[Lecture2Go] Add new extractor
[youtube-dl] / youtube_dl / extractor / nhl.py
1 from __future__ import unicode_literals
2
3 import re
4 import json
5 import os
6
7 from .common import InfoExtractor
8 from ..compat import (
9     compat_urlparse,
10     compat_urllib_parse,
11     compat_urllib_parse_urlparse
12 )
13 from ..utils import (
14     unified_strdate,
15 )
16
17
18 class NHLBaseInfoExtractor(InfoExtractor):
19     @staticmethod
20     def _fix_json(json_string):
21         return json_string.replace('\\\'', '\'')
22
23     def _real_extract_video(self, video_id):
24         json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
25         data = self._download_json(
26             json_url, video_id, transform_source=self._fix_json)
27         return self._extract_video(data[0])
28
29     def _extract_video(self, info):
30         video_id = info['id']
31         self.report_extraction(video_id)
32
33         initial_video_url = info['publishPoint']
34         if info['formats'] == '1':
35             parsed_url = compat_urllib_parse_urlparse(initial_video_url)
36             filename, ext = os.path.splitext(parsed_url.path)
37             path = '%s_sd%s' % (filename, ext)
38             data = compat_urllib_parse.urlencode({
39                 'type': 'fvod',
40                 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
41             })
42             path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
43             path_doc = self._download_xml(
44                 path_url, video_id, 'Downloading final video url')
45             video_url = path_doc.find('path').text
46         else:
47             video_url = initial_video_url
48
49         join = compat_urlparse.urljoin
50         return {
51             'id': video_id,
52             'title': info['name'],
53             'url': video_url,
54             'description': info['description'],
55             'duration': int(info['duration']),
56             'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
57             'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
58         }
59
60
61 class NHLIE(NHLBaseInfoExtractor):
62     IE_NAME = 'nhl.com'
63     _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
64
65     _TESTS = [{
66         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
67         'md5': 'db704a4ea09e8d3988c85e36cc892d09',
68         'info_dict': {
69             'id': '453614',
70             'ext': 'mp4',
71             'title': 'Quick clip: Weise 4-3 goal vs Flames',
72             'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
73             'duration': 18,
74             'upload_date': '20131006',
75         },
76     }, {
77         'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
78         'md5': 'd22e82bc592f52d37d24b03531ee9696',
79         'info_dict': {
80             'id': '2014020024-628-h',
81             'ext': 'mp4',
82             'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
83             'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
84             'duration': 0,
85             'upload_date': '20141011',
86         },
87     }, {
88         'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
89         'md5': 'c78fc64ea01777e426cfc202b746c825',
90         'info_dict': {
91             'id': '58665',
92             'ext': 'flv',
93             'title': 'Classic Game In Six - April 22, 1979',
94             'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
95             'duration': 400,
96             'upload_date': '20100129'
97         },
98     }, {
99         'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
100         'only_matching': True,
101     }, {
102         'url': 'http://video.nhl.com/videocenter/?id=736722',
103         'only_matching': True,
104     }]
105
106     def _real_extract(self, url):
107         video_id = self._match_id(url)
108         return self._real_extract_video(video_id)
109
110
111 class NHLNewsIE(NHLBaseInfoExtractor):
112     IE_NAME = 'nhl.com:news'
113     IE_DESC = 'NHL news'
114     _VALID_URL = r'https?://(?:www\.)?nhl\.com/ice/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
115
116     _TEST = {
117         'url': 'http://www.nhl.com/ice/news.htm?id=750727',
118         'md5': '4b3d1262e177687a3009937bd9ec0be8',
119         'info_dict': {
120             'id': '736722',
121             'ext': 'mp4',
122             'title': 'Cal Clutterbuck has been fined $2,000',
123             'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
124             'duration': 37,
125             'upload_date': '20150128',
126         },
127     }
128
129     def _real_extract(self, url):
130         news_id = self._match_id(url)
131         webpage = self._download_webpage(url, news_id)
132         video_id = self._search_regex(
133             [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'"],
134             webpage, 'video id')
135         return self._real_extract_video(video_id)
136
137
138 class NHLVideocenterIE(NHLBaseInfoExtractor):
139     IE_NAME = 'nhl.com:videocenter'
140     IE_DESC = 'NHL videocenter category'
141     _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
142     _TEST = {
143         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
144         'info_dict': {
145             'id': '999',
146             'title': 'Highlights',
147         },
148         'playlist_count': 12,
149     }
150
151     def _real_extract(self, url):
152         mobj = re.match(self._VALID_URL, url)
153         team = mobj.group('team')
154         webpage = self._download_webpage(url, team)
155         cat_id = self._search_regex(
156             [r'var defaultCatId = "(.+?)";',
157              r'{statusIndex:0,index:0,.*?id:(.*?),'],
158             webpage, 'category id')
159         playlist_title = self._html_search_regex(
160             r'tab0"[^>]*?>(.*?)</td>',
161             webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
162
163         data = compat_urllib_parse.urlencode({
164             'cid': cat_id,
165             # This is the default value
166             'count': 12,
167             'ptrs': 3,
168             'format': 'json',
169         })
170         path = '/videocenter/servlets/browse?' + data
171         request_url = compat_urlparse.urljoin(url, path)
172         response = self._download_webpage(request_url, playlist_title)
173         response = self._fix_json(response)
174         if not response.strip():
175             self._downloader.report_warning('Got an empty reponse, trying '
176                                             'adding the "newvideos" parameter')
177             response = self._download_webpage(request_url + '&newvideos=true',
178                                               playlist_title)
179             response = self._fix_json(response)
180         videos = json.loads(response)
181
182         return {
183             '_type': 'playlist',
184             'title': playlist_title,
185             'id': cat_id,
186             'entries': [self._extract_video(v) for v in videos],
187         }