X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/87a0165ca7e39af4dacb7ec637063b2cd35ae40b..0b13e4356aba72763a8d75f0395070537889f61b:/youtube_dl/extractor/cctv.py diff --git a/youtube_dl/extractor/cctv.py b/youtube_dl/extractor/cctv.py index 72a72cb..c76f361 100644 --- a/youtube_dl/extractor/cctv.py +++ b/youtube_dl/extractor/cctv.py @@ -4,50 +4,188 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import float_or_none +from ..compat import compat_str +from ..utils import ( + float_or_none, + try_get, + unified_timestamp, +) class CCTVIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://(?:.+?\.)? - (?: - cctv\.(?:com|cn)| - cntv\.cn - )/ - (?: - video/[^/]+/(?P[0-9a-f]{32})| - \d{4}/\d{2}/\d{2}/(?PVID[0-9A-Za-z]+) - )''' + IE_DESC = '央视网' + _VALID_URL = r'https?://(?:(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)|(?:www\.)?ncpa-classic\.com)/(?:[^/]+/)*?(?P[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)' _TESTS = [{ - 'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml', - 'md5': '819c7b49fc3927d529fb4cd555621823', + # fo.addVariable("videoCenterId","id") + 'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml', + 'md5': 'd61ec00a493e09da810bf406a078f691', 'info_dict': { - 'id': '454368eb19ad44a1925bf1eb96140a61', + 'id': '5ecdbeab623f4973b40ff25f18b174e8', 'ext': 'mp4', - 'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1', - } + 'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕（快讯）', + 'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95', + 'duration': 98, + 'uploader': 'songjunjie', + 'timestamp': 1455279956, + 'upload_date': '20160212', + }, + }, { + # var guid = "id" + 'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml', + 'info_dict': { + 'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae', + 'ext': 'mp4', + 'title': '[赛车]“车王”舒马赫恢复情况成谜（快讯）', + 'description': '2月4日，蒙特泽莫罗透露了关于“车王”舒马赫恢复情况，但情况是否属实遭到了质疑。', + 'duration': 37, + 'uploader': 'shujun', + 'timestamp': 1454677291, + 'upload_date': '20160205', + }, + 'params': { + 'skip_download': True, + }, + }, { + # changePlayer('id') + 'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml', + 'info_dict': { + 'id': '4bb9bb4db7a6471ba85fdeda5af0381e', + 'ext': 'mp4', + 'title': 'NHnews008 ANNUAL POLITICAL SEASON', + 'description': 'Four Comprehensives', + 'duration': 60, + 'uploader': 'zhangyunlei', + 'timestamp': 1425385521, + 'upload_date': '20150303', + }, + 'params': { + 'skip_download': True, + }, + }, { + # loadvideo('id') + 'url': 'http://cctv.cntv.cn/lm/tvseries_russian/yilugesanghua/index.shtml', + 'info_dict': { + 'id': 'b15f009ff45c43968b9af583fc2e04b2', + 'ext': 'mp4', + 'title': 'Путь，усыпанный космеями Серия 1', + 'description': 'Путь, усыпанный космеями', + 'duration': 2645, + 'uploader': 'renxue', + 'timestamp': 1477479241, + 'upload_date': '20161026', + }, + 'params': { + 'skip_download': True, + }, + }, { + # var initMyAray = 'id' + 'url': 'http://www.ncpa-classic.com/2013/05/22/VIDE1369219508996867.shtml', + 'info_dict': { + 'id': 'a194cfa7f18c426b823d876668325946', + 'ext': 'mp4', + 'title': '小泽征尔音乐塾 音乐梦想无国界', + 'duration': 2173, + 'timestamp': 1369248264, + 'upload_date': '20130522', + }, + 'params': { + 'skip_download': True, + }, + }, { + # var ids = ["id"] + 'url': 'http://www.ncpa-classic.com/clt/more/416/index.shtml', + 'info_dict': { + 'id': 'a8606119a4884588a79d81c02abecc16', + 'ext': 'mp3', + 'title': '来自维也纳的新年贺礼', + 'description': 'md5:f13764ae8dd484e84dd4b39d5bcba2a7', + 'duration': 1578, + 'uploader': 'djy', + 'timestamp': 1482942419, + 'upload_date': '20161228', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Failed to download m3u8 information'], + }, { + 'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml', + 'only_matching': True, + }, { + 'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44', + 'only_matching': True, + }, { + 'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml', + 'only_matching': True, }, { 'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml', 'only_matching': True, }, { 'url': 'http://tv.cntv.cn/video/C39296/95cfac44cabd3ddc4a9438780a4e5c44', - 'only_matching': True + 'only_matching': True, }] def _real_extract(self, url): - video_id, display_id = re.match(self._VALID_URL, url).groups() - if not video_id: - webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})', - webpage, 'video_id') - api_data = self._download_json( - 'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id) - m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url']) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_id = self._search_regex( + [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)', + r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)', + r'changePlayer\s*\(\s*["\']([\da-fA-F]+)', + r'load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)', + r'var\s+initMyAray\s*=\s*["\']([\da-fA-F]+)', + r'var\s+ids\s*=\s*\[["\']([\da-fA-F]+)'], + webpage, 'video id') + + data = self._download_json( + 'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do', video_id, + query={ + 'pid': video_id, + 'url': url, + 'idl': 32, + 'idlr': 32, + 'modifyed': 'false', + }) + + title = data['title'] + + formats = [] + + video = data.get('video') + if isinstance(video, dict): + for quality, chapters_key in enumerate(('lowChapters', 'chapters')): + video_url = try_get( + video, lambda x: x[chapters_key][0]['url'], compat_str) + if video_url: + formats.append({ + 'url': video_url, + 'format_id': 'http', + 'quality': quality, + 'preference': -1, + }) + + hls_url = try_get(data, lambda x: x['hls_url'], compat_str) + if hls_url: + hls_url = re.sub(r'maxbr=\d+&?', '', hls_url) + formats.extend(self._extract_m3u8_formats( + hls_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + + self._sort_formats(formats) + + uploader = data.get('editer_name') + description = self._html_search_meta( + 'description', webpage, default=None) + timestamp = unified_timestamp(data.get('f_pgmtime')) + duration = float_or_none(try_get(video, lambda x: x['totalLength'])) return { 'id': video_id, - 'title': api_data['title'], - 'formats': self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False), - 'duration': float_or_none(api_data.get('video', {}).get('totalLength')), + 'title': title, + 'description': description, + 'uploader': uploader, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, }