about summary refs log tree commit diff
path: root/youtube_dl/extractor/americastestkitchen.py
blob: 35d3220c15b267e4b5a22db07ac232367aef5425 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
# coding: utf-8
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    int_or_none,
    try_get,
    unified_strdate,
    unified_timestamp,
)


class AmericasTestKitchenIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
        'md5': 'b861c3e365ac38ad319cfd509c30577f',
        'info_dict': {
            'id': '5b400b9ee338f922cb06450c',
            'title': 'Japanese Suppers',
            'ext': 'mp4',
            'description': 'md5:64e606bfee910627efc4b5f050de92b3',
            'thumbnail': r're:^https?://',
            'timestamp': 1523318400,
            'upload_date': '20180410',
            'release_date': '20180410',
            'series': "America's Test Kitchen",
            'season_number': 18,
            'episode': 'Japanese Suppers',
            'episode_number': 15,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above)
        'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner',
        'md5': '06451608c57651e985a498e69cec17e5',
        'info_dict': {
            'id': '5fbe8c61bda2010001c6763b',
            'title': 'Simple Chicken Dinner',
            'ext': 'mp4',
            'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
            'thumbnail': r're:^https?://',
            'timestamp': 1610755200,
            'upload_date': '20210116',
            'release_date': '20210116',
            'series': "America's Test Kitchen",
            'season_number': 21,
            'episode': 'Simple Chicken Dinner',
            'episode_number': 3,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
        'only_matching': True,
    }, {
        'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
        'only_matching': True,
    }, {
        'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        resource_type, video_id = re.match(self._VALID_URL, url).groups()
        is_episode = resource_type == 'episode'
        if is_episode:
            resource_type = 'episodes'

        resource = self._download_json(
            'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
        video = resource['video'] if is_episode else resource
        episode = resource if is_episode else resource.get('episode') or {}

        return {
            '_type': 'url_transparent',
            'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
            'ie_key': 'Zype',
            'description': clean_html(video.get('description')),
            'timestamp': unified_timestamp(video.get('publishDate')),
            'release_date': unified_strdate(video.get('publishDate')),
            'episode_number': int_or_none(episode.get('number')),
            'season_number': int_or_none(episode.get('season')),
            'series': try_get(episode, lambda x: x['show']['title']),
            'episode': episode.get('title'),
        }


class AmericasTestKitchenSeasonIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
    _TESTS = [{
        # ATK Season
        'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
        'info_dict': {
            'id': 'season-1',
            'title': 'Season 1',
        },
        'playlist_count': 13,
    }, {
        # Cooks Country Season
        'url': 'https://www.cookscountry.com/episodes/browse/season_12',
        'info_dict': {
            'id': 'season-12',
            'title': 'Season 12',
        },
        'playlist_count': 13,
    }, {
        # Multi-digit season
        'url': 'https://www.americastestkitchen.com/episodes/browse/season_20',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        show_name, season = re.match(self._VALID_URL, url).groups()

        slug = 'atk' if show_name == 'americastestkitchen' else 'cco'

        filters = [
            'search_season_list:Season %s' % season,
            'search_document_klass:episode',
            'search_show_slug:%s' % slug,
        ]

        season_search = self._download_json(
            'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_atk_season_desc_production',
            season, headers={
                'Origin': 'https://www.%s.com' % show_name,
                'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
                'X-Algolia-Application-Id': 'Y1FNZXUI30',
            }, query={
                'facetFilters': json.dumps(filters),
                'attributesToRetrieve': 'search_url',
                'attributesToHighlight': '',
                # ATK and CCO generally have less than 26 episodes per season
                'hitsPerPage': '100',
            })

        entries = [
            self.url_result(
                'https://www.%s.com%s' % (show_name, episode['search_url']),
                'AmericasTestKitchen',
                try_get(episode, lambda e: e['objectID'].split('_')[-1]))
            for episode in season_search['hits']
            if 'search_url' in episode and episode['search_url']
        ]

        return {
            '_type': 'playlist',
            'id': 'season-%s' % season,
            'title': 'Season %s' % season,
            'entries': sorted(entries, key=lambda e: e.get('id')),
        }