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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     int_or_none,
  10     qualities,
  11     unescapeHTML,
  12 )
  13
  14
  15 class GiantBombIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/videos/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
  17     _TEST = {
  18         'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/',
  19         'md5': 'c8ea694254a59246a42831155dec57ac',
  20         'info_dict': {
  21             'id': '2300-9782',
  22             'display_id': 'quick-look-destiny-the-dark-below',
  23             'ext': 'mp4',
  24             'title': 'Quick Look: Destiny: The Dark Below',
  25             'description': 'md5:0aa3aaf2772a41b91d44c63f30dfad24',
  26             'duration': 2399,
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34         display_id = mobj.group('display_id')
  35
  36         webpage = self._download_webpage(url, display_id)
  37
  38         title = self._og_search_title(webpage)
  39         description = self._og_search_description(webpage)
  40         thumbnail = self._og_search_thumbnail(webpage)
  41
  42         video = json.loads(unescapeHTML(self._search_regex(
  43             r'data-video="([^"]+)"', webpage, 'data-video')))
  44
  45         duration = int_or_none(video.get('lengthSeconds'))
  46
  47         quality = qualities([
  48             'f4m_low', 'progressive_low', 'f4m_high',
  49             'progressive_high', 'f4m_hd', 'progressive_hd'])
  50
  51         formats = []
  52         for format_id, video_url in video['videoStreams'].items():
  53             if format_id == 'f4m_stream':
  54                 continue
  55             ext = determine_ext(video_url)
  56             if ext == 'f4m':
  57                 f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.3.1', display_id)
  58                 if f4m_formats:
  59                     f4m_formats[0]['quality'] = quality(format_id)
  60                     formats.extend(f4m_formats)
  61             elif ext == 'm3u8':
  62                 formats.extend(self._extract_m3u8_formats(
  63                     video_url, display_id, ext='mp4', entry_protocol='m3u8_native',
  64                     m3u8_id='hls', fatal=False))
  65             else:
  66                 formats.append({
  67                     'url': video_url,
  68                     'format_id': format_id,
  69                     'quality': quality(format_id),
  70                 })
  71
  72         if not formats:
  73             youtube_id = video.get('youtubeID')
  74             if youtube_id:
  75                 return self.url_result(youtube_id, 'Youtube')
  76
  77         self._sort_formats(formats)
  78
  79         return {
  80             'id': video_id,
  81             'display_id': display_id,
  82             'title': title,
  83             'description': description,
  84             'thumbnail': thumbnail,
  85             'duration': duration,
  86             'formats': formats,
  87         }