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|barrons)\.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         'url': 'http://www.barrons.com/video/capitalism-deserves-more-respect-from-millennials/F301217E-6F46-43AE-B8D2-B7180D642EE9.html',
  40         'only_matching': True,
  41     }, {
  42         'url': 'https://www.wsj.com/video/series/a-brief-history-of/the-modern-cell-carrier-how-we-got-here/980E2187-401D-48A1-B82B-1486CEE06CB9',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48
  49         info = self._download_json(
  50             'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
  51             query={
  52                 'type': 'guid',
  53                 'count': 1,
  54                 'query': video_id,
  55                 'fields': ','.join((
  56                     'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
  57                     'description', 'name', 'duration', 'videoURL', 'titletag',
  58                     'formattedCreationDate', 'keywords', 'editor')),
  59             })['items'][0]
  60         title = info.get('name', info.get('titletag'))
  61
  62         formats = []
  63
  64         f4m_url = info.get('videoURL')
  65         if f4m_url:
  66             formats.extend(self._extract_f4m_formats(
  67                 f4m_url, video_id, f4m_id='hds', fatal=False))
  68
  69         m3u8_url = info.get('hls')
  70         if m3u8_url:
  71             formats.extend(self._extract_m3u8_formats(
  72                 info['hls'], video_id, ext='mp4',
  73                 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  74
  75         for v in info.get('videoMP4List', []):
  76             mp4_url = v.get('url')
  77             if not mp4_url:
  78                 continue
  79             tbr = int_or_none(v.get('bitrate'))
  80             formats.append({
  81                 'url': mp4_url,
  82                 'format_id': 'http' + ('-%d' % tbr if tbr else ''),
  83                 'tbr': tbr,
  84                 'width': int_or_none(v.get('width')),
  85                 'height': int_or_none(v.get('height')),
  86                 'fps': float_or_none(v.get('fps')),
  87             })
  88         self._sort_formats(formats)
  89
  90         return {
  91             'id': video_id,
  92             'formats': formats,
  93             # Thumbnails are conveniently in the correct format already
  94             'thumbnails': info.get('thumbnailList'),
  95             'creator': info.get('author'),
  96             'uploader_id': info.get('editor'),
  97             'duration': int_or_none(info.get('duration')),
  98             'upload_date': unified_strdate(info.get(
  99                 'formattedCreationDate'), day_first=False),
 100             'title': title,
 101             'categories': info.get('keywords'),
 102         }
 103
 104
 105 class WSJArticleIE(InfoExtractor):
 106     _VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
 107     _TEST = {
 108         'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
 109         'info_dict': {
 110             'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
 111             'ext': 'mp4',
 112             'upload_date': '20170221',
 113             'uploader_id': 'ralcaraz',
 114             'title': 'Bao Bao the Panda Leaves for China',
 115         }
 116     }
 117
 118     def _real_extract(self, url):
 119         article_id = self._match_id(url)
 120         webpage = self._download_webpage(url, article_id)
 121         video_id = self._search_regex(
 122             r'data-src=["\']([a-fA-F0-9-]{36})', webpage, 'video id')
 123         return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)