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     url_or_none,
  15 )
  16
  17
  18 class XTubeIE(InfoExtractor):
  19     _VALID_URL = r'''(?x)
  20                         (?:
  21                             xtube:|
  22                             https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P<display_id>[^/]+)-)
  23                         )
  24                         (?P<id>[^/?&#]+)
  25                     '''
  26
  27     _TESTS = [{
  28         # old URL schema
  29         'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
  30         'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
  31         'info_dict': {
  32             'id': 'kVTUy_G222_',
  33             'ext': 'mp4',
  34             'title': 'strange erotica',
  35             'description': 'contains:an ET kind of thing',
  36             'uploader': 'greenshowers',
  37             'duration': 450,
  38             'view_count': int,
  39             'comment_count': int,
  40             'age_limit': 18,
  41         }
  42     }, {
  43         # FLV videos with duplicated formats
  44         'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
  45         'md5': 'a406963eb349dd43692ec54631efd88b',
  46         'info_dict': {
  47             'id': '9299752',
  48             'display_id': 'A-Super-Run-Part-1-YT',
  49             'ext': 'flv',
  50             'title': 'A Super Run - Part 1 (YT)',
  51             'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616',
  52             'uploader': 'tshirtguy59',
  53             'duration': 579,
  54             'view_count': int,
  55             'comment_count': int,
  56             'age_limit': 18,
  57         },
  58     }, {
  59         # new URL schema
  60         'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
  61         'only_matching': True,
  62     }, {
  63         'url': 'xtube:625837',
  64         'only_matching': True,
  65     }, {
  66         'url': 'xtube:kVTUy_G222_',
  67         'only_matching': True,
  68     }, {
  69         'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big',
  70         'only_matching': True,
  71     }]
  72
  73     def _real_extract(self, url):
  74         mobj = re.match(self._VALID_URL, url)
  75         video_id = mobj.group('id')
  76         display_id = mobj.group('display_id')
  77
  78         if not display_id:
  79             display_id = video_id
  80
  81         if video_id.isdigit() and len(video_id) < 11:
  82             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  83         else:
  84             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  85
  86         webpage = self._download_webpage(
  87             url_pattern % video_id, display_id, headers={
  88                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  89             })
  90
  91         title, thumbnail, duration, sources, media_definition = [None] * 5
  92
  93         config = self._parse_json(self._search_regex(
  94             r'playerConf\s*=\s*({.+?})\s*,\s*(?:\n|loaderConf|playerWrapper)', webpage, 'config',
  95             default='{}'), video_id, transform_source=js_to_json, fatal=False)
  96         if config:
  97             config = config.get('mainRoll')
  98             if isinstance(config, dict):
  99                 title = config.get('title')
 100                 thumbnail = config.get('poster')
 101                 duration = int_or_none(config.get('duration'))
 102                 sources = config.get('sources') or config.get('format')
 103                 media_definition = config.get('mediaDefinition')
 104
 105         if not isinstance(sources, dict) and not media_definition:
 106             sources = self._parse_json(self._search_regex(
 107                 r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
 108                 webpage, 'sources', group='sources'), video_id,
 109                 transform_source=js_to_json)
 110
 111         formats = []
 112         format_urls = set()
 113
 114         if isinstance(sources, dict):
 115             for format_id, format_url in sources.items():
 116                 format_url = url_or_none(format_url)
 117                 if not format_url:
 118                     continue
 119                 if format_url in format_urls:
 120                     continue
 121                 format_urls.add(format_url)
 122                 formats.append({
 123                     'url': format_url,
 124                     'format_id': format_id,
 125                     'height': int_or_none(format_id),
 126                 })
 127
 128         if isinstance(media_definition, list):
 129             for media in media_definition:
 130                 video_url = url_or_none(media.get('videoUrl'))
 131                 if not video_url:
 132                     continue
 133                 if video_url in format_urls:
 134                     continue
 135                 format_urls.add(video_url)
 136                 format_id = media.get('format')
 137                 if format_id == 'hls':
 138                     formats.extend(self._extract_m3u8_formats(
 139                         video_url, video_id, 'mp4', entry_protocol='m3u8_native',
 140                         m3u8_id='hls', fatal=False))
 141                 elif format_id == 'mp4':
 142                     height = int_or_none(media.get('quality'))
 143                     formats.append({
 144                         'url': video_url,
 145                         'format_id': '%s-%d' % (format_id, height) if height else format_id,
 146                         'height': height,
 147                     })
 148
 149         self._remove_duplicate_formats(formats)
 150         self._sort_formats(formats)
 151
 152         if not title:
 153             title = self._search_regex(
 154                 (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
 155                 webpage, 'title', group='title')
 156         description = self._og_search_description(
 157             webpage, default=None) or self._html_search_meta(
 158             'twitter:description', webpage, default=None) or self._search_regex(
 159             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
 160         uploader = self._search_regex(
 161             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
 162              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
 163             webpage, 'uploader', fatal=False)
 164         if not duration:
 165             duration = parse_duration(self._search_regex(
 166                 r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
 167                 webpage, 'duration', fatal=False))
 168         view_count = str_to_int(self._search_regex(
 169             (r'["\']viewsCount["\'][^>]*>(\d+)\s+views',
 170              r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'),
 171             webpage, 'view count', fatal=False))
 172         comment_count = str_to_int(self._html_search_regex(
 173             r'>Comments? \(([\d,\.]+)\)<',
 174             webpage, 'comment count', fatal=False))
 175
 176         return {
 177             'id': video_id,
 178             'display_id': display_id,
 179             'title': title,
 180             'description': description,
 181             'thumbnail': thumbnail,
 182             'uploader': uploader,
 183             'duration': duration,
 184             'view_count': view_count,
 185             'comment_count': comment_count,
 186             'age_limit': 18,
 187             'formats': formats,
 188         }
 189
 190
 191 class XTubeUserIE(InfoExtractor):
 192     IE_DESC = 'XTube user profile'
 193     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 194     _TEST = {
 195         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 196         'info_dict': {
 197             'id': 'greenshowers-4056496',
 198             'age_limit': 18,
 199         },
 200         'playlist_mincount': 154,
 201     }
 202
 203     def _real_extract(self, url):
 204         user_id = self._match_id(url)
 205
 206         entries = []
 207         for pagenum in itertools.count(1):
 208             request = sanitized_Request(
 209                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 210                 headers={
 211                     'Cookie': 'popunder=4',
 212                     'X-Requested-With': 'XMLHttpRequest',
 213                     'Referer': url,
 214                 })
 215
 216             page = self._download_json(
 217                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 218
 219             html = page.get('html')
 220             if not html:
 221                 break
 222
 223             for video_id in orderedSet([video_id for _, video_id in re.findall(
 224                     r'data-plid=(["\'])(.+?)\1', html)]):
 225                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 226
 227             page_count = int_or_none(page.get('pageCount'))
 228             if not page_count or pagenum == page_count:
 229                 break
 230
 231         playlist = self.playlist_result(entries, user_id)
 232         playlist['age_limit'] = 18
 233         return playlist