yt_dlp/extractor/wsj.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5     join_nonempty,
   6     unified_strdate,
   7 )
   8
   9
  10 class WSJIE(InfoExtractor):
  11     _VALID_URL = r'''(?x)
  12                         (?:
  13                             https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
  14                             https?://(?:www\.)?(?:wsj|barrons)\.com/video/(?:[^/]+/)+|
  15                             wsj:
  16                         )
  17                         (?P<id>[a-fA-F0-9-]{36})
  18                     '''
  19     IE_DESC = 'Wall Street Journal'
  20     _TESTS = [{
  21         'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
  22         'md5': 'e230a5bb249075e40793b655a54a02e4',
  23         'info_dict': {
  24             'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
  25             'ext': 'mp4',
  26             'upload_date': '20150202',
  27             'uploader_id': 'jdesai',
  28             'creator': 'jdesai',
  29             'categories': list,  # a long list
  30             'duration': 90,
  31             'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
  32         },
  33     }, {
  34         'url': 'http://www.wsj.com/video/can-alphabet-build-a-smarter-city/359DDAA8-9AC1-489C-82E6-0429C1E430E0.html',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.barrons.com/video/capitalism-deserves-more-respect-from-millennials/F301217E-6F46-43AE-B8D2-B7180D642EE9.html',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://www.wsj.com/video/series/a-brief-history-of/the-modern-cell-carrier-how-we-got-here/980E2187-401D-48A1-B82B-1486CEE06CB9',
  41         'only_matching': True,
  42     }]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         info = self._download_json(
  48             'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
  49             query={
  50                 'type': 'guid',
  51                 'count': 1,
  52                 'query': video_id,
  53                 'fields': ','.join((
  54                     'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
  55                     'description', 'name', 'duration', 'videoURL', 'titletag',
  56                     'formattedCreationDate', 'keywords', 'editor')),
  57             })['items'][0]
  58         title = info.get('name', info.get('titletag'))
  59
  60         formats = []
  61
  62         f4m_url = info.get('videoURL')
  63         if f4m_url:
  64             formats.extend(self._extract_f4m_formats(
  65                 f4m_url, video_id, f4m_id='hds', fatal=False))
  66
  67         m3u8_url = info.get('hls')
  68         if m3u8_url:
  69             formats.extend(self._extract_m3u8_formats(
  70                 info['hls'], video_id, ext='mp4',
  71                 entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
  72
  73         for v in info.get('videoMP4List', []):
  74             mp4_url = v.get('url')
  75             if not mp4_url:
  76                 continue
  77             tbr = int_or_none(v.get('bitrate'))
  78             formats.append({
  79                 'url': mp4_url,
  80                 'format_id': join_nonempty('http', tbr),
  81                 'tbr': tbr,
  82                 'width': int_or_none(v.get('width')),
  83                 'height': int_or_none(v.get('height')),
  84                 'fps': float_or_none(v.get('fps')),
  85             })
  86
  87         return {
  88             'id': video_id,
  89             'formats': formats,
  90             # Thumbnails are conveniently in the correct format already
  91             'thumbnails': info.get('thumbnailList'),
  92             'creator': info.get('author'),
  93             'uploader_id': info.get('editor'),
  94             'duration': int_or_none(info.get('duration')),
  95             'upload_date': unified_strdate(info.get(
  96                 'formattedCreationDate'), day_first=False),
  97             'title': title,
  98             'categories': info.get('keywords'),
  99         }
 100
 101
 102 class WSJArticleIE(InfoExtractor):
 103     _VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
 104     _TEST = {
 105         'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
 106         'info_dict': {
 107             'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
 108             'ext': 'mp4',
 109             'upload_date': '20170221',
 110             'uploader_id': 'ralcaraz',
 111             'title': 'Bao Bao the Panda Leaves for China',
 112         },
 113     }
 114
 115     def _real_extract(self, url):
 116         article_id = self._match_id(url)
 117         webpage = self._download_webpage(url, article_id)
 118         video_id = self._search_regex(
 119             r'(?:id=["\']video|video-|iframe\.html\?guid=|data-src=["\'])([a-fA-F0-9-]{36})',
 120             webpage, 'video id')
 121         return self.url_result(f'wsj:{video_id}', WSJIE.ie_key(), video_id)