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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     float_or_none,
   8     unified_strdate,
   9 )
  10
  11
  12 class WSJIE(InfoExtractor):
  13     _VALID_URL = r'''(?x)
  14                         (?:
  15                             https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
  16                             https?://(?:www\.)?wsj\.com/video/[^/]+/|
  17                             wsj:
  18                         )
  19                         (?P<id>[a-fA-F0-9-]{36})
  20                     '''
  21     IE_DESC = 'Wall Street Journal'
  22     _TESTS = [{
  23         'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
  24         'md5': 'e230a5bb249075e40793b655a54a02e4',
  25         'info_dict': {
  26             'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
  27             'ext': 'mp4',
  28             'upload_date': '20150202',
  29             'uploader_id': 'jdesai',
  30             'creator': 'jdesai',
  31             'categories': list,  # a long list
  32             'duration': 90,
  33             'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
  34         },
  35     }, {
  36         'url': 'http://www.wsj.com/video/can-alphabet-build-a-smarter-city/359DDAA8-9AC1-489C-82E6-0429C1E430E0.html',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         info = self._download_json(
  44             'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
  45             query={
  46                 'type': 'guid',
  47                 'count': 1,
  48                 'query': video_id,
  49                 'fields': ','.join((
  50                     'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
  51                     'description', 'name', 'duration', 'videoURL', 'titletag',
  52                     'formattedCreationDate', 'keywords', 'editor')),
  53             })['items'][0]
  54         title = info.get('name', info.get('titletag'))
  55
  56         formats = []
  57
  58         f4m_url = info.get('videoURL')
  59         if f4m_url:
  60             formats.extend(self._extract_f4m_formats(
  61                 f4m_url, video_id, f4m_id='hds', fatal=False))
  62
  63         m3u8_url = info.get('hls')
  64         if m3u8_url:
  65             formats.extend(self._extract_m3u8_formats(
  66                 info['hls'], video_id, ext='mp4',
  67                 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  68
  69         for v in info.get('videoMP4List', []):
  70             mp4_url = v.get('url')
  71             if not mp4_url:
  72                 continue
  73             tbr = int_or_none(v.get('bitrate'))
  74             formats.append({
  75                 'url': mp4_url,
  76                 'format_id': 'http' + ('-%d' % tbr if tbr else ''),
  77                 'tbr': tbr,
  78                 'width': int_or_none(v.get('width')),
  79                 'height': int_or_none(v.get('height')),
  80                 'fps': float_or_none(v.get('fps')),
  81             })
  82         self._sort_formats(formats)
  83
  84         return {
  85             'id': video_id,
  86             'formats': formats,
  87             # Thumbnails are conveniently in the correct format already
  88             'thumbnails': info.get('thumbnailList'),
  89             'creator': info.get('author'),
  90             'uploader_id': info.get('editor'),
  91             'duration': int_or_none(info.get('duration')),
  92             'upload_date': unified_strdate(info.get(
  93                 'formattedCreationDate'), day_first=False),
  94             'title': title,
  95             'categories': info.get('keywords'),
  96         }
  97
  98
  99 class WSJArticleIE(InfoExtractor):
 100     _VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
 101     _TEST = {
 102         'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
 103         'info_dict': {
 104             'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
 105             'ext': 'mp4',
 106             'upload_date': '20170221',
 107             'uploader_id': 'ralcaraz',
 108             'title': 'Bao Bao the Panda Leaves for China',
 109         }
 110     }
 111
 112     def _real_extract(self, url):
 113         article_id = self._match_id(url)
 114         webpage = self._download_webpage(url, article_id)
 115         video_id = self._search_regex(
 116             r'data-src=["\']([a-fA-F0-9-]{36})', webpage, 'video id')
 117         return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)