1 from __future__ import unicode_literals
7 from .common import InfoExtractor
11 compat_urllib_parse_urlparse
18 class NHLBaseInfoExtractor(InfoExtractor):
20 def _fix_json(json_string):
21 return json_string.replace('\\\'', '\'')
23 def _real_extract_video(self, video_id):
24 vid_parts = video_id.split(',')
25 if len(vid_parts) == 3:
26 video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0'))
27 json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
28 data = self._download_json(
29 json_url, video_id, transform_source=self._fix_json)
30 return self._extract_video(data[0])
32 def _extract_video(self, info):
34 self.report_extraction(video_id)
36 initial_video_url = info['publishPoint']
37 if info['formats'] == '1':
38 parsed_url = compat_urllib_parse_urlparse(initial_video_url)
39 filename, ext = os.path.splitext(parsed_url.path)
40 path = '%s_sd%s' % (filename, ext)
41 data = compat_urllib_parse.urlencode({
43 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
45 path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
46 path_doc = self._download_xml(
47 path_url, video_id, 'Downloading final video url')
48 video_url = path_doc.find('path').text
50 video_url = initial_video_url
52 join = compat_urlparse.urljoin
55 'title': info['name'],
57 'description': info['description'],
58 'duration': int(info['duration']),
59 'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
60 'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
64 class NHLIE(NHLBaseInfoExtractor):
66 _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)(?:id|hlg)=(?P<id>[-0-9a-zA-Z,]+)'
69 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
70 'md5': 'db704a4ea09e8d3988c85e36cc892d09',
74 'title': 'Quick clip: Weise 4-3 goal vs Flames',
75 'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
77 'upload_date': '20131006',
80 'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
81 'md5': 'd22e82bc592f52d37d24b03531ee9696',
83 'id': '2014020024-628-h',
85 'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
86 'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
88 'upload_date': '20141011',
91 'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
92 'md5': 'c78fc64ea01777e426cfc202b746c825',
96 'title': 'Classic Game In Six - April 22, 1979',
97 '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.',
99 'upload_date': '20100129'
102 'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
103 'only_matching': True,
105 'url': 'http://video.nhl.com/videocenter/?id=736722',
106 'only_matching': True,
108 'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en',
109 'md5': '076fcb88c255154aacbf0a7accc3f340',
111 'id': '2014020299-X-h',
113 'title': 'Penguins at Islanders / Game Highlights',
114 'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014',
116 'upload_date': '20141122',
120 def _real_extract(self, url):
121 video_id = self._match_id(url)
122 return self._real_extract_video(video_id)
125 class NHLNewsIE(NHLBaseInfoExtractor):
126 IE_NAME = 'nhl.com:news'
128 _VALID_URL = r'https?://(?:www\.)?nhl\.com/ice/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
131 'url': 'http://www.nhl.com/ice/news.htm?id=750727',
132 'md5': '4b3d1262e177687a3009937bd9ec0be8',
136 'title': 'Cal Clutterbuck has been fined $2,000',
137 'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
139 'upload_date': '20150128',
143 def _real_extract(self, url):
144 news_id = self._match_id(url)
145 webpage = self._download_webpage(url, news_id)
146 video_id = self._search_regex(
147 [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'"],
149 return self._real_extract_video(video_id)
152 class NHLVideocenterIE(NHLBaseInfoExtractor):
153 IE_NAME = 'nhl.com:videocenter'
154 IE_DESC = 'NHL videocenter category'
155 _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
157 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
160 'title': 'Highlights',
162 'playlist_count': 12,
165 def _real_extract(self, url):
166 mobj = re.match(self._VALID_URL, url)
167 team = mobj.group('team')
168 webpage = self._download_webpage(url, team)
169 cat_id = self._search_regex(
170 [r'var defaultCatId = "(.+?)";',
171 r'{statusIndex:0,index:0,.*?id:(.*?),'],
172 webpage, 'category id')
173 playlist_title = self._html_search_regex(
174 r'tab0"[^>]*?>(.*?)</td>',
175 webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
177 data = compat_urllib_parse.urlencode({
179 # This is the default value
184 path = '/videocenter/servlets/browse?' + data
185 request_url = compat_urlparse.urljoin(url, path)
186 response = self._download_webpage(request_url, playlist_title)
187 response = self._fix_json(response)
188 if not response.strip():
189 self._downloader.report_warning('Got an empty reponse, trying '
190 'adding the "newvideos" parameter')
191 response = self._download_webpage(request_url + '&newvideos=true',
193 response = self._fix_json(response)
194 videos = json.loads(response)
198 'title': playlist_title,
200 'entries': [self._extract_video(v) for v in videos],