Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/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 ..compat import compat_urlparse
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     int_or_none,
  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': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
  32         'md5': '53362fac3a27352da20fa2803cc5cd6f',
  33         'info_dict': {
  34             'id': '3777899',
  35             'ext': 'mp4',
  36             'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
  37             'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
  38             'thumbnail': r're:^https?://.*\.jpg$',
  39             'duration': 3190,
  40         },
  41     }, {
  42         'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
  43         'only_matching': True,
  44     }, {
  45         'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
  46         'only_matching': True,
  47     }]
  48
  49     @staticmethod
  50     def _extract_url(webpage):
  51         mobj = re.search(
  52             r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1', webpage)
  53         if mobj:
  54             return mobj.group('url')
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58
  59         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  60         pl = qs.get('pl', ['1'])[0]
  61
  62         video = self._download_xml(
  63             'http://out.pladform.ru/getVideo', video_id, query={
  64                 'pl': pl,
  65                 'videoid': video_id,
  66             })
  67
  68         def fail(text):
  69             raise ExtractorError(
  70                 '%s returned error: %s' % (self.IE_NAME, text),
  71                 expected=True)
  72
  73         if video.tag == 'error':
  74             fail(video.text)
  75
  76         quality = qualities(('ld', 'sd', 'hd'))
  77
  78         formats = []
  79         for src in video.findall('./src'):
  80             if src is None:
  81                 continue
  82             format_url = src.text
  83             if not format_url:
  84                 continue
  85             if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
  86                 formats.extend(self._extract_m3u8_formats(
  87                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
  88                     m3u8_id='hls', fatal=False))
  89             else:
  90                 formats.append({
  91                     'url': src.text,
  92                     'format_id': src.get('quality'),
  93                     'quality': quality(src.get('quality')),
  94                 })
  95
  96         if not formats:
  97             error = xpath_text(video, './cap', 'error', default=None)
  98             if error:
  99                 fail(error)
 100
 101         self._sort_formats(formats)
 102
 103         webpage = self._download_webpage(
 104             'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
 105             video_id)
 106
 107         title = self._og_search_title(webpage, fatal=False) or xpath_text(
 108             video, './/title', 'title', fatal=True)
 109         description = self._search_regex(
 110             r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
 111         thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
 112             video, './/cover', 'cover')
 113
 114         duration = int_or_none(xpath_text(video, './/time', 'duration'))
 115         age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
 116
 117         return {
 118             'id': video_id,
 119             'title': title,
 120             'description': description,
 121             'thumbnail': thumbnail,
 122             'duration': duration,
 123             'age_limit': age_limit,
 124             'formats': formats,
 125         }