yt_dlp/extractor/cgtn.py

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