From b03d65c2370d812f4bb141e6d9599553267c07ac Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 11 Apr 2013 10:47:21 +0200 Subject: [PATCH] Minor improvements for ARD IE --- test/tests.json | 10 ++++++++++ youtube_dl/InfoExtractors.py | 16 ++++++++++------ 2 files changed, 20 insertions(+), 6 deletions(-) diff --git a/test/tests.json b/test/tests.json index 0c94c65bd..0c3b24054 100644 --- a/test/tests.json +++ b/test/tests.json @@ -328,5 +328,15 @@ "info_dict": { "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! " } + }, + { + "name": "ARD", + "url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640", + "file": "14077640.mp4", + "md5": "6ca8824255460c787376353f9e20bbd8", + "info_dict": { + "title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden" + } } + ] diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 3d8145e16..51aca5497 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -4357,15 +4357,19 @@ def _real_extract(self, url): return [info] class ARDIE(InfoExtractor): - IE_NAME = 'ard' - _VALID_URL = r'^(?:http?://)?mediathek\.daserste\.de/(?:.*/)(?P[^/\?]+)(?:\?.*)?' - _TITLE = r'

(?P.*)</h1>' + _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' + _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>' _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)' def _real_extract(self, url): # determine video id from url m = re.match(self._VALID_URL, url) - video_id = m.group('video_id') + + numid = re.search(r'documentId=([0-9]+)', url) + if numid: + video_id = numid.group(1) + else: + video_id = m.group('video_id') # determine title and media streams from webpage html = self._download_webpage(url, video_id) @@ -4377,8 +4381,8 @@ def _real_extract(self, url): return # choose default media type and highest quality for now - stream = max([s for s in streams if int(s["media_type"]) == 0], key=lambda s: int(s["quality"])) - #stream = streams[-1] + stream = max([s for s in streams if int(s["media_type"]) == 0], + key=lambda s: int(s["quality"])) # there's two possibilities: RTMP stream or HTTP download info = {'id': video_id, 'title': title, 'ext': 'mp4'}