8516a2940cb38c7e030e504e6a29f88fcd3946a1
[youtube-dl] / youtube_dl / extractor / viddler.py
1 from __future__ import unicode_literals
2
3 from .common import InfoExtractor
4 from ..utils import (
5     float_or_none,
6     int_or_none,
7 )
8 from ..compat import (
9     compat_urllib_request
10 )
11
12
13 class ViddlerIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
15     _TESTS = [{
16         'url': 'http://www.viddler.com/v/43903784',
17         'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
18         'info_dict': {
19             'id': '43903784',
20             'ext': 'mp4',
21             'title': 'Video Made Easy',
22             'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
23             'uploader': 'viddler',
24             'timestamp': 1335371429,
25             'upload_date': '20120425',
26             'duration': 100.89,
27             'thumbnail': 're:^https?://.*\.jpg$',
28             'view_count': int,
29             'comment_count': int,
30             'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
31         }
32     }, {
33         'url': 'http://www.viddler.com/v/4d03aad9/',
34         'md5': 'faa71fbf70c0bee7ab93076fd007f4b0',
35         'info_dict': {
36             'id': '4d03aad9',
37             'ext': 'mp4',
38             'title': 'WALL-TO-GORTAT',
39             'upload_date': '20150126',
40             'uploader': 'deadspin',
41             'timestamp': 1422285291,
42             'view_count': int,
43             'comment_count': int,
44         }
45     }, {
46         'url': 'http://www.viddler.com/player/221ebbbd/0/',
47         'md5': '0defa2bd0ea613d14a6e9bd1db6be326',
48         'info_dict': {
49             'id': '221ebbbd',
50             'ext': 'mp4',
51             'title': 'LETeens-Grammar-snack-third-conditional',
52             'description': ' ',
53             'upload_date': '20140929',
54             'uploader': 'BCLETeens',
55             'timestamp': 1411997190,
56             'view_count': int,
57             'comment_count': int,
58         }
59     }]
60
61     def _real_extract(self, url):
62         video_id = self._match_id(url)
63
64         json_url = (
65             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
66             video_id)
67         headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
68         request = compat_urllib_request.Request(json_url, None, headers)
69         data = self._download_json(request, video_id)['video']
70
71         formats = []
72         for filed in data['files']:
73             if filed.get('status', 'ready') != 'ready':
74                 continue
75             format_id = filed.get('profile_id') or filed['profile_name']
76             f = {
77                 'format_id': format_id,
78                 'format_note': filed['profile_name'],
79                 'url': self._proto_relative_url(filed['url']),
80                 'width': int_or_none(filed.get('width')),
81                 'height': int_or_none(filed.get('height')),
82                 'filesize': int_or_none(filed.get('size')),
83                 'ext': filed.get('ext'),
84                 'source_preference': -1,
85             }
86             formats.append(f)
87
88             if filed.get('cdn_url'):
89                 f = f.copy()
90                 f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
91                 f['format_id'] = format_id + '-cdn'
92                 f['source_preference'] = 1
93                 formats.append(f)
94
95             if filed.get('html5_video_source'):
96                 f = f.copy()
97                 f['url'] = self._proto_relative_url(filed['html5_video_source'])
98                 f['format_id'] = format_id + '-html5'
99                 f['source_preference'] = 0
100                 formats.append(f)
101         self._sort_formats(formats)
102
103         categories = [
104             t.get('text') for t in data.get('tags', []) if 'text' in t]
105
106         return {
107             'id': video_id,
108             'title': data['title'],
109             'formats': formats,
110             'description': data.get('description'),
111             'timestamp': int_or_none(data.get('upload_time')),
112             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
113             'uploader': data.get('author'),
114             'duration': float_or_none(data.get('length')),
115             'view_count': int_or_none(data.get('view_count')),
116             'comment_count': int_or_none(data.get('comment_count')),
117             'categories': categories,
118         }