yt_dlp/extractor/pladform.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     ExtractorError,
   5     int_or_none,
   6     parse_qs,
   7     xpath_text,
   8     qualities,
   9 )
  10
  11
  12 class PladformIE(InfoExtractor):
  13     _VALID_URL = r'''(?x)
  14                     https?://
  15                         (?:
  16                             (?:
  17                                 out\.pladform\.ru/player|
  18                                 static\.pladform\.ru/player\.swf
  19                             )
  20                             \?.*\bvideoid=|
  21                             video\.pladform\.ru/catalog/video/videoid/
  22                         )
  23                         (?P<id>\d+)
  24                     '''
  25     _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1']
  26     _TESTS = [{
  27         'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282',
  28         'info_dict': {
  29             'id': '6216d548e755edae6e8280667d774791',
  30             'ext': 'mp4',
  31             'timestamp': 1406117012,
  32             'title': 'Гарик Мартиросян и Гарик Харламов - Кастинг на концерт ко Дню милиции',
  33             'age_limit': 0,
  34             'upload_date': '20140723',
  35             'thumbnail': str,
  36             'view_count': int,
  37             'description': str,
  38             'category': list,
  39             'uploader_id': '12082',
  40             'uploader': 'Comedy Club',
  41             'duration': 367,
  42         },
  43         'expected_warnings': ['HTTP Error 404: Not Found']
  44     }, {
  45         'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
  46         'md5': '53362fac3a27352da20fa2803cc5cd6f',
  47         'info_dict': {
  48             'id': '3777899',
  49             'ext': 'mp4',
  50             'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
  51             'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
  52             'thumbnail': r're:^https?://.*\.jpg$',
  53             'duration': 3190,
  54         },
  55     }, {
  56         'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
  57         'only_matching': True,
  58     }, {
  59         'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
  60         'only_matching': True,
  61     }]
  62
  63     def _real_extract(self, url):
  64         video_id = self._match_id(url)
  65
  66         qs = parse_qs(url)
  67         pl = qs.get('pl', ['1'])[0]
  68
  69         video = self._download_xml(
  70             'http://out.pladform.ru/getVideo', video_id, query={
  71                 'pl': pl,
  72                 'videoid': video_id,
  73             }, fatal=False)
  74
  75         def fail(text):
  76             raise ExtractorError(
  77                 '%s returned error: %s' % (self.IE_NAME, text),
  78                 expected=True)
  79
  80         if not video:
  81             targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').geturl()
  82             if targetUrl == url:
  83                 raise ExtractorError('Can\'t parse page')
  84             return self.url_result(targetUrl)
  85
  86         if video.tag == 'error':
  87             fail(video.text)
  88
  89         quality = qualities(('ld', 'sd', 'hd'))
  90
  91         formats = []
  92         for src in video.findall('./src'):
  93             if src is None:
  94                 continue
  95             format_url = src.text
  96             if not format_url:
  97                 continue
  98             if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
  99                 formats.extend(self._extract_m3u8_formats(
 100                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 101                     m3u8_id='hls', fatal=False))
 102             else:
 103                 formats.append({
 104                     'url': src.text,
 105                     'format_id': src.get('quality'),
 106                     'quality': quality(src.get('quality')),
 107                 })
 108
 109         if not formats:
 110             error = xpath_text(video, './cap', 'error', default=None)
 111             if error:
 112                 fail(error)
 113
 114         self._sort_formats(formats)
 115
 116         webpage = self._download_webpage(
 117             'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
 118             video_id)
 119
 120         title = self._og_search_title(webpage, fatal=False) or xpath_text(
 121             video, './/title', 'title', fatal=True)
 122         description = self._search_regex(
 123             r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
 124         thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
 125             video, './/cover', 'cover')
 126
 127         duration = int_or_none(xpath_text(video, './/time', 'duration'))
 128         age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
 129
 130         return {
 131             'id': video_id,
 132             'title': title,
 133             'description': description,
 134             'thumbnail': thumbnail,
 135             'duration': duration,
 136             'age_limit': age_limit,
 137             'formats': formats,
 138         }