youtube_dl/extractor/trutv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .turner import TurnerBaseIE
   7 from ..utils import (
   8     int_or_none,
   9     parse_iso8601,
  10 )
  11
  12
  13 class TruTVIE(TurnerBaseIE):
  14     _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P<series_slug>[0-9A-Za-z-]+)/(?:videos/(?P<clip_slug>[0-9A-Za-z-]+)|(?P<id>\d+))'
  15     _TEST = {
  16         'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html',
  17         'info_dict': {
  18             'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1',
  19             'ext': 'mp4',
  20             'title': 'Sunlight-Activated Flower',
  21             'description': "A customer is stunned when he sees Michael's sunlight-activated flower.",
  22         },
  23         'params': {
  24             # m3u8 download
  25             'skip_download': True,
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         series_slug, clip_slug, video_id = re.match(self._VALID_URL, url).groups()
  31
  32         if video_id:
  33             path = 'episode'
  34             display_id = video_id
  35         else:
  36             path = 'series/clip'
  37             display_id = clip_slug
  38
  39         data = self._download_json(
  40             'https://api.trutv.com/v2/web/%s/%s/%s' % (path, series_slug, display_id),
  41             display_id)
  42         video_data = data['episode'] if video_id else data['info']
  43         media_id = video_data['mediaId']
  44         title = video_data['title'].strip()
  45
  46         info = self._extract_ngtv_info(
  47             media_id, {}, {
  48                 'url': url,
  49                 'site_name': 'truTV',
  50                 'auth_required': video_data.get('isAuthRequired'),
  51             })
  52
  53         thumbnails = []
  54         for image in video_data.get('images', []):
  55             image_url = image.get('srcUrl')
  56             if not image_url:
  57                 continue
  58             thumbnails.append({
  59                 'url': image_url,
  60                 'width': int_or_none(image.get('width')),
  61                 'height': int_or_none(image.get('height')),
  62             })
  63
  64         info.update({
  65             'id': media_id,
  66             'display_id': display_id,
  67             'title': title,
  68             'description': video_data.get('description'),
  69             'thumbnails': thumbnails,
  70             'timestamp': parse_iso8601(video_data.get('publicationDate')),
  71             'series': video_data.get('showTitle'),
  72             'season_number': int_or_none(video_data.get('seasonNum')),
  73             'episode_number': int_or_none(video_data.get('episodeNum')),
  74         })
  75         return info