]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cbc.py
Merge pull request #1 from e7appew/python3
[youtubedl] / youtube_dl / extractor / cbc.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_str
8 from ..utils import (
9 js_to_json,
10 smuggle_url,
11 try_get,
12 )
13
14
15 class CBCIE(InfoExtractor):
16 _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)'
17 _TESTS = [{
18 # with mediaId
19 'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs',
20 'md5': '97e24d09672fc4cf56256d6faa6c25bc',
21 'info_dict': {
22 'id': '2682904050',
23 'ext': 'mp4',
24 'title': 'Don Cherry – All-Stars',
25 'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guy’s got heart.',
26 'timestamp': 1454463000,
27 'upload_date': '20160203',
28 'uploader': 'CBCC-NEW',
29 },
30 'skip': 'Geo-restricted to Canada',
31 }, {
32 # with clipId, feed available via tpfeed.cbc.ca and feed.theplatform.com
33 'url': 'http://www.cbc.ca/22minutes/videos/22-minutes-update/22-minutes-update-episode-4',
34 'md5': '162adfa070274b144f4fdc3c3b8207db',
35 'info_dict': {
36 'id': '2414435309',
37 'ext': 'mp4',
38 'title': '22 Minutes Update: What Not To Wear Quebec',
39 'description': "This week's latest Canadian top political story is What Not To Wear Quebec.",
40 'upload_date': '20131025',
41 'uploader': 'CBCC-NEW',
42 'timestamp': 1382717907,
43 },
44 }, {
45 # with clipId, feed only available via tpfeed.cbc.ca
46 'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
47 'md5': '0274a90b51a9b4971fe005c63f592f12',
48 'info_dict': {
49 'id': '2487345465',
50 'ext': 'mp4',
51 'title': 'Robin Williams freestyles on 90 Minutes Live',
52 'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.',
53 'upload_date': '19780210',
54 'uploader': 'CBCC-NEW',
55 'timestamp': 255977160,
56 },
57 }, {
58 # multiple iframes
59 'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot',
60 'playlist': [{
61 'md5': '377572d0b49c4ce0c9ad77470e0b96b4',
62 'info_dict': {
63 'id': '2680832926',
64 'ext': 'mp4',
65 'title': 'An Eagle\'s-Eye View Off Burrard Bridge',
66 'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.',
67 'upload_date': '20160201',
68 'timestamp': 1454342820,
69 'uploader': 'CBCC-NEW',
70 },
71 }, {
72 'md5': '415a0e3f586113894174dfb31aa5bb1a',
73 'info_dict': {
74 'id': '2658915080',
75 'ext': 'mp4',
76 'title': 'Fly like an eagle!',
77 'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower',
78 'upload_date': '20150315',
79 'timestamp': 1426443984,
80 'uploader': 'CBCC-NEW',
81 },
82 }],
83 'skip': 'Geo-restricted to Canada',
84 }]
85
86 @classmethod
87 def suitable(cls, url):
88 return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url)
89
90 def _real_extract(self, url):
91 display_id = self._match_id(url)
92 webpage = self._download_webpage(url, display_id)
93 player_init = self._search_regex(
94 r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init',
95 default=None)
96 if player_init:
97 player_info = self._parse_json(player_init, display_id, js_to_json)
98 media_id = player_info.get('mediaId')
99 if not media_id:
100 clip_id = player_info['clipId']
101 feed = self._download_json(
102 'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
103 clip_id, fatal=False)
104 if feed:
105 media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
106 if not media_id:
107 media_id = self._download_json(
108 'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
109 clip_id)['entries'][0]['id'].split('/')[-1]
110 return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
111 else:
112 entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
113 return self.playlist_result(entries)
114
115
116 class CBCPlayerIE(InfoExtractor):
117 _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
118 _TESTS = [{
119 'url': 'http://www.cbc.ca/player/play/2683190193',
120 'md5': '64d25f841ddf4ddb28a235338af32e2c',
121 'info_dict': {
122 'id': '2683190193',
123 'ext': 'mp4',
124 'title': 'Gerry Runs a Sweat Shop',
125 'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0',
126 'timestamp': 1455071400,
127 'upload_date': '20160210',
128 'uploader': 'CBCC-NEW',
129 },
130 'skip': 'Geo-restricted to Canada',
131 }, {
132 # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
133 'url': 'http://www.cbc.ca/player/play/2657631896',
134 'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
135 'info_dict': {
136 'id': '2657631896',
137 'ext': 'mp3',
138 'title': 'CBC Montreal is organizing its first ever community hackathon!',
139 'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
140 'timestamp': 1425704400,
141 'upload_date': '20150307',
142 'uploader': 'CBCC-NEW',
143 },
144 }, {
145 # available only when we add `formats=MPEG4,FLV,MP3` to theplatform url
146 'url': 'http://www.cbc.ca/player/play/2164402062',
147 'md5': '17a61eb813539abea40618d6323a7f82',
148 'info_dict': {
149 'id': '2164402062',
150 'ext': 'flv',
151 'title': 'Cancer survivor four times over',
152 'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
153 'timestamp': 1320410746,
154 'upload_date': '20111104',
155 'uploader': 'CBCC-NEW',
156 },
157 }]
158
159 def _real_extract(self, url):
160 video_id = self._match_id(url)
161 return {
162 '_type': 'url_transparent',
163 'ie_key': 'ThePlatform',
164 'url': smuggle_url(
165 'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/%s?mbr=true&formats=MPEG4,FLV,MP3' % video_id, {
166 'force_smil_url': True
167 }),
168 'id': video_id,
169 }