views')),
  276.                 'age_limit': age_limit if age_limit is not None else 18,
  277.                 'categories': categories,
  278.                 'formats': formats,
  279.             }
  281.         # Old layout fallback
  283.         title = self._html_search_regex(
  284.             [r'<h1[^>]*>([^<]+)</h1>',
  285.              r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
  286.              r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
  287.             webpage, 'title')
  289.         formats = []
  290.         format_urls = set()
  292.         sources = self._parse_json(
  293.             self._search_regex(
  294.                 r'sources\s*:\s*({.+?})\s*,?\s*\n', webpage, 'sources',
  295.                 default='{}'),
  296.             video_id, fatal=False)
  297.         for format_id, format_url in sources.items():
  298.             format_url = url_or_none(format_url)
  299.             if not format_url:
  300.                 continue
  301.             if format_url in format_urls:
  302.                 continue
  303.             format_urls.add(format_url)
  304.             formats.append({
  305.                 'format_id': format_id,
  306.                 'url': format_url,
  307.                 'height': get_height(format_id),
  308.             })
  310.         video_url = self._search_regex(
  311.             [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
  312.              r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
  313.              r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
  314.             webpage, 'video url', group='mp4', default=None)
  315.         if video_url and video_url not in format_urls:
  316.             formats.append({
  317.                 'url': video_url,
  318.             })
  320.         self._sort_formats(formats)
  322.         # Only a few videos have an description
  323.         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
  324.         description = mobj.group(1) if mobj else None
  326.         upload_date = unified_strdate(self._search_regex(
  327.             r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
  328.             webpage, 'upload date', fatal=False))
  330.         uploader = self._html_search_regex(
  331.             r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
  332.             webpage, 'uploader', default='anonymous')
  334.         thumbnail = self._search_regex(
  335.             [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
  336.              r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
  337.             webpage, 'thumbnail', fatal=False, group='thumbnail')
  339.         duration = parse_duration(self._search_regex(
  340.             [r'<[^<]+\bitemprop=["\']duration["\'][^<]+\bcontent=["\'](.+?)["\']',
  341.              r'Runtime:\s*</span>\s*([\d:]+)'], webpage,
  342.             'duration', fatal=False))
  344.         view_count = int_or_none(self._search_regex(
  345.             r'content=["\']User(?:View|Play)s:(\d+)',
  346.             webpage, 'view count', fatal=False))
  348.         mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
  349.         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
  351.         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
  352.         comment_count = mobj.group('commentcount') if mobj else 0
  354.         categories_html = self._search_regex(
  355.             r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
  356.             'categories', default=None)
  357.         categories = [clean_html(category) for category in re.findall(
  358.             r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
  360.         return {
  361.             'id': video_id,
  362.             'display_id': display_id,
  363.             'title': title,
  364.             'description': description,
  365.             'upload_date': upload_date,
  366.             'uploader': uploader,
  367.             'uploader_id': uploader.lower() if uploader else None,
  368.             'thumbnail': thumbnail,
  369.             'duration': duration,
  370.             'view_count': view_count,
  371.             'like_count': int_or_none(like_count),
  372.             'dislike_count': int_or_none(dislike_count),
  373.             'comment_count': int_or_none(comment_count),
  374.             'age_limit': age_limit,
  375.             'categories': categories,
  376.             'formats': formats,
  377.         }
  380. class XHamsterEmbedIE(InfoExtractor):
  381.     _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
  382.     _TEST = {
  383.         'url': 'http://xhamster.com/xembed.php?video=3328539',
  384.         'info_dict': {
  385.             'id': '3328539',
  386.             'ext': 'mp4',
  387.             'title': 'Pen Masturbation',
  388.             'timestamp': 1406581861,
  389.             'upload_date': '20140728',
  390.             'uploader': 'ManyakisArt',
  391.             'duration': 5,
  392.             'age_limit': 18,
  393.         }
  394.     }
  396.     @staticmethod
  397.     def _extract_urls(webpage):
  398.         return [url for _, url in re.findall(
  399.             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1',
  400.             webpage)]
  402.     def _real_extract(self, url):
  403.         video_id = self._match_id(url)
  405.         webpage = self._download_webpage(url, video_id)
  407.         video_url = self._search_regex(
  408.             r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
  409.             webpage, 'xhamster url', default=None)
  411.         if not video_url:
  412.             vars = self._parse_json(
  413.                 self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
  414.                 video_id)
  415.             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
  417.         return self.url_result(video_url, 'XHamster')
  420. class XHamsterUserIE(InfoExtractor):
  421.     _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
  422.     _TESTS = [{
  423.         # Paginated user profile
  424.         'url': 'https://xhamster.com/users/netvideogirls/videos',
  425.         'info_dict': {
  426.             'id': 'netvideogirls',
  427.         },
  428.         'playlist_mincount': 267,
  429.     }, {
  430.         # Non-paginated user profile
  431.         'url': 'https://xhamster.com/users/firatkaan/videos',
  432.         'info_dict': {
  433.             'id': 'firatkaan',
  434.         },
  435.         'playlist_mincount': 1,
  436.     }, {
  437.         'url': 'https://xhday.com/users/mobhunter',
  438.         'only_matching': True,
  439.     }, {
  440.         'url': 'https://xhvid.com/users/pelushe21',
  441.         'only_matching': True,
  442.     }]
  444.     def _entries(self, user_id):
  445.         next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
  446.         for pagenum in itertools.count(1):
  447.             page = self._download_webpage(
  448.                 next_page_url, user_id, 'Downloading page %s' % pagenum)
  449.             for video_tag in re.findall(
  450.                     r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
  451.                     page):
  452.                 video = extract_attributes(video_tag)
  453.                 video_url = url_or_none(video.get('href'))
  454.                 if not video_url or not XHamsterIE.suitable(video_url):
  455.                     continue
  456.                 video_id = XHamsterIE._match_id(video_url)
  457.                 yield self.url_result(
  458.                     video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
  459.             mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
  460.             if not mobj:
  461.                 break
  462.             next_page = extract_attributes(mobj.group(0))
  463.             next_page_url = url_or_none(next_page.get('href'))
  464.             if not next_page_url:
  465.                 break
  467.     def _real_extract(self, url):
  468.         user_id = self._match_id(url)
  469.         return self.playlist_result(self._entries(user_id), user_id)