yt_dlp/extractor/cgtn.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     try_get,
   4     unified_timestamp,
   5 )
   6
   7
   8 class CGTNIE(InfoExtractor):
   9     _VALID_URL = r'https?://news\.cgtn\.com/news/[0-9]{4}-[0-9]{2}-[0-9]{2}/[a-zA-Z0-9-]+-(?P<id>[a-zA-Z0-9-]+)/index\.html'
  10     _TESTS = [
  11         {
  12             'url': 'https://news.cgtn.com/news/2021-03-09/Up-and-Out-of-Poverty-Ep-1-A-solemn-promise-YuOUaOzGQU/index.html',
  13             'info_dict': {
  14                 'id': 'YuOUaOzGQU',
  15                 'ext': 'mp4',
  16                 'title': 'Up and Out of Poverty Ep. 1: A solemn promise',
  17                 'thumbnail': r're:^https?://.*\.jpg$',
  18                 'timestamp': 1615295940,
  19                 'upload_date': '20210309',
  20                 'categories': ['Video'],
  21             },
  22             'params': {
  23                 'skip_download': True
  24             }
  25         }, {
  26             'url': 'https://news.cgtn.com/news/2021-06-06/China-Indonesia-vow-to-further-deepen-maritime-cooperation-10REvJCewCY/index.html',
  27             'info_dict': {
  28                 'id': '10REvJCewCY',
  29                 'ext': 'mp4',
  30                 'title': 'China, Indonesia vow to further deepen maritime cooperation',
  31                 'thumbnail': r're:^https?://.*\.png$',
  32                 'description': 'China and Indonesia vowed to upgrade their cooperation into the maritime sector and also for political security, economy, and cultural and people-to-people exchanges.',
  33                 'creators': ['CGTN'],
  34                 'categories': ['China'],
  35                 'timestamp': 1622950200,
  36                 'upload_date': '20210606',
  37             },
  38             'params': {
  39                 'skip_download': False
  40             }
  41         }
  42     ]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46         webpage = self._download_webpage(url, video_id)
  47
  48         download_url = self._html_search_regex(r'data-video ="(?P<url>.+m3u8)"', webpage, 'download_url')
  49         datetime_str = self._html_search_regex(
  50             r'<span class="date">\s*(.+?)\s*</span>', webpage, 'datetime_str', fatal=False)
  51         category = self._html_search_regex(
  52             r'<span class="section">\s*(.+?)\s*</span>', webpage, 'category', fatal=False)
  53         author = self._search_regex(
  54             r'<div class="news-author-name">\s*(.+?)\s*</div>', webpage, 'author', default=None)
  55
  56         return {
  57             'id': video_id,
  58             'title': self._og_search_title(webpage),
  59             'description': self._og_search_description(webpage, default=None),
  60             'thumbnail': self._og_search_thumbnail(webpage),
  61             'formats': self._extract_m3u8_formats(download_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'),
  62             'categories': [category] if category else None,
  63             'creators': [author] if author else None,
  64             'timestamp': try_get(unified_timestamp(datetime_str), lambda x: x - 8 * 3600),
  65         }