From 8cfb5bbf92bec632ae3bc08c3d87c0eb7c199b75 Mon Sep 17 00:00:00 2001 From: pulpe Date: Sat, 1 Mar 2014 11:47:52 +0100 Subject: [PATCH 1/4] [CeskaTelevize] Add initial support for ceskatelevize.cz --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ceskatelevize.py | 106 ++++++++++++++++++++++++++ 2 files changed, 107 insertions(+) create mode 100644 youtube_dl/extractor/ceskatelevize.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2f8fcb8c9..a4f6fbffd 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -26,6 +26,7 @@ from .c56 import C56IE from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE +from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE from .cinemassacre import CinemassacreIE diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py new file mode 100644 index 000000000..92ae4ffcb --- /dev/null +++ b/youtube_dl/extractor/ceskatelevize.py @@ -0,0 +1,106 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re +import json +from urllib import unquote + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, + compat_urllib_parse, + compat_urllib_parse_urlparse +) + + +class CeskaTelevizeIE(InfoExtractor): + _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P[^?#]+)' + + _TESTS = [{ + 'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka', + 'info_dict': { + 'id': '213512120230004', + 'ext': 'flv', + 'title': 'První republika: Španělská chřipka', + 'duration': 3107.4, + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }, { + 'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt', + 'info_dict': { + 'id': '20138143440', + 'ext': 'flv', + 'title': 'Tsatsiki, maminka a policajt', + 'duration': 6754.1, + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }] + + def _real_extract(self, url): + url = url.replace('/porady/', '/ivysilani/').replace('/video/', '') + + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type') + episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id') + + data = { + 'playlist[0][type]': typ, + 'playlist[0][id]': episode_id, + 'requestUrl': compat_urllib_parse_urlparse(url).path, + 'requestSource': 'iVysilani', + } + + req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url', + data=compat_urllib_parse.urlencode(data)) + + req.add_header('Content-type', 'application/x-www-form-urlencoded') + req.add_header('x-addr', '127.0.0.1') + req.add_header('X-Requested-With', 'XMLHttpRequest') + req.add_header('Referer', url) + + playlistpage = self._download_webpage(req, video_id) + + req = compat_urllib_request.Request(unquote(json.loads(playlistpage)['url'])) + req.add_header('Referer', url) + + playlist = self._download_xml(req, video_id) + + formats = [] + for i in playlist.find('smilRoot/body'): + if 'AD' not in i.attrib['id']: + base_url = i.attrib['base'] + parsedurl = compat_urllib_parse_urlparse(base_url) + duration = i.attrib['duration'] + + for video in i.findall('video'): + if video.attrib['label'] != 'AD': + format_id = video.attrib['label'] + play_path = video.attrib['src'] + vbr = int(video.attrib['system-bitrate']) + + formats.append({ + 'format_id': format_id, + 'url': base_url, + 'vbr': vbr, + 'play_path': play_path, + 'app': parsedurl.path[1:] + '?' + parsedurl.query, + 'rtmp_live': True, + 'ext': 'flv', + }) + + self._sort_formats(formats) + + return { + 'id': episode_id, + 'title': self._html_search_regex(r'(.+?) — iVysílání — Česká televize', webpage, 'title'), + 'duration': float(duration), + 'formats': formats, + } From aa5590fa078927c2409b3f5301ae94d462d5d910 Mon Sep 17 00:00:00 2001 From: pulpe Date: Sat, 1 Mar 2014 12:34:01 +0100 Subject: [PATCH 2/4] skip test --- youtube_dl/extractor/ceskatelevize.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 92ae4ffcb..8a36bd980 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -27,6 +27,7 @@ class CeskaTelevizeIE(InfoExtractor): 'params': { 'skip_download': True, # requires rtmpdump }, + 'skip': 'Works only from Czech Republic.', }, { 'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt', 'info_dict': { @@ -38,6 +39,7 @@ class CeskaTelevizeIE(InfoExtractor): 'params': { 'skip_download': True, # requires rtmpdump }, + 'skip': 'Works only from Czech Republic.', }] def _real_extract(self, url): From c3cb92d1ab1b4d449dde9e234a1854c85d093ecc Mon Sep 17 00:00:00 2001 From: pulpe Date: Sat, 1 Mar 2014 16:02:51 +0100 Subject: [PATCH 3/4] [CeskaTelevize] fix python3 support @dstftw --- youtube_dl/extractor/ceskatelevize.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 8a36bd980..b1c683787 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re import json -from urllib import unquote from .common import InfoExtractor from ..utils import ( @@ -70,7 +69,7 @@ class CeskaTelevizeIE(InfoExtractor): playlistpage = self._download_webpage(req, video_id) - req = compat_urllib_request.Request(unquote(json.loads(playlistpage)['url'])) + req = compat_urllib_request.Request(compat_urllib_parse.unquote(json.loads(playlistpage)['url'])) req.add_header('Referer', url) playlist = self._download_xml(req, video_id) From 392017874c646cd884817fb5c16d101b67f20760 Mon Sep 17 00:00:00 2001 From: pulpe Date: Sat, 1 Mar 2014 16:17:29 +0100 Subject: [PATCH 4/4] [CeskaTelevize] raise ExtractorError if you are outside of CR --- youtube_dl/extractor/ceskatelevize.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index b1c683787..59f2a8e45 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -8,7 +8,8 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_request, compat_urllib_parse, - compat_urllib_parse_urlparse + compat_urllib_parse_urlparse, + ExtractorError, ) @@ -49,6 +50,10 @@ class CeskaTelevizeIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + if '

Chyba konfigurace prohlížeče.

' not in webpage: + msg = self._html_search_regex(r'

(.+?)

', webpage, 'error-message') + raise ExtractorError(msg.replace('
', ' ')) + typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type') episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')