Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/seeker.py

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