yt_dlp/extractor/bostonglobe.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5 from ..utils import (
   6     extract_attributes,
   7 )
   8
   9
  10 class BostonGlobeIE(InfoExtractor):
  11     _VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?'
  12     _TESTS = [
  13         {
  14             'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html',
  15             'md5': '0a62181079c85c2d2b618c9a738aedaf',
  16             'info_dict': {
  17                 'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood',
  18                 'id': '5320421710001',
  19                 'ext': 'mp4',
  20                 'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.',
  21                 'timestamp': 1486877593,
  22                 'upload_date': '20170212',
  23                 'uploader_id': '245991542',
  24             },
  25         },
  26         {
  27             # Embedded youtube video; we hand it off to the Generic extractor.
  28             'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html',
  29             'md5': '582b40327089d5c0c949b3c54b13c24b',
  30             'info_dict': {
  31                 'title': "Who Is Matt Damon's Favorite Batman?",
  32                 'id': 'ZW1QCnlA6Qc',
  33                 'ext': 'mp4',
  34                 'upload_date': '20170217',
  35                 'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb',
  36                 'uploader': 'The Late Late Show with James Corden',
  37                 'uploader_id': 'TheLateLateShow',
  38             },
  39             'expected_warnings': ['404'],
  40         },
  41     ]
  42
  43     def _real_extract(self, url):
  44         page_id = self._match_id(url)
  45         webpage = self._download_webpage(url, page_id)
  46
  47         page_title = self._og_search_title(webpage, default=None)
  48
  49         # <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject">
  50         entries = []
  51         for video in re.findall(r'(?i)(<video[^>]+>)', webpage):
  52             attrs = extract_attributes(video)
  53
  54             video_id = attrs.get('data-brightcove-video-id')
  55             account_id = attrs.get('data-account')
  56             player_id = attrs.get('data-player')
  57             embed = attrs.get('data-embed')
  58
  59             if video_id and account_id and player_id and embed:
  60                 entries.append(
  61                     'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
  62                     % (account_id, player_id, embed, video_id))
  63
  64         if len(entries) == 0:
  65             return self.url_result(url, 'Generic')
  66         elif len(entries) == 1:
  67             return self.url_result(entries[0], 'BrightcoveNew')
  68         else:
  69             return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew')