diff options
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/ceskatelevize.py | 106 |
2 files changed, 107 insertions, 0 deletions
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<id>[^?#]+)' + + _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'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'), + 'duration': float(duration), + 'formats': formats, + } |