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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class TenPlayIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?ten(play)?\.com\.au/.+'
  11     _TEST = {
  12         'url': 'http://tenplay.com.au/ten-insider/extra/season-2013/tenplay-tv-your-way',
  13         #'md5': 'd68703d9f73dc8fccf3320ab34202590',
  14         'info_dict': {
  15             'id': '2695695426001',
  16             'ext': 'flv',
  17             'title': 'TENplay: TV your way',
  18             'description': 'Welcome to a new TV experience. Enjoy a taste of the TENplay benefits.',
  19             'timestamp': 1380150606.889,
  20             'upload_date': '20130925',
  21             'uploader': 'TENplay',
  22         },
  23         'params': {
  24             'skip_download': True,  # Requires rtmpdump
  25         }
  26     }
  27
  28     _video_fields = [
  29         "id", "name", "shortDescription", "longDescription", "creationDate",
  30         "publishedDate", "lastModifiedDate", "customFields", "videoStillURL",
  31         "thumbnailURL", "referenceId", "length", "playsTotal",
  32         "playsTrailingWeek", "renditions", "captioning", "startDate", "endDate"]
  33
  34     def _real_extract(self, url):
  35         webpage = self._download_webpage(url, url)
  36         video_id = self._html_search_regex(
  37             r'videoID: "(\d+?)"', webpage, 'video_id')
  38         api_token = self._html_search_regex(
  39             r'apiToken: "([a-zA-Z0-9-_\.]+?)"', webpage, 'api_token')
  40         title = self._html_search_regex(
  41             r'<meta property="og:title" content="\s*(.*?)\s*"\s*/?\s*>',
  42             webpage, 'title')
  43
  44         json = self._download_json('https://api.brightcove.com/services/library?command=find_video_by_id&video_id=%s&token=%s&video_fields=%s' % (video_id, api_token, ','.join(self._video_fields)), title)
  45
  46         formats = []
  47         for rendition in json['renditions']:
  48             url = rendition['remoteUrl'] or rendition['url']
  49             protocol = 'rtmp' if url.startswith('rtmp') else 'http'
  50             ext = 'flv' if protocol == 'rtmp' else rendition['videoContainer'].lower()
  51
  52             if protocol == 'rtmp':
  53                 url = url.replace('&mp4:', '')
  54
  55             formats.append({
  56                 'format_id': '_'.join(['rtmp', rendition['videoContainer'].lower(), rendition['videoCodec'].lower()]),
  57                 'width': rendition['frameWidth'],
  58                 'height': rendition['frameHeight'],
  59                 'tbr': rendition['encodingRate'] / 1024,
  60                 'filesize': rendition['size'],
  61                 'protocol': protocol,
  62                 'ext': ext,
  63                 'vcodec': rendition['videoCodec'].lower(),
  64                 'container': rendition['videoContainer'].lower(),
  65                 'url': url,
  66             })
  67
  68         return {
  69             'id': video_id,
  70             'display_id': json['referenceId'],
  71             'title': json['name'],
  72             'description': json['shortDescription'] or json['longDescription'],
  73             'formats': formats,
  74             'thumbnails': [{
  75                 'url': json['videoStillURL']
  76             }, {
  77                 'url': json['thumbnailURL']
  78             }],
  79             'thumbnail': json['videoStillURL'],
  80             'duration': json['length'] / 1000,
  81             'timestamp': float(json['creationDate']) / 1000,
  82             'uploader': json['customFields']['production_company_distributor'] if 'production_company_distributor' in json['customFields'] else 'TENplay',
  83             'view_count': json['playsTotal']
  84         }