[youtube] Fix extraction.
[youtube-dl] / youtube_dl / extractor / noovo.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .brightcove import BrightcoveNewIE
5 from .common import InfoExtractor
6 from ..compat import compat_str
7 from ..utils import (
8     int_or_none,
9     js_to_json,
10     smuggle_url,
11     try_get,
12 )
13
14
15 class NoovoIE(InfoExtractor):
16     _VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P<id>[^/]+/[^/?#&]+)'
17     _TESTS = [{
18         # clip
19         'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial',
20         'info_dict': {
21             'id': '5386045029001',
22             'ext': 'mp4',
23             'title': 'Chrysler Imperial',
24             'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056',
25             'timestamp': 1491399228,
26             'upload_date': '20170405',
27             'uploader_id': '618566855001',
28             'series': 'RPM+',
29         },
30         'params': {
31             'skip_download': True,
32         },
33     }, {
34         # episode
35         'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8',
36         'info_dict': {
37             'id': '5395865725001',
38             'title': 'Épisode 13 : Les retrouvailles',
39             'description': 'md5:888c3330f0c1b4476c5bc99a1c040473',
40             'ext': 'mp4',
41             'timestamp': 1492019320,
42             'upload_date': '20170412',
43             'uploader_id': '618566855001',
44             'series': "L'amour est dans le pré",
45             'season_number': 5,
46             'episode': 'Épisode 13',
47             'episode_number': 13,
48         },
49         'params': {
50             'skip_download': True,
51         },
52     }]
53     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s'
54
55     def _real_extract(self, url):
56         video_id = self._match_id(url)
57
58         webpage = self._download_webpage(url, video_id)
59
60         brightcove_id = self._search_regex(
61             r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
62
63         data = self._parse_json(
64             self._search_regex(
65                 r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data',
66                 default='{}'),
67             video_id, transform_source=js_to_json, fatal=False)
68
69         title = try_get(
70             data, lambda x: x['video']['nom'],
71             compat_str) or self._html_search_meta(
72             'dcterms.Title', webpage, 'title', fatal=True)
73
74         description = self._html_search_meta(
75             ('dcterms.Description', 'description'), webpage, 'description')
76
77         series = try_get(
78             data, lambda x: x['emission']['nom']) or self._search_regex(
79             r'<div[^>]+class="banner-card__subtitle h4"[^>]*>([^<]+)',
80             webpage, 'series', default=None)
81
82         season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {}
83         season = try_get(season_el, lambda x: x['nom'], compat_str)
84         season_number = int_or_none(try_get(season_el, lambda x: x['numero']))
85
86         episode_el = try_get(season_el, lambda x: x['episode'], dict) or {}
87         episode = try_get(episode_el, lambda x: x['nom'], compat_str)
88         episode_number = int_or_none(try_get(episode_el, lambda x: x['numero']))
89
90         return {
91             '_type': 'url_transparent',
92             'ie_key': BrightcoveNewIE.ie_key(),
93             'url': smuggle_url(
94                 self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
95                 {'geo_countries': ['CA']}),
96             'id': brightcove_id,
97             'title': title,
98             'description': description,
99             'series': series,
100             'season': season,
101             'season_number': season_number,
102             'episode': episode,
103             'episode_number': episode_number,
104         }