_ Git - youtube-dl/blob - youtube_dl/extractor/xtube.py

   1 from __future__ import unicode_literals
   2
   3 import itertools
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     js_to_json,
  10     orderedSet,
  11     parse_duration,
  12     sanitized_Request,
  13     str_to_int,
  14 )
  15
  16
  17 class XTubeIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)
  19                         (?:
  20                             xtube:|
  21                             https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
  22                         )
  23                         (?P<id>[^/?&#]+)
  24                     '''
  25
  26     _TESTS = [{
  27         # old URL schema
  28         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  29         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  30         'info_dict': {
  31             'id': 'kVTUy_G222_',
  32             'ext': 'mp4',
  33             'title': 'strange erotica',
  34             'description': 'contains:an ET kind of thing',
  35             'uploader': 'greenshowers',
  36             'duration': 450,
  37             'view_count': int,
  38             'comment_count': int,
  39             'age_limit': 18,
  40         }
  41     }, {
  42         # FLV videos with duplicated formats
  43         'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
  44         'md5': 'a406963eb349dd43692ec54631efd88b',
  45         'info_dict': {
  46             'id': '9299752',
  47             'display_id': 'A-Super-Run-Part-1-YT',
  48             'ext': 'flv',
  49             'title': 'A Super Run - Part 1 (YT)',
  50             'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616',
  51             'uploader': 'tshirtguy59',
  52             'duration': 579,
  53             'view_count': int,
  54             'comment_count': int,
  55             'age_limit': 18,
  56         },
  57     }, {
  58         # new URL schema
  59         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  60         'only_matching': True,
  61     }, {
  62         'url': 'xtube:625837',
  63         'only_matching': True,
  64     }, {
  65         'url': 'xtube:kVTUy_G222_',
  66         'only_matching': True,
  67     }, {
  68         'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         video_id = mobj.group('id')
  75         display_id = mobj.group('display_id')
  76
  77         if not display_id:
  78             display_id = video_id
  79
  80         if video_id.isdigit() and len(video_id) < 11:
  81             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  82         else:
  83             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  84
  85         webpage = self._download_webpage(
  86             url_pattern % video_id, display_id, headers={
  87                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  88             })
  89
  90         title, thumbnail, duration = [None] * 3
  91
  92         config = self._parse_json(self._search_regex(
  93             r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config',
  94             default='{}'), video_id, transform_source=js_to_json, fatal=False)
  95         if config:
  96             config = config.get('mainRoll')
  97             if isinstance(config, dict):
  98                 title = config.get('title')
  99                 thumbnail = config.get('poster')
 100                 duration = int_or_none(config.get('duration'))
 101                 sources = config.get('sources') or config.get('format')
 102
 103         if not isinstance(sources, dict):
 104             sources = self._parse_json(self._search_regex(
 105                 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
 106                 webpage, 'sources', group='sources'), video_id,
 107                 transform_source=js_to_json)
 108
 109         formats = []
 110         for format_id, format_url in sources.items():
 111             formats.append({
 112                 'url': format_url,
 113                 'format_id': format_id,
 114                 'height': int_or_none(format_id),
 115             })
 116         self._remove_duplicate_formats(formats)
 117         self._sort_formats(formats)
 118
 119         if not title:
 120             title = self._search_regex(
 121                 (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
 122                 webpage, 'title', group='title')
 123         description = self._og_search_description(
 124             webpage, default=None) or self._html_search_meta(
 125             'twitter:description', webpage, default=None) or self._search_regex(
 126             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
 127         uploader = self._search_regex(
 128             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
 129              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
 130             webpage, 'uploader', fatal=False)
 131         if not duration:
 132             duration = parse_duration(self._search_regex(
 133                 r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
 134                 webpage, 'duration', fatal=False))
 135         view_count = str_to_int(self._search_regex(
 136             (r'["\']viewsCount["\'][^>]*>(\d+)\s+views',
 137              r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'),
 138             webpage, 'view count', fatal=False))
 139         comment_count = str_to_int(self._html_search_regex(
 140             r'>Comments? \(([\d,\.]+)\)<',
 141             webpage, 'comment count', fatal=False))
 142
 143         return {
 144             'id': video_id,
 145             'display_id': display_id,
 146             'title': title,
 147             'description': description,
 148             'thumbnail': thumbnail,
 149             'uploader': uploader,
 150             'duration': duration,
 151             'view_count': view_count,
 152             'comment_count': comment_count,
 153             'age_limit': 18,
 154             'formats': formats,
 155         }
 156
 157
 158 class XTubeUserIE(InfoExtractor):
 159     IE_DESC = 'XTube user profile'
 160     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 161     _TEST = {
 162         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 163         'info_dict': {
 164             'id': 'greenshowers-4056496',
 165             'age_limit': 18,
 166         },
 167         'playlist_mincount': 154,
 168     }
 169
 170     def _real_extract(self, url):
 171         user_id = self._match_id(url)
 172
 173         entries = []
 174         for pagenum in itertools.count(1):
 175             request = sanitized_Request(
 176                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 177                 headers={
 178                     'Cookie': 'popunder=4',
 179                     'X-Requested-With': 'XMLHttpRequest',
 180                     'Referer': url,
 181                 })
 182
 183             page = self._download_json(
 184                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 185
 186             html = page.get('html')
 187             if not html:
 188                 break
 189
 190             for video_id in orderedSet([video_id for _, video_id in re.findall(
 191                     r'data-plid=(["\'])(.+?)\1', html)]):
 192                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 193
 194             page_count = int_or_none(page.get('pageCount'))
 195             if not page_count or pagenum == page_count:
 196                 break
 197
 198         playlist = self.playlist_result(entries, user_id)
 199         playlist['age_limit'] = 18
 200         return playlist