yt_dlp/extractor/newspicks.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5
   6
   7 class NewsPicksIE(InfoExtractor):
   8     _VALID_URL = r'https?://newspicks\.com/movie-series/(?P<channel_id>\d+)\?movieId=(?P<id>\d+)'
   9
  10     _TESTS = [{
  11         'url': 'https://newspicks.com/movie-series/11?movieId=1813',
  12         'info_dict': {
  13             'id': '1813',
  14             'title': '日本の課題を破壊せよ【ゲスト：成田悠輔】',
  15             'description': 'md5:09397aad46d6ded6487ff13f138acadf',
  16             'channel': 'HORIE ONE',
  17             'channel_id': '11',
  18             'release_date': '20220117',
  19             'thumbnail': r're:https://.+jpg',
  20             'ext': 'mp4',
  21         },
  22     }]
  23
  24     def _real_extract(self, url):
  25         video_id, channel_id = self._match_valid_url(url).group('id', 'channel_id')
  26         webpage = self._download_webpage(url, video_id)
  27         entries = self._parse_html5_media_entries(
  28             url, webpage.replace('movie-for-pc', 'movie'), video_id, 'hls')
  29         if not entries:
  30             raise ExtractorError('No HTML5 media elements found')
  31         info = entries[0]
  32
  33         title = self._html_search_meta('og:title', webpage, fatal=False)
  34         description = self._html_search_meta(
  35             ('og:description', 'twitter:title'), webpage, fatal=False)
  36         channel = self._html_search_regex(
  37             r'value="11".+?<div\s+class="title">(.+?)</div', webpage, 'channel name', fatal=False)
  38         if not title or not channel:
  39             title, channel = re.split(r'\s*|\s*', self._html_extract_title(webpage))
  40
  41         release_date = self._search_regex(
  42             r'<span\s+class="on-air-date">\s*(\d+)年(\d+)月(\d+)日\s*</span>',
  43             webpage, 'release date', fatal=False, group=(1, 2, 3))
  44
  45         info.update({
  46             'id': video_id,
  47             'title': title,
  48             'description': description,
  49             'channel': channel,
  50             'channel_id': channel_id,
  51             'release_date': ('%04d%02d%02d' % tuple(map(int, release_date))) if release_date else None,
  52         })
  53         return info