X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnhl.py;h=40746599880469f5c79110020f39d31f2a8cbff6;hb=39aa42ffbbe4df95ded3e70d4126808898a43f24;hp=2a84f676150afb9f93a52bef68557ea5ac7bd54f;hpb=ea2ee40357eb2c43f8968a4eeba47e1cf97667ba;p=youtube-dl diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 2a84f6761..407465998 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -2,11 +2,13 @@ from __future__ import unicode_literals import re import json +import os from .common import InfoExtractor from ..compat import ( compat_urlparse, compat_urllib_parse, + compat_urllib_parse_urlparse ) from ..utils import ( unified_strdate, @@ -18,15 +20,24 @@ class NHLBaseInfoExtractor(InfoExtractor): def _fix_json(json_string): return json_string.replace('\\\'', '\'') + def _real_extract_video(self, video_id): + json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id + data = self._download_json( + json_url, video_id, transform_source=self._fix_json) + return self._extract_video(data[0]) + def _extract_video(self, info): video_id = info['id'] self.report_extraction(video_id) initial_video_url = info['publishPoint'] if info['formats'] == '1': + parsed_url = compat_urllib_parse_urlparse(initial_video_url) + filename, ext = os.path.splitext(parsed_url.path) + path = '%s_sd%s' % (filename, ext) data = compat_urllib_parse.urlencode({ 'type': 'fvod', - 'path': initial_video_url.replace('.mp4', '_sd.mp4'), + 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:]) }) path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data path_doc = self._download_xml( @@ -49,7 +60,7 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): IE_NAME = 'nhl.com' - _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P[0-9a-z-]+)' + _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)id=(?P[-0-9a-zA-Z]+)' _TESTS = [{ 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', @@ -73,18 +84,55 @@ class NHLIE(NHLBaseInfoExtractor): 'duration': 0, 'upload_date': '20141011', }, + }, { + 'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802', + 'md5': 'c78fc64ea01777e426cfc202b746c825', + 'info_dict': { + 'id': '58665', + 'ext': 'flv', + 'title': 'Classic Game In Six - April 22, 1979', + '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.', + 'duration': 400, + 'upload_date': '20100129' + }, }, { 'url': 'http://video.flames.nhl.com/videocenter/console?id=630616', 'only_matching': True, + }, { + 'url': 'http://video.nhl.com/videocenter/?id=736722', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id - data = self._download_json( - json_url, video_id, transform_source=self._fix_json) - return self._extract_video(data[0]) + video_id = self._match_id(url) + return self._real_extract_video(video_id) + + +class NHLNewsIE(NHLBaseInfoExtractor): + IE_NAME = 'nhl.com:news' + IE_DESC = 'NHL news' + _VALID_URL = r'https?://(?:www\.)?nhl\.com/ice/news\.html?(?:\?(?:.*?[?&])?)id=(?P[-0-9a-zA-Z]+)' + + _TEST = { + 'url': 'http://www.nhl.com/ice/news.htm?id=750727', + 'md5': '4b3d1262e177687a3009937bd9ec0be8', + 'info_dict': { + 'id': '736722', + 'ext': 'mp4', + 'title': 'Cal Clutterbuck has been fined $2,000', + 'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6', + 'duration': 37, + 'upload_date': '20150128', + }, + } + + def _real_extract(self, url): + news_id = self._match_id(url) + webpage = self._download_webpage(url, news_id) + video_id = self._search_regex( + [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'"], + webpage, 'video id') + return self._real_extract_video(video_id) class NHLVideocenterIE(NHLBaseInfoExtractor):