aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nowness.py
blob: b6c5ee6e417e12d35731e45e5755435867a3b67b (plain)
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
# coding: utf-8
from __future__ import unicode_literals

from .brightcove import (
    BrightcoveLegacyIE,
    BrightcoveNewIE,
)
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    ExtractorError,
    sanitized_Request,
)


class NownessBaseIE(InfoExtractor):
    def _extract_url_result(self, post):
        if post['type'] == 'video':
            for media in post['media']:
                if media['type'] == 'video':
                    video_id = media['content']
                    source = media['source']
                    if source == 'brightcove':
                        player_code = self._download_webpage(
                            'http://www.nowness.com/iframe?id=%s' % video_id, video_id,
                            note='Downloading player JavaScript',
                            errnote='Unable to download player JavaScript')
                        bc_url = BrightcoveLegacyIE._extract_brightcove_url(player_code)
                        if bc_url:
                            return self.url_result(bc_url, BrightcoveLegacyIE.ie_key())
                        bc_url = BrightcoveNewIE._extract_url(player_code)
                        if bc_url:
                            return self.url_result(bc_url, BrightcoveNewIE.ie_key())
                        raise ExtractorError('Could not find player definition')
                    elif source == 'vimeo':
                        return self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
                    elif source == 'youtube':
                        return self.url_result(video_id, 'Youtube')
                    elif source == 'cinematique':
                        # youtube-dl currently doesn't support cinematique
                        # return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique')
                        pass

    def _api_request(self, url, request_path):
        display_id = self._match_id(url)
        request = sanitized_Request(
            'http://api.nowness.com/api/' + request_path % display_id,
            headers={
                'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us',
            })
        return display_id, self._download_json(request, display_id)


class NownessIE(NownessBaseIE):
    IE_NAME = 'nowness'
    _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])'
    _TESTS = [{
        'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation',
        'md5': '068bc0202558c2e391924cb8cc470676',
        'info_dict': {
            'id': '2520295746001',
            'ext': 'mp4',
            'title': 'Candor: The Art of Gesticulation',
            'description': 'Candor: The Art of Gesticulation',
            'thumbnail': r're:^https?://.*\.jpg',
            'timestamp': 1446745676,
            'upload_date': '20151105',
            'uploader_id': '2385340575001',
        },
        'add_ie': ['BrightcoveNew'],
    }, {
        'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
        'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
        'info_dict': {
            'id': '3716354522001',
            'ext': 'mp4',
            'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
            'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
            'thumbnail': r're:^https?://.*\.jpg',
            'timestamp': 1407315371,
            'upload_date': '20140806',
            'uploader_id': '2385340575001',
        },
        'add_ie': ['BrightcoveNew'],
    }, {
        # vimeo
        'url': 'https://www.nowness.com/series/nowness-picks/jean-luc-godard-supercut',
        'md5': '9a5a6a8edf806407e411296ab6bc2a49',
        'info_dict': {
            'id': '130020913',
            'ext': 'mp4',
            'title': 'Bleu, Blanc, Rouge - A Godard Supercut',
            'description': 'md5:f0ea5f1857dffca02dbd37875d742cec',
            'thumbnail': r're:^https?://.*\.jpg',
            'upload_date': '20150607',
            'uploader': 'Cinema Sem Lei',
            'uploader_id': 'cinemasemlei',
        },
        'add_ie': ['Vimeo'],
    }]

    def _real_extract(self, url):
        _, post = self._api_request(url, 'post/getBySlug/%s')
        return self._extract_url_result(post)


class NownessPlaylistIE(NownessBaseIE):
    IE_NAME = 'nowness:playlist'
    _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
    _TEST = {
        'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
        'info_dict': {
            'id': '3286',
        },
        'playlist_mincount': 8,
    }

    def _real_extract(self, url):
        playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s')
        entries = [self._extract_url_result(item) for item in playlist['items']]
        return self.playlist_result(entries, playlist_id)


class NownessSeriesIE(NownessBaseIE):
    IE_NAME = 'nowness:series'
    _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
    _TEST = {
        'url': 'https://www.nowness.com/series/60-seconds',
        'info_dict': {
            'id': '60',
            'title': '60 Seconds',
            'description': 'One-minute wisdom in a new NOWNESS series',
        },
        'playlist_mincount': 4,
    }

    def _real_extract(self, url):
        display_id, series = self._api_request(url, 'series/getBySlug/%s')
        entries = [self._extract_url_result(post) for post in series['posts']]
        series_title = None
        series_description = None
        translations = series.get('translations', [])
        if translations:
            series_title = translations[0].get('title') or translations[0]['seoTitle']
            series_description = translations[0].get('seoDescription')
        return self.playlist_result(
            entries, compat_str(series['id']), series_title, series_description)