yt_dlp/extractor/seeker.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     get_element_by_class,
   6     strip_or_none,
   7 )
   8
   9
  10 class SeekerIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P<display_id>.*)-(?P<article_id>\d+)\.html'
  12     _TESTS = [{
  13         'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html',
  14         'md5': '897d44bbe0d8986a2ead96de565a92db',
  15         'info_dict': {
  16             'id': 'Elrn3gnY',
  17             'ext': 'mp4',
  18             'title': 'Should Trump Be Required To Release His Tax Returns?',
  19             'description': 'md5:41efa8cfa8d627841045eec7b018eb45',
  20             'timestamp': 1490090165,
  21             'upload_date': '20170321',
  22         }
  23     }, {
  24         'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html',
  25         'playlist': [
  26             {
  27                 'md5': '0497b9f20495174be73ae136949707d2',
  28                 'info_dict': {
  29                     'id': 'FihYQ8AE',
  30                     'ext': 'mp4',
  31                     'title': 'The Pros & Cons Of Zoos',
  32                     'description': 'md5:d88f99a8ea8e7d25e6ff77f271b1271c',
  33                     'timestamp': 1490039133,
  34                     'upload_date': '20170320',
  35                 },
  36             }
  37         ],
  38         'info_dict': {
  39             'id': '1834116536',
  40             'title': 'After Gorilla Killing, Changes Ahead for Zoos',
  41             'description': 'The largest association of zoos and others are hoping to learn from recent incidents that led to the shooting deaths of a gorilla and two lions.',
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         display_id, article_id = self._match_valid_url(url).groups()
  47         webpage = self._download_webpage(url, display_id)
  48         entries = []
  49         for jwp_id in re.findall(r'data-video-id="([a-zA-Z0-9]{8})"', webpage):
  50             entries.append(self.url_result(
  51                 'jwplatform:' + jwp_id, 'JWPlatform', jwp_id))
  52         return self.playlist_result(
  53             entries, article_id,
  54             self._og_search_title(webpage),
  55             strip_or_none(get_element_by_class('subtitle__text', webpage)) or self._og_search_description(webpage))