yt_dlp/extractor/giantbomb.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     int_or_none,
   9     qualities,
  10     unescapeHTML,
  11 )
  12
  13
  14 class GiantBombIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?giantbomb\.com/(?:videos|shows)/(?P<display_id>[^/]+)/(?P<id>\d+-\d+)'
  16     _TESTS = [{
  17         'url': 'http://www.giantbomb.com/videos/quick-look-destiny-the-dark-below/2300-9782/',
  18         'md5': '132f5a803e7e0ab0e274d84bda1e77ae',
  19         'info_dict': {
  20             'id': '2300-9782',
  21             'display_id': 'quick-look-destiny-the-dark-below',
  22             'ext': 'mp4',
  23             'title': 'Quick Look: Destiny: The Dark Below',
  24             'description': 'md5:0aa3aaf2772a41b91d44c63f30dfad24',
  25             'duration': 2399,
  26             'thumbnail': r're:^https?://.*\.jpg$',
  27         }
  28     }, {
  29         'url': 'https://www.giantbomb.com/shows/ben-stranding/2970-20212',
  30         'only_matching': True,
  31     }]
  32
  33     def _real_extract(self, url):
  34         mobj = self._match_valid_url(url)
  35         video_id = mobj.group('id')
  36         display_id = mobj.group('display_id')
  37
  38         webpage = self._download_webpage(url, display_id)
  39
  40         title = self._og_search_title(webpage)
  41         description = self._og_search_description(webpage)
  42         thumbnail = self._og_search_thumbnail(webpage)
  43
  44         video = json.loads(unescapeHTML(self._search_regex(
  45             r'data-video="([^"]+)"', webpage, 'data-video')))
  46
  47         duration = int_or_none(video.get('lengthSeconds'))
  48
  49         quality = qualities([
  50             'f4m_low', 'progressive_low', 'f4m_high',
  51             'progressive_high', 'f4m_hd', 'progressive_hd'])
  52
  53         formats = []
  54         for format_id, video_url in video['videoStreams'].items():
  55             if format_id == 'f4m_stream':
  56                 continue
  57             ext = determine_ext(video_url)
  58             if ext == 'f4m':
  59                 f4m_formats = self._extract_f4m_formats(video_url + '?hdcore=3.3.1', display_id)
  60                 if f4m_formats:
  61                     f4m_formats[0]['quality'] = quality(format_id)
  62                     formats.extend(f4m_formats)
  63             elif ext == 'm3u8':
  64                 formats.extend(self._extract_m3u8_formats(
  65                     video_url, display_id, ext='mp4', entry_protocol='m3u8_native',
  66                     m3u8_id='hls', fatal=False))
  67             else:
  68                 formats.append({
  69                     'url': video_url,
  70                     'format_id': format_id,
  71                     'quality': quality(format_id),
  72                 })
  73
  74         if not formats:
  75             youtube_id = video.get('youtubeID')
  76             if youtube_id:
  77                 return self.url_result(youtube_id, 'Youtube')
  78
  79         self._sort_formats(formats)
  80
  81         return {
  82             'id': video_id,
  83             'display_id': display_id,
  84             'title': title,
  85             'description': description,
  86             'thumbnail': thumbnail,
  87             'duration': duration,
  88             'formats': formats,
  89         }