From f4858a71035549cf82b258d01dda5060aef707b7 Mon Sep 17 00:00:00 2001 From: Christopher Krooss Date: Sun, 4 Jan 2015 13:33:26 +0100 Subject: [PATCH] Add support for Radio Bremen --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/radiobremen.py | 55 +++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/radiobremen.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 143cd5c49..349f4fe71 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -339,6 +339,7 @@ from .pyvideo import PyvideoIE from .quickvid import QuickVidIE from .radiode import RadioDeIE +from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE diff --git a/youtube_dl/extractor/radiobremen.py b/youtube_dl/extractor/radiobremen.py new file mode 100644 index 000000000..68c78c4f9 --- /dev/null +++ b/youtube_dl/extractor/radiobremen.py @@ -0,0 +1,55 @@ +# -*- coding: utf-8 -*- + +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class RadioBremenIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(index\.html)?\?id=(?P[0-9]+)' + IE_NAME = 'radiobremen' + + _TEST = { + 'url': 'http://www.radiobremen.de/mediathek/index.html?id=114720', + 'info_dict': { + 'id': '114720', + 'ext': 'mp4', + 'height': 288, + 'width': 512, + 'title': 'buten un binnen vom 22. Dezember', + 'description': 'Unter anderem mit diesen Themen: 45 Flüchtlinge sind in Worpswede angekommen +++ Freies Internet für alle: Bremer arbeiten an einem flächendeckenden W-Lan-Netzwerk +++ Aktivisten kämpfen für das Unibad +++ So war das Wetter 2014 +++', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('video_id') + + meta_url = "http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s" % video_id + meta_doc = self._download_webpage(meta_url, video_id, 'Downloading metadata') + title = self._html_search_regex("(?P.+)</h1>", meta_doc, "title") + description = self._html_search_regex("<p>(?P<description>.*)</p>", meta_doc, "description") + duration = self._html_search_regex("Länge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>", meta_doc, "duration") + + page_doc = self._download_webpage(url, video_id, 'Downloading video information') + pattern = "ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)" + mobj = re.search(pattern, page_doc) + width, video_id, secret, thumbnail = int(mobj.group("width")), mobj.group("video_id"), mobj.group("secret"), mobj.group("thumbnail") + video_url = "http://dl-ondemand.radiobremen.de/mediabase/{:}/{:}_{:}_{:}.mp4".format(video_id, video_id, secret, width) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'formats': [ + {'url': video_url, + 'ext': 'mp4', + 'width': width, + 'protocol': 'http' + } + ], + 'thumbnail': thumbnail, + }