diff options
author | Boris Wachtmeister <boris-code@gmx.com> | 2016-05-26 19:58:55 +0200 |
---|---|---|
committer | Boris Wachtmeister <boris-code@gmx.com> | 2016-05-26 20:54:51 +0200 |
commit | 949fc42e009aed5414caad280d0dc551ffcd9c14 (patch) | |
tree | 356d690fc9ce8d5578e550684937568731d873fa /youtube_dl/extractor/wdr.py | |
parent | 33a1ff7113d9dd656b3c56cb404de85646caa559 (diff) |
[WDR] the other wdrmaus.de pages also changed to the new player
Diffstat (limited to 'youtube_dl/extractor/wdr.py')
-rw-r--r-- | youtube_dl/extractor/wdr.py | 89 |
1 files changed, 15 insertions, 74 deletions
diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index dd107ef8a..1af1e996d 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -4,10 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_parse_qs, - compat_urlparse, -) from ..utils import ( determine_ext, js_to_json, @@ -18,7 +14,7 @@ from ..utils import ( class WDRIE(InfoExtractor): - _CURRENT_MAUS_URL = r'https?://www.wdrmaus.de/aktuelle-sendung/(wdr|index).php5' + _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5' _PAGE_REGEX = r'/mediathek/(?P<media_type>[^/]+)/(?P<type>[^/]+)/(?P<display_id>.+)\.html' _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL @@ -92,6 +88,20 @@ class WDRIE(InfoExtractor): }, 'skip': 'The id changes from week to week because of the new episode' }, + { + 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5', + 'md5': 'ca365705551e4bd5217490f3b0591290', + 'info_dict': { + 'id': 'mdb-186083', + 'ext': 'flv', + 'upload_date': '20130919', + 'title': 'Sachgeschichte - Achterbahn ', + 'description': '- Die Sendung mit der Maus -', + }, + 'params': { + 'skip_download': True, # the file has different versions :( + }, + }, ] def _real_extract(self, url): @@ -222,72 +232,3 @@ class WDRMobileIE(InfoExtractor): 'User-Agent': 'mobile', }, } - - -class WDRMausIE(InfoExtractor): - _VALID_URL = 'https?://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)((?<!index)\.php5|/(?:$|[?#]))' - IE_DESC = 'Sendung mit der Maus' - _TESTS = [{ - 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5', - 'md5': '178b432d002162a14ccb3e0876741095', - 'info_dict': { - 'id': 'achterbahn', - 'ext': 'mp4', - 'thumbnail': 're:^http://.+\.jpg', - 'upload_date': '20131001', - 'title': '19.09.2013 - Achterbahn', - } - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - param_code = self._html_search_regex( - r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters') - - title_date = self._search_regex( - r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>', - webpage, 'air date') - title_str = self._html_search_regex( - r'<h1>(.*?)</h1>', webpage, 'title') - title = '%s - %s' % (title_date, title_str) - upload_date = unified_strdate( - self._html_search_meta('dc.date', webpage)) - - fields = compat_parse_qs(param_code) - video_url = fields['firstVideo'][0] - thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0]) - - formats = [{ - 'format_id': 'rtmp', - 'url': video_url, - }] - - jscode = self._download_webpage( - 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js', - video_id, fatal=False, - note='Downloading URL translation table', - errnote='Could not download URL translation table') - if jscode: - for m in re.finditer( - r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}", - jscode): - if video_url.startswith(m.group('stream')): - http_url = video_url.replace( - m.group('stream'), m.group('dl')) - formats.append({ - 'format_id': 'http', - 'url': http_url, - }) - break - - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - } |