X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/540fd68c40df72763aee5d75598675c45cfa9aba..fe979149c83b5a935f7d28baf75848a9137316fd:/youtube_dl/extractor/nhl.py?ds=sidebyside diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 279b183..b04d211 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -7,11 +7,16 @@ import os from .common import InfoExtractor from ..compat import ( compat_urlparse, - compat_urllib_parse, - compat_urllib_parse_urlparse + compat_urllib_parse_urlencode, + compat_urllib_parse_urlparse, + compat_str, ) from ..utils import ( unified_strdate, + determine_ext, + int_or_none, + parse_iso8601, + parse_duration, ) @@ -38,7 +43,7 @@ class NHLBaseInfoExtractor(InfoExtractor): 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({ + data = compat_urllib_parse_urlencode({ 'type': 'fvod', 'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:]) }) @@ -70,9 +75,9 @@ class NHLBaseInfoExtractor(InfoExtractor): return ret -class NHLIE(NHLBaseInfoExtractor): - IE_NAME = 'nhl.com' - _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/(?:console)?(?:\?(?:.*?[?&])?)(?:id|hlg)=(?P[-0-9a-zA-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', @@ -136,6 +141,9 @@ class NHLIE(NHLBaseInfoExtractor): 'params': { 'skip_download': True, # Requires rtmpdump } + }, { + 'url': 'http://video.nhl.com/videocenter/embed?playlist=836127', + 'only_matching': True, }] def _real_extract(self, url): @@ -146,9 +154,9 @@ class NHLIE(NHLBaseInfoExtractor): 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]+)' + _VALID_URL = r'https?://(?:.+?\.)?nhl\.com/(?:ice|club)/news\.html?(?:\?(?:.*?[?&])?)id=(?P[-0-9a-zA-Z]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.nhl.com/ice/news.htm?id=750727', 'md5': '4b3d1262e177687a3009937bd9ec0be8', 'info_dict': { @@ -159,19 +167,32 @@ class NHLNewsIE(NHLBaseInfoExtractor): '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'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 NHLVideocenterIE(NHLBaseInfoExtractor): - IE_NAME = 'nhl.com:videocenter' +class NHLVideocenterCategoryIE(NHLBaseInfoExtractor): + IE_NAME = 'nhl.com:videocenter:category' IE_DESC = 'NHL videocenter category' _VALID_URL = r'https?://video\.(?P[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P[0-9]+)(?![&?]id=).*?)?$' _TEST = { @@ -195,7 +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, @@ -207,7 +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) @@ -220,3 +241,86 @@ 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\.)?nhl\.com/([^/]+/)*c-(?P\d+)' + _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, + }, + }] + + def _real_extract(self, url): + tmp_id = self._match_id(url) + video_data = self._download_json( + 'https://nhl.bamcontent.com/nhl/id/v1/%s/details/web-v1.json' % 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': + formats.extend(self._extract_m3u8_formats( + playback_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=playback.get('name', 'hls'), fatal=False)) + 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, + }