0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-29 01:51:06 +00:00
yt-dlp/yt_dlp/extractor/cgtn.py
sepro add96eb9f8
[cleanup] Add more ruff rules ()
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

65 lines
2.9 KiB
Python

from .common import InfoExtractor
from ..utils import (
try_get,
unified_timestamp,
)
class CGTNIE(InfoExtractor):
_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'
_TESTS = [
{
'url': 'https://news.cgtn.com/news/2021-03-09/Up-and-Out-of-Poverty-Ep-1-A-solemn-promise-YuOUaOzGQU/index.html',
'info_dict': {
'id': 'YuOUaOzGQU',
'ext': 'mp4',
'title': 'Up and Out of Poverty Ep. 1: A solemn promise',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1615295940,
'upload_date': '20210309',
'categories': ['Video'],
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://news.cgtn.com/news/2021-06-06/China-Indonesia-vow-to-further-deepen-maritime-cooperation-10REvJCewCY/index.html',
'info_dict': {
'id': '10REvJCewCY',
'ext': 'mp4',
'title': 'China, Indonesia vow to further deepen maritime cooperation',
'thumbnail': r're:^https?://.*\.png$',
'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.',
'creators': ['CGTN'],
'categories': ['China'],
'timestamp': 1622950200,
'upload_date': '20210606',
},
'params': {
'skip_download': False,
},
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
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)
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,
'title': self._og_search_title(webpage),
'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'),
'categories': [category] if category else None,
'creators': [author] if author else None,
'timestamp': try_get(unified_timestamp(datetime_str), lambda x: x - 8 * 3600),
}