X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/15b1d10671b48df598afd70e17ba21e9e64ac766..4231113a7be907539052ce59df44e23c54d21d38:/youtube_dl/extractor/nhl.py diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index bdcf7e2..62ce800 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -2,14 +2,21 @@ 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_urlencode, + compat_urllib_parse_urlparse, + compat_str, ) from ..utils import ( unified_strdate, + determine_ext, + int_or_none, + parse_iso8601, + parse_duration, ) @@ -18,15 +25,27 @@ class NHLBaseInfoExtractor(InfoExtractor): def _fix_json(json_string): return json_string.replace('\\\'', '\'') + def _real_extract_video(self, video_id): + vid_parts = video_id.split(',') + if len(vid_parts) == 3: + video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0')) + 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': - data = compat_urllib_parse.urlencode({ + 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( @@ -36,7 +55,7 @@ class NHLBaseInfoExtractor(InfoExtractor): video_url = initial_video_url join = compat_urlparse.urljoin - return { + ret = { 'id': video_id, 'title': info['name'], 'url': video_url, @@ -45,11 +64,20 @@ class NHLBaseInfoExtractor(InfoExtractor): 'thumbnail': join(join(video_url, '/u/'), info['bigImage']), 'upload_date': unified_strdate(info['releaseDate'].split('.')[0]), } + if video_url.startswith('rtmp:'): + mobj = re.match(r'(?Prtmp://[^/]+/(?P[a-z0-9/]+))/(?Pmp4:.*)', video_url) + ret.update({ + 'tc_url': mobj.group('tc_url'), + 'play_path': mobj.group('play_path'), + 'app': mobj.group('app'), + 'no_resume': True, + }) + return ret -class NHLIE(NHLBaseInfoExtractor): - IE_NAME = 'nhl.com' - _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P[0-9a-z-]+)' +class NHLVideocenterIE(NHLBaseInfoExtractor): + IE_NAME = 'nhl.com:videocenter' + _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/(?:console|embed)?(?:\?(?:.*?[?&])?)(?:id|hlg|playlist)=(?P[-0-9a-zA-Z,]+)' _TESTS = [{ 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', @@ -73,24 +101,100 @@ 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, + }, { + 'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en', + 'md5': '076fcb88c255154aacbf0a7accc3f340', + 'info_dict': { + 'id': '2014020299-X-h', + 'ext': 'mp4', + 'title': 'Penguins at Islanders / Game Highlights', + 'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014', + 'duration': 268, + 'upload_date': '20141122', + } + }, { + 'url': 'http://video.oilers.nhl.com/videocenter/console?id=691469&catid=4', + 'info_dict': { + 'id': '691469', + 'ext': 'mp4', + 'title': 'RAW | Craig MacTavish Full Press Conference', + 'description': 'Oilers GM Craig MacTavish addresses the media at Rexall Place on Friday.', + 'upload_date': '20141205', + }, + 'params': { + 'skip_download': True, # Requires rtmpdump + } + }, { + 'url': 'http://video.nhl.com/videocenter/embed?playlist=836127', + '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 NHLVideocenterIE(NHLBaseInfoExtractor): - IE_NAME = 'nhl.com:videocenter' +class NHLNewsIE(NHLBaseInfoExtractor): + IE_NAME = 'nhl.com:news' + IE_DESC = 'NHL news' + _VALID_URL = r'https?://(?:.+?\.)?nhl\.com/(?:ice|club)/news\.html?(?:\?(?:.*?[?&])?)id=(?P[-0-9a-zA-Z]+)' + + _TESTS = [{ + 'url': 'http://www.nhl.com/ice/news.htm?id=750727', + 'md5': '4b3d1262e177687a3009937bd9ec0be8', + 'info_dict': { + 'id': '736722', + 'ext': 'mp4', + 'title': 'Cal Clutterbuck has been fined $2,000', + 'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6', + 'duration': 37, + 'upload_date': '20150128', + }, + }, { + # iframe embed + 'url': 'http://sabres.nhl.com/club/news.htm?id=780189', + 'md5': '9f663d1c006c90ac9fb82777d4294e12', + 'info_dict': { + 'id': '836127', + 'ext': 'mp4', + 'title': 'Morning Skate: OTT vs. BUF (9/23/15)', + 'description': "Brian Duff chats with Tyler Ennis prior to Buffalo's first preseason home game.", + 'duration': 93, + 'upload_date': '20150923', + }, + }] + + def _real_extract(self, url): + news_id = self._match_id(url) + webpage = self._download_webpage(url, news_id) + video_id = self._search_regex( + [r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'", + r']+src=["\']https?://video.*?\.nhl\.com/videocenter/embed\?.*\bplaylist=(\d+)'], + webpage, 'video id') + return self._real_extract_video(video_id) + + +class NHLVideocenterCategoryIE(NHLBaseInfoExtractor): + IE_NAME = 'nhl.com:videocenter:category' IE_DESC = 'NHL videocenter category' - _VALID_URL = r'https?://video\.(?P[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P[0-9]+)(?![&?]id=).*?)?$' + _VALID_URL = r'https?://video\.(?P[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P[0-9]+)(?![&?]id=).*?)?$' _TEST = { 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999', 'info_dict': { @@ -112,7 +216,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): r'tab0"[^>]*?>(.*?)', webpage, 'playlist title', flags=re.DOTALL).lower().capitalize() - data = compat_urllib_parse.urlencode({ + data = compat_urllib_parse_urlencode({ 'cid': cat_id, # This is the default value 'count': 12, @@ -124,7 +228,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): response = self._download_webpage(request_url, playlist_title) response = self._fix_json(response) if not response.strip(): - self._downloader.report_warning('Got an empty reponse, trying ' + self._downloader.report_warning('Got an empty response, trying ' 'adding the "newvideos" parameter') response = self._download_webpage(request_url + '&newvideos=true', playlist_title) @@ -137,3 +241,111 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): 'id': cat_id, 'entries': [self._extract_video(v) for v in videos], } + + +class NHLIE(InfoExtractor): + IE_NAME = 'nhl.com' + _VALID_URL = r'https?://(?:www\.)?(?Pnhl|wch2016)\.com/(?:[^/]+/)*c-(?P\d+)' + _SITES_MAP = { + 'nhl': 'nhl', + 'wch2016': 'wch', + } + _TESTS = [{ + # type=video + 'url': 'https://www.nhl.com/video/anisimov-cleans-up-mess/t-277752844/c-43663503', + 'md5': '0f7b9a8f986fb4b4eeeece9a56416eaf', + 'info_dict': { + 'id': '43663503', + 'ext': 'mp4', + 'title': 'Anisimov cleans up mess', + 'description': 'md5:a02354acdfe900e940ce40706939ca63', + 'timestamp': 1461288600, + 'upload_date': '20160422', + }, + }, { + # type=article + 'url': 'https://www.nhl.com/news/dennis-wideman-suspended/c-278258934', + 'md5': '1f39f4ea74c1394dea110699a25b366c', + 'info_dict': { + 'id': '40784403', + 'ext': 'mp4', + 'title': 'Wideman suspended by NHL', + 'description': 'Flames defenseman Dennis Wideman was banned 20 games for violation of Rule 40 (Physical Abuse of Officials)', + 'upload_date': '20160204', + 'timestamp': 1454544904, + }, + }, { + # Some m3u8 URLs are invalid (https://github.com/rg3/youtube-dl/issues/10713) + 'url': 'https://www.nhl.com/predators/video/poile-laviolette-on-subban-trade/t-277437416/c-44315003', + 'md5': '50b2bb47f405121484dda3ccbea25459', + 'info_dict': { + 'id': '44315003', + 'ext': 'mp4', + 'title': 'Poile, Laviolette on Subban trade', + 'description': 'General manager David Poile and head coach Peter Laviolette share their thoughts on acquiring P.K. Subban from Montreal (06/29/16)', + 'timestamp': 1467242866, + 'upload_date': '20160629', + }, + }, { + 'url': 'https://www.wch2016.com/video/caneur-best-of-game-2-micd-up/t-281230378/c-44983703', + 'only_matching': True, + }, { + 'url': 'https://www.wch2016.com/news/3-stars-team-europe-vs-team-canada/c-282195068', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + tmp_id, site = mobj.group('id'), mobj.group('site') + video_data = self._download_json( + 'https://nhl.bamcontent.com/%s/id/v1/%s/details/web-v1.json' + % (self._SITES_MAP[site], tmp_id), tmp_id) + if video_data.get('type') == 'article': + video_data = video_data['media'] + + video_id = compat_str(video_data['id']) + title = video_data['title'] + + formats = [] + for playback in video_data.get('playbacks', []): + playback_url = playback.get('url') + if not playback_url: + continue + ext = determine_ext(playback_url) + if ext == 'm3u8': + m3u8_formats = self._extract_m3u8_formats( + playback_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=playback.get('name', 'hls'), fatal=False) + self._check_formats(m3u8_formats, video_id) + formats.extend(m3u8_formats) + else: + height = int_or_none(playback.get('height')) + formats.append({ + 'format_id': playback.get('name', 'http' + ('-%dp' % height if height else '')), + 'url': playback_url, + 'width': int_or_none(playback.get('width')), + 'height': height, + }) + self._sort_formats(formats, ('preference', 'width', 'height', 'tbr', 'format_id')) + + thumbnails = [] + for thumbnail_id, thumbnail_data in video_data.get('image', {}).get('cuts', {}).items(): + thumbnail_url = thumbnail_data.get('src') + if not thumbnail_url: + continue + thumbnails.append({ + 'id': thumbnail_id, + 'url': thumbnail_url, + 'width': int_or_none(thumbnail_data.get('width')), + 'height': int_or_none(thumbnail_data.get('height')), + }) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'timestamp': parse_iso8601(video_data.get('date')), + 'duration': parse_duration(video_data.get('duration')), + 'thumbnails': thumbnails, + 'formats': formats, + }