w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

Minor improvements for ARD IE

Browse source
This commit is contained in:
Philipp Hagemeister 2013-04-11 10:47:21 +02:00
parent df2dedeefb
commit b03d65c237
2 changed files with 20 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
test/tests.json
View file

@ -328,5 +328,15 @@
"info_dict": { "info_dict": {
"title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! " "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"
}
} }
] ]

16
youtube_dl/InfoExtractors.py
View file

@ -4357,15 +4357,19 @@ class LiveLeakIE(InfoExtractor):
return [info] return [info]
class ARDIE(InfoExtractor): class ARDIE(InfoExtractor):
IE_NAME = 'ard' _VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
_VALID_URL = r'^(?:http?://)?mediathek\.daserste\.de/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?' _TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
_TITLE = r'<h1 class="boxTopHeadline">(?P<title>.*)</h1>'
_MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)' _MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
def _real_extract(self, url): def _real_extract(self, url):
# determine video id from url # determine video id from url
m = re.match(self._VALID_URL, 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 # determine title and media streams from webpage
html = self._download_webpage(url, video_id) html = self._download_webpage(url, video_id)
@ -4377,8 +4381,8 @@ class ARDIE(InfoExtractor):
return return
# choose default media type and highest quality for now # 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 = max([s for s in streams if int(s["media_type"]) == 0],
#stream = streams[-1] key=lambda s: int(s["quality"]))
# there's two possibilities: RTMP stream or HTTP download # there's two possibilities: RTMP stream or HTTP download
info = {'id': video_id, 'title': title, 'ext': 'mp4'} info = {'id': video_id, 'title': title, 'ext': 'mp4'}