Raphaël G. Git Repositories - youtubedl/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/(?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:ca0d47afff4a9b2942e4b41aa970fd93',
  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
  69     def _real_extract(self, url):
  70         mobj = re.match(self._VALID_URL, url)
  71         video_id = mobj.group('id')
  72         display_id = mobj.group('display_id')
  73
  74         if not display_id:
  75             display_id = video_id
  76
  77         if video_id.isdigit() and len(video_id) < 11:
  78             url_pattern = 'http://www.xtube.com/video-watch/-%s'
  79         else:
  80             url_pattern = 'http://www.xtube.com/watch.php?v=%s'
  81
  82         webpage = self._download_webpage(
  83             url_pattern % video_id, display_id, headers={
  84                 'Cookie': 'age_verified=1; cookiesAccepted=1',
  85             })
  86
  87         sources = self._parse_json(self._search_regex(
  88             r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),',
  89             webpage, 'sources', group='sources'), video_id,
  90             transform_source=js_to_json)
  91
  92         formats = []
  93         for format_id, format_url in sources.items():
  94             formats.append({
  95                 'url': format_url,
  96                 'format_id': format_id,
  97                 'height': int_or_none(format_id),
  98             })
  99         self._remove_duplicate_formats(formats)
 100         self._sort_formats(formats)
 101
 102         title = self._search_regex(
 103             (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'),
 104             webpage, 'title', group='title')
 105         description = self._search_regex(
 106             r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
 107         uploader = self._search_regex(
 108             (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"',
 109              r'<span[^>]+class="nickname"[^>]*>([^<]+)'),
 110             webpage, 'uploader', fatal=False)
 111         duration = parse_duration(self._search_regex(
 112             r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>',
 113             webpage, 'duration', fatal=False))
 114         view_count = str_to_int(self._search_regex(
 115             r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>',
 116             webpage, 'view count', fatal=False))
 117         comment_count = str_to_int(self._html_search_regex(
 118             r'>Comments? \(([\d,\.]+)\)<',
 119             webpage, 'comment count', fatal=False))
 120
 121         return {
 122             'id': video_id,
 123             'display_id': display_id,
 124             'title': title,
 125             'description': description,
 126             'uploader': uploader,
 127             'duration': duration,
 128             'view_count': view_count,
 129             'comment_count': comment_count,
 130             'age_limit': 18,
 131             'formats': formats,
 132         }
 133
 134
 135 class XTubeUserIE(InfoExtractor):
 136     IE_DESC = 'XTube user profile'
 137     _VALID_URL = r'https?://(?:www\.)?xtube\.com/profile/(?P<id>[^/]+-\d+)'
 138     _TEST = {
 139         'url': 'http://www.xtube.com/profile/greenshowers-4056496',
 140         'info_dict': {
 141             'id': 'greenshowers-4056496',
 142             'age_limit': 18,
 143         },
 144         'playlist_mincount': 155,
 145     }
 146
 147     def _real_extract(self, url):
 148         user_id = self._match_id(url)
 149
 150         entries = []
 151         for pagenum in itertools.count(1):
 152             request = sanitized_Request(
 153                 'http://www.xtube.com/profile/%s/videos/%d' % (user_id, pagenum),
 154                 headers={
 155                     'Cookie': 'popunder=4',
 156                     'X-Requested-With': 'XMLHttpRequest',
 157                     'Referer': url,
 158                 })
 159
 160             page = self._download_json(
 161                 request, user_id, 'Downloading videos JSON page %d' % pagenum)
 162
 163             html = page.get('html')
 164             if not html:
 165                 break
 166
 167             for video_id in orderedSet([video_id for _, video_id in re.findall(
 168                     r'data-plid=(["\'])(.+?)\1', html)]):
 169                 entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key()))
 170
 171             page_count = int_or_none(page.get('pageCount'))
 172             if not page_count or pagenum == page_count:
 173                 break
 174
 175         playlist = self.playlist_result(entries, user_id)
 176         playlist['age_limit'] = 18
 177         return playlist