From 4a7a5e41f7c653cf2b2f8b9bf10987291a19c074 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Jul 2016 14:51:44 +0100 Subject: [PATCH] [tvplay] improve extraction --- youtube_dl/extractor/tvplay.py | 123 +++++++++++++++++---------------- 1 file changed, 64 insertions(+), 59 deletions(-) diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index df70a6b23..918f8f8bc 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -8,43 +8,36 @@ from ..compat import compat_str from ..utils import ( parse_iso8601, qualities, + determine_ext, + update_url_query, + int_or_none, ) class TVPlayIE(InfoExtractor): IE_DESC = 'TV3Play and related services' _VALID_URL = r'''(?x)https?://(?:www\.)? - (?:tvplay\.lv/parraides| - tv3play\.lt/programos| - play\.tv3\.lt/programos| - tv3play\.ee/sisu| - tv3play\.se/program| - tv6play\.se/program| - tv8play\.se/program| - tv10play\.se/program| - tv3play\.no/programmer| - viasat4play\.no/programmer| - tv6play\.no/programmer| - tv3play\.dk/programmer| + (?:tvplay(?:\.skaties)?\.lv/parraides| + (?:tv3play|play\.tv3)\.lt/programos| + tv3play(?:\.tv3)?\.ee/sisu| + tv(?:3|6|8|10)play\.se/program| + (?:(?:tv3play|viasat4play|tv6play)\.no|tv3play\.dk)/programmer| play\.novatv\.bg/programi )/[^/]+/(?P\d+) ''' _TESTS = [ { 'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true', + 'md5': 'a1612fe0849455423ad8718fe049be21', 'info_dict': { 'id': '418113', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Kādi ir īri? - Viņas melo labāk', 'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.', 'duration': 25, 'timestamp': 1406097056, 'upload_date': '20140723', }, - 'params': { - # rtmp download - 'skip_download': True, - }, }, { 'url': 'http://play.tv3.lt/programos/moterys-meluoja-geriau/409229?autostart=true', @@ -82,7 +75,7 @@ class TVPlayIE(InfoExtractor): 'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true', 'info_dict': { 'id': '395385', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Husräddarna S02E07', 'description': 'md5:f210c6c89f42d4fc39faa551be813777', 'duration': 2574, @@ -90,7 +83,6 @@ class TVPlayIE(InfoExtractor): 'upload_date': '20140520', }, 'params': { - # rtmp download 'skip_download': True, }, }, @@ -98,7 +90,7 @@ class TVPlayIE(InfoExtractor): 'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true', 'info_dict': { 'id': '266636', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Den sista dokusåpan S01E08', 'description': 'md5:295be39c872520221b933830f660b110', 'duration': 1492, @@ -107,7 +99,6 @@ class TVPlayIE(InfoExtractor): 'age_limit': 18, }, 'params': { - # rtmp download 'skip_download': True, }, }, @@ -115,7 +106,7 @@ class TVPlayIE(InfoExtractor): 'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true', 'info_dict': { 'id': '282756', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Antikjakten S01E10', 'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8', 'duration': 2646, @@ -123,7 +114,6 @@ class TVPlayIE(InfoExtractor): 'upload_date': '20120925', }, 'params': { - # rtmp download 'skip_download': True, }, }, @@ -131,7 +121,7 @@ class TVPlayIE(InfoExtractor): 'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true', 'info_dict': { 'id': '230898', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Anna Anka søker assistent - Ep. 8', 'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474', 'duration': 2656, @@ -139,7 +129,6 @@ class TVPlayIE(InfoExtractor): 'upload_date': '20100628', }, 'params': { - # rtmp download 'skip_download': True, }, }, @@ -147,7 +136,7 @@ class TVPlayIE(InfoExtractor): 'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true', 'info_dict': { 'id': '21873', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Budbringerne program 10', 'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d', 'duration': 1297, @@ -155,7 +144,6 @@ class TVPlayIE(InfoExtractor): 'upload_date': '20090929', }, 'params': { - # rtmp download 'skip_download': True, }, }, @@ -163,7 +151,7 @@ class TVPlayIE(InfoExtractor): 'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true', 'info_dict': { 'id': '361883', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Hotelinspektør Alex Polizzi - Ep. 10', 'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81', 'duration': 2594, @@ -171,7 +159,6 @@ class TVPlayIE(InfoExtractor): 'upload_date': '20140224', }, 'params': { - # rtmp download 'skip_download': True, }, }, @@ -191,6 +178,14 @@ class TVPlayIE(InfoExtractor): 'skip_download': True, }, }, + { + 'url': 'http://tvplay.skaties.lv/parraides/vinas-melo-labak/418113?autostart=true', + 'only_matching': True, + }, + { + 'url': 'http://tv3play.tv3.ee/sisu/kodu-keset-linna/238551?autostart=true', + 'only_matching': True, + } ] def _real_extract(self, url): @@ -199,7 +194,9 @@ class TVPlayIE(InfoExtractor): video = self._download_json( 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON') - if video['is_geo_blocked']: + title = video['title'] + + if video.get('is_geo_blocked'): self.report_warning( 'This content might not be available in your country due to copyright reasons') @@ -208,42 +205,50 @@ class TVPlayIE(InfoExtractor): quality = qualities(['hls', 'medium', 'high']) formats = [] - for format_id, video_url in streams['streams'].items(): + for format_id, video_url in streams.get('streams', {}).items(): if not video_url or not isinstance(video_url, compat_str): continue - fmt = { - 'format_id': format_id, - 'preference': quality(format_id), - } - if video_url.startswith('rtmp'): - m = re.search(r'^(?Prtmp://[^/]+/(?P[^/]+))/(?P.+)$', video_url) - if not m: - continue - fmt.update({ - 'ext': 'flv', - 'url': m.group('url'), - 'app': m.group('app'), - 'play_path': m.group('playpath'), - }) - elif video_url.endswith('.f4m'): + ext = determine_ext(video_url) + if ext == 'f4m': formats.extend(self._extract_f4m_formats( - video_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id)) - continue + update_url_query(video_url, { + 'hdcore': '3.5.0', + 'plugin': 'aasp-3.5.0.151.81' + }), video_id, f4m_id='hds', fatal=False)) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) else: - fmt.update({ - 'url': video_url, - }) - formats.append(fmt) - + fmt = { + 'format_id': format_id, + 'quality': quality(format_id), + 'ext': ext, + } + if video_url.startswith('rtmp'): + m = re.search(r'^(?Prtmp://[^/]+/(?P[^/]+))/(?P.+)$', video_url) + if not m: + continue + fmt.update({ + 'ext': 'flv', + 'url': m.group('url'), + 'app': m.group('app'), + 'play_path': m.group('playpath'), + }) + else: + fmt.update({ + 'url': video_url, + }) + formats.append(fmt) self._sort_formats(formats) return { 'id': video_id, - 'title': video['title'], - 'description': video['description'], - 'duration': video['duration'], - 'timestamp': parse_iso8601(video['created_at']), - 'view_count': video['views']['total'], - 'age_limit': video.get('age_limit', 0), + 'title': title, + 'description': video.get('description'), + 'duration': int_or_none(video.get('duration')), + 'timestamp': parse_iso8601(video.get('created_at')), + 'view_count': int_or_none(video.get('views', {}).get('total')), + 'age_limit': int_or_none(video.get('age_limit', 0)), 'formats': formats, }