youtube_dl/extractor/wsj.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     unified_strdate,
   8 )
   9
  10
  11 class WSJIE(InfoExtractor):
  12     _VALID_URL = r'https?://video-api\.wsj\.com/api-video/player/iframe\.html\?guid=(?P<id>[a-zA-Z0-9-]+)'
  13     IE_DESC = 'Wall Street Journal'
  14     _TEST = {
  15         'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
  16         'md5': '9747d7a6ebc2f4df64b981e1dde9efa9',
  17         'info_dict': {
  18             'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
  19             'ext': 'mp4',
  20             'upload_date': '20150202',
  21             'uploader_id': 'jdesai',
  22             'creator': 'jdesai',
  23             'categories': list,  # a long list
  24             'duration': 90,
  25             'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         bitrates = [128, 174, 264, 320, 464, 664, 1264]
  33         api_url = (
  34             'http://video-api.wsj.com/api-video/find_all_videos.asp?'
  35             'type=guid&count=1&query=%s&'
  36             'fields=hls,adZone,thumbnailList,guid,state,secondsUntilStartTime,'
  37             'author,description,name,linkURL,videoStillURL,duration,videoURL,'
  38             'adCategory,catastrophic,linkShortURL,doctypeID,youtubeID,'
  39             'titletag,rssURL,wsj-section,wsj-subsection,allthingsd-section,'
  40             'allthingsd-subsection,sm-section,sm-subsection,provider,'
  41             'formattedCreationDate,keywords,keywordsOmniture,column,editor,'
  42             'emailURL,emailPartnerID,showName,omnitureProgramName,'
  43             'omnitureVideoFormat,linkRelativeURL,touchCastID,'
  44             'omniturePublishDate,%s') % (
  45                 video_id, ','.join('video%dkMP4Url' % br for br in bitrates))
  46         info = self._download_json(api_url, video_id)['items'][0]
  47
  48         # Thumbnails are conveniently in the correct format already
  49         thumbnails = info.get('thumbnailList')
  50         creator = info.get('author')
  51         uploader_id = info.get('editor')
  52         categories = info.get('keywords')
  53         duration = int_or_none(info.get('duration'))
  54         upload_date = unified_strdate(
  55             info.get('formattedCreationDate'), day_first=False)
  56         title = info.get('name', info.get('titletag'))
  57
  58         formats = [{
  59             'format_id': 'f4m',
  60             'format_note': 'f4m (meta URL)',
  61             'url': info['videoURL'],
  62         }]
  63         if info.get('hls'):
  64             formats.extend(self._extract_m3u8_formats(
  65                 info['hls'], video_id, ext='mp4',
  66                 preference=0, entry_protocol='m3u8_native'))
  67         for br in bitrates:
  68             field = 'video%dkMP4Url' % br
  69             if info.get(field):
  70                 formats.append({
  71                     'format_id': 'mp4-%d' % br,
  72                     'container': 'mp4',
  73                     'tbr': br,
  74                     'url': info[field],
  75                 })
  76         self._sort_formats(formats)
  77
  78         return {
  79             'id': video_id,
  80             'formats': formats,
  81             'thumbnails': thumbnails,
  82             'creator': creator,
  83             'uploader_id': uploader_id,
  84             'duration': duration,
  85             'upload_date': upload_date,
  86             'title': title,
  87             'categories': categories,
  88         }