Upgrade yt_dlp and download script

This commit is contained in:
2025-05-02 16:11:08 -05:00
parent 3a2e8eeb08
commit d68d9ce4f9
1194 changed files with 60099 additions and 44436 deletions

View File

@@ -17,10 +17,11 @@ class CGTNIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1615295940,
'upload_date': '20210309',
'categories': ['Video'],
},
'params': {
'skip_download': True
}
'skip_download': True,
},
}, {
'url': 'https://news.cgtn.com/news/2021-06-06/China-Indonesia-vow-to-further-deepen-maritime-cooperation-10REvJCewCY/index.html',
'info_dict': {
@@ -29,15 +30,15 @@ class CGTNIE(InfoExtractor):
'title': 'China, Indonesia vow to further deepen maritime cooperation',
'thumbnail': r're:^https?://.*\.png$',
'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.',
'author': 'CGTN',
'category': 'China',
'creators': ['CGTN'],
'categories': ['China'],
'timestamp': 1622950200,
'upload_date': '20210606',
},
'params': {
'skip_download': False
}
}
'skip_download': False,
},
},
]
def _real_extract(self, url):
@@ -45,7 +46,12 @@ class CGTNIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
download_url = self._html_search_regex(r'data-video ="(?P<url>.+m3u8)"', webpage, 'download_url')
datetime_str = self._html_search_regex(r'<span class="date">\s*(.+?)\s*</span>', webpage, 'datetime_str', fatal=False)
datetime_str = self._html_search_regex(
r'<span class="date">\s*(.+?)\s*</span>', webpage, 'datetime_str', fatal=False)
category = self._html_search_regex(
r'<span class="section">\s*(.+?)\s*</span>', webpage, 'category', fatal=False)
author = self._search_regex(
r'<div class="news-author-name">\s*(.+?)\s*</div>', webpage, 'author', default=None)
return {
'id': video_id,
@@ -53,9 +59,7 @@ class CGTNIE(InfoExtractor):
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': self._extract_m3u8_formats(download_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'),
'category': self._html_search_regex(r'<span class="section">\s*(.+?)\s*</span>',
webpage, 'category', fatal=False),
'author': self._html_search_regex(r'<div class="news-author-name">\s*(.+?)\s*</div>',
webpage, 'author', default=None, fatal=False),
'categories': [category] if category else None,
'creators': [author] if author else None,
'timestamp': try_get(unified_timestamp(datetime_str), lambda x: x - 8 * 3600),
}