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 ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     xpath_text,
  11     qualities,
  12 )
  13
  14
  15 class PladformIE(InfoExtractor):
  16     _VALID_URL = r'''(?x)
  17                     https?://
  18                         (?:
  19                             (?:
  20                                 out\.pladform\.ru/player|
  21                                 static\.pladform\.ru/player\.swf
  22                             )
  23                             \?.*\bvideoid=|
  24                             video\.pladform\.ru/catalog/video/videoid/
  25                         )
  26                         (?P<id>\d+)
  27                     '''
  28     _TESTS = [{
  29         # http://muz-tv.ru/kinozal/view/7400/
  30         'url': 'http://out.pladform.ru/player?pl=24822&videoid=100183293',
  31         'md5': '61f37b575dd27f1bb2e1854777fe31f4',
  32         'info_dict': {
  33             'id': '100183293',
  34             'ext': 'mp4',
  35             'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  36             'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  37             'thumbnail': r're:^https?://.*\.jpg$',
  38             'duration': 694,
  39             'age_limit': 0,
  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         video = self._download_xml(
  60             'http://out.pladform.ru/getVideo?pl=1&videoid=%s' % video_id,
  61             video_id)
  62
  63         if video.tag == 'error':
  64             raise ExtractorError(
  65                 '%s returned error: %s' % (self.IE_NAME, video.text),
  66                 expected=True)
  67
  68         quality = qualities(('ld', 'sd', 'hd'))
  69
  70         formats = [{
  71             'url': src.text,
  72             'format_id': src.get('quality'),
  73             'quality': quality(src.get('quality')),
  74         } for src in video.findall('./src')]
  75         self._sort_formats(formats)
  76
  77         webpage = self._download_webpage(
  78             'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
  79             video_id)
  80
  81         title = self._og_search_title(webpage, fatal=False) or xpath_text(
  82             video, './/title', 'title', fatal=True)
  83         description = self._search_regex(
  84             r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
  85         thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
  86             video, './/cover', 'cover')
  87
  88         duration = int_or_none(xpath_text(video, './/time', 'duration'))
  89         age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
  90
  91         return {
  92             'id': video_id,
  93             'title': title,
  94             'description': description,
  95             'thumbnail': thumbnail,
  96             'duration': duration,
  97             'age_limit': age_limit,
  98             'formats': formats,
  99         }