yt_dlp/extractor/pladform.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     ExtractorError,
  10     int_or_none,
  11     parse_qs,
  12     xpath_text,
  13     qualities,
  14 )
  15
  16
  17 class PladformIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)
  19                     https?://
  20                         (?:
  21                             (?:
  22                                 out\.pladform\.ru/player|
  23                                 static\.pladform\.ru/player\.swf
  24                             )
  25                             \?.*\bvideoid=|
  26                             video\.pladform\.ru/catalog/video/videoid/
  27                         )
  28                         (?P<id>\d+)
  29                     '''
  30     _TESTS = [{
  31         'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282',
  32         'info_dict': {
  33             'id': '6216d548e755edae6e8280667d774791',
  34             'ext': 'mp4',
  35             'timestamp': 1406117012,
  36             'title': 'Гарик Мартиросян и Гарик Харламов - Кастинг на концерт ко Дню милиции',
  37             'age_limit': 0,
  38             'upload_date': '20140723',
  39             'thumbnail': str,
  40             'view_count': int,
  41             'description': str,
  42             'category': list,
  43             'uploader_id': '12082',
  44             'uploader': 'Comedy Club',
  45             'duration': 367,
  46         },
  47         'expected_warnings': ['HTTP Error 404: Not Found']
  48     }, {
  49         'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
  50         'md5': '53362fac3a27352da20fa2803cc5cd6f',
  51         'info_dict': {
  52             'id': '3777899',
  53             'ext': 'mp4',
  54             'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
  55             'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
  56             'thumbnail': r're:^https?://.*\.jpg$',
  57             'duration': 3190,
  58         },
  59     }, {
  60         'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
  61         'only_matching': True,
  62     }, {
  63         'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
  64         'only_matching': True,
  65     }]
  66
  67     @staticmethod
  68     def _extract_url(webpage):
  69         mobj = re.search(
  70             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1', webpage)
  71         if mobj:
  72             return mobj.group('url')
  73
  74     def _real_extract(self, url):
  75         video_id = self._match_id(url)
  76
  77         qs = parse_qs(url)
  78         pl = qs.get('pl', ['1'])[0]
  79
  80         video = self._download_xml(
  81             'http://out.pladform.ru/getVideo', video_id, query={
  82                 'pl': pl,
  83                 'videoid': video_id,
  84             }, fatal=False)
  85
  86         def fail(text):
  87             raise ExtractorError(
  88                 '%s returned error: %s' % (self.IE_NAME, text),
  89                 expected=True)
  90
  91         if not video:
  92             targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').geturl()
  93             if targetUrl == url:
  94                 raise ExtractorError('Can\'t parse page')
  95             return self.url_result(targetUrl)
  96
  97         if video.tag == 'error':
  98             fail(video.text)
  99
 100         quality = qualities(('ld', 'sd', 'hd'))
 101
 102         formats = []
 103         for src in video.findall('./src'):
 104             if src is None:
 105                 continue
 106             format_url = src.text
 107             if not format_url:
 108                 continue
 109             if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
 110                 formats.extend(self._extract_m3u8_formats(
 111                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 112                     m3u8_id='hls', fatal=False))
 113             else:
 114                 formats.append({
 115                     'url': src.text,
 116                     'format_id': src.get('quality'),
 117                     'quality': quality(src.get('quality')),
 118                 })
 119
 120         if not formats:
 121             error = xpath_text(video, './cap', 'error', default=None)
 122             if error:
 123                 fail(error)
 124
 125         self._sort_formats(formats)
 126
 127         webpage = self._download_webpage(
 128             'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
 129             video_id)
 130
 131         title = self._og_search_title(webpage, fatal=False) or xpath_text(
 132             video, './/title', 'title', fatal=True)
 133         description = self._search_regex(
 134             r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
 135         thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
 136             video, './/cover', 'cover')
 137
 138         duration = int_or_none(xpath_text(video, './/time', 'duration'))
 139         age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
 140
 141         return {
 142             'id': video_id,
 143             'title': title,
 144             'description': description,
 145             'thumbnail': thumbnail,
 146             'duration': duration,
 147             'age_limit': age_limit,
 148             'formats': formats,
 149         }