Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/meta.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .pladform import PladformIE
   6 from ..utils import (
   7     unescapeHTML,
   8     int_or_none,
   9     ExtractorError,
  10 )
  11
  12
  13 class METAIE(InfoExtractor):
  14     _VALID_URL = r'https?://video\.meta\.ua/(?:iframe/)?(?P<id>[0-9]+)'
  15     _TESTS = [{
  16         'url': 'http://video.meta.ua/5502115.video',
  17         'md5': '71b6f3ee274bef16f1ab410f7f56b476',
  18         'info_dict': {
  19             'id': '5502115',
  20             'ext': 'mp4',
  21             'title': 'Sony Xperia Z camera test [HQ]',
  22             'description': 'Xperia Z shoots video in FullHD HDR.',
  23             'uploader_id': 'nomobile',
  24             'uploader': 'CHЁZA.TV',
  25             'upload_date': '20130211',
  26         },
  27         'add_ie': ['Youtube'],
  28     }, {
  29         'url': 'http://video.meta.ua/iframe/5502115',
  30         'only_matching': True,
  31     }, {
  32         # pladform embed
  33         'url': 'http://video.meta.ua/7121015.video',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39         webpage = self._download_webpage(url, video_id)
  40
  41         st_html5 = self._search_regex(
  42             r"st_html5\s*=\s*'#([^']+)'", webpage, 'uppod html5 st', default=None)
  43
  44         if st_html5:
  45             # uppod st decryption algorithm is reverse engineered from function un(s) at uppod.js
  46             json_str = ''
  47             for i in range(0, len(st_html5), 3):
  48                 json_str += '&#x0%s;' % st_html5[i:i + 3]
  49             uppod_data = self._parse_json(unescapeHTML(json_str), video_id)
  50             error = uppod_data.get('customnotfound')
  51             if error:
  52                 raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
  53
  54             video_url = uppod_data['file']
  55             info = {
  56                 'id': video_id,
  57                 'url': video_url,
  58                 'title': uppod_data.get('comment') or self._og_search_title(webpage),
  59                 'description': self._og_search_description(webpage, default=None),
  60                 'thumbnail': uppod_data.get('poster') or self._og_search_thumbnail(webpage),
  61                 'duration': int_or_none(self._og_search_property(
  62                     'video:duration', webpage, default=None)),
  63             }
  64             if 'youtube.com/' in video_url:
  65                 info.update({
  66                     '_type': 'url_transparent',
  67                     'ie_key': 'Youtube',
  68                 })
  69             return info
  70
  71         pladform_url = PladformIE._extract_url(webpage)
  72         if pladform_url:
  73             return self.url_result(pladform_url)