[pokemon] Add new extractor(closes #10093)
[youtube-dl] / youtube_dl / extractor / pokemon.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     extract_attributes,
9     int_or_none,
10 )
11
12
13 class PokemonIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/pokemon-episodes/(?P<display_id>[^/?#]+))'
15     _TESTS = [{
16         'url': 'http://www.pokemon.com/us/pokemon-episodes/19_01-from-a-to-z/?play=true',
17         'md5': '9fb209ae3a569aac25de0f5afc4ee08f',
18         'info_dict': {
19             'id': 'd0436c00c3ce4071ac6cee8130ac54a1',
20             'ext': 'mp4',
21             'title': 'From A to Z!',
22             'description': 'Bonnie makes a new friend, Ash runs into an old friend, and a terrifying premonition begins to unfold!',
23             'timestamp': 1460478136,
24             'upload_date': '20160412',
25         },
26         'add_id': ['LimelightMedia']
27     }, {
28         'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
29         'only_matching': True,
30     }]
31
32     def _real_extract(self, url):
33         video_id, display_id = re.match(self._VALID_URL, url).groups()
34         webpage = self._download_webpage(url, video_id or display_id)
35         video_data = extract_attributes(self._search_regex(
36             r'(<[^>]+data-video-id="%s"[^>]*>)' % (video_id if video_id else '[a-z0-9]{32}'),
37             webpage, 'video data element'))
38         video_id = video_data['data-video-id']
39         title = video_data['data-video-title']
40         return {
41             '_type': 'url_transparent',
42             'id': video_id,
43             'url': 'limelight:media:%s' % video_id,
44             'title': title,
45             'description': video_data.get('data-video-summary'),
46             'thumbnail': video_data.get('data-video-poster'),
47             'series': 'Pokémon',
48             'season_number': int_or_none(video_data.get('data-video-season')),
49             'episode': title,
50             'episode_number': int_or_none(video_data.get('data-video-episode')),
51             'ie_key': 'LimelightMedia',
52         }