yt_dlp/extractor/pladform.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     determine_ext,
   6     ExtractorError,
   7     int_or_none,
   8     parse_qs,
   9     xpath_text,
  10     qualities,
  11 )
  12
  13
  14 class PladformIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:
  18                             (?:
  19                                 out\.pladform\.ru/player|
  20                                 static\.pladform\.ru/player\.swf
  21                             )
  22                             \?.*\bvideoid=|
  23                             video\.pladform\.ru/catalog/video/videoid/
  24                         )
  25                         (?P<id>\d+)
  26                     '''
  27     _TESTS = [{
  28         'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282',
  29         'info_dict': {
  30             'id': '6216d548e755edae6e8280667d774791',
  31             'ext': 'mp4',
  32             'timestamp': 1406117012,
  33             'title': 'Гарик Мартиросян и Гарик Харламов - Кастинг на концерт ко Дню милиции',
  34             'age_limit': 0,
  35             'upload_date': '20140723',
  36             'thumbnail': str,
  37             'view_count': int,
  38             'description': str,
  39             'category': list,
  40             'uploader_id': '12082',
  41             'uploader': 'Comedy Club',
  42             'duration': 367,
  43         },
  44         'expected_warnings': ['HTTP Error 404: Not Found']
  45     }, {
  46         'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
  47         'md5': '53362fac3a27352da20fa2803cc5cd6f',
  48         'info_dict': {
  49             'id': '3777899',
  50             'ext': 'mp4',
  51             'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
  52             'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
  53             'thumbnail': r're:^https?://.*\.jpg$',
  54             'duration': 3190,
  55         },
  56     }, {
  57         'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
  58         'only_matching': True,
  59     }, {
  60         'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
  61         'only_matching': True,
  62     }]
  63
  64     @staticmethod
  65     def _extract_url(webpage):
  66         mobj = re.search(
  67             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1', webpage)
  68         if mobj:
  69             return mobj.group('url')
  70
  71     def _real_extract(self, url):
  72         video_id = self._match_id(url)
  73
  74         qs = parse_qs(url)
  75         pl = qs.get('pl', ['1'])[0]
  76
  77         video = self._download_xml(
  78             'http://out.pladform.ru/getVideo', video_id, query={
  79                 'pl': pl,
  80                 'videoid': video_id,
  81             }, fatal=False)
  82
  83         def fail(text):
  84             raise ExtractorError(
  85                 '%s returned error: %s' % (self.IE_NAME, text),
  86                 expected=True)
  87
  88         if not video:
  89             targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').geturl()
  90             if targetUrl == url:
  91                 raise ExtractorError('Can\'t parse page')
  92             return self.url_result(targetUrl)
  93
  94         if video.tag == 'error':
  95             fail(video.text)
  96
  97         quality = qualities(('ld', 'sd', 'hd'))
  98
  99         formats = []
 100         for src in video.findall('./src'):
 101             if src is None:
 102                 continue
 103             format_url = src.text
 104             if not format_url:
 105                 continue
 106             if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
 107                 formats.extend(self._extract_m3u8_formats(
 108                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 109                     m3u8_id='hls', fatal=False))
 110             else:
 111                 formats.append({
 112                     'url': src.text,
 113                     'format_id': src.get('quality'),
 114                     'quality': quality(src.get('quality')),
 115                 })
 116
 117         if not formats:
 118             error = xpath_text(video, './cap', 'error', default=None)
 119             if error:
 120                 fail(error)
 121
 122         self._sort_formats(formats)
 123
 124         webpage = self._download_webpage(
 125             'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
 126             video_id)
 127
 128         title = self._og_search_title(webpage, fatal=False) or xpath_text(
 129             video, './/title', 'title', fatal=True)
 130         description = self._search_regex(
 131             r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
 132         thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
 133             video, './/cover', 'cover')
 134
 135         duration = int_or_none(xpath_text(video, './/time', 'duration'))
 136         age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
 137
 138         return {
 139             'id': video_id,
 140             'title': title,
 141             'description': description,
 142             'thumbnail': thumbnail,
 143             'duration': duration,
 144             'age_limit': age_limit,
 145             'formats': formats,
 146         }