[radiobremen] Fix under Python 2.6 and fix duration

This commit is contained in:
Philipp Hagemeister 2015-01-05 18:13:19 +01:00
parent 93e40a7b2f
commit 9d247bbd2d

View file

@ -5,10 +5,11 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import parse_duration
class RadioBremenIE(InfoExtractor): class RadioBremenIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(index\.html)?\?id=(?P<video_id>[0-9]+)' _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(?:index\.html)?\?id=(?P<id>[0-9]+)'
IE_NAME = 'radiobremen' IE_NAME = 'radiobremen'
_TEST = { _TEST = {
@ -16,6 +17,7 @@ class RadioBremenIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '114720', 'id': '114720',
'ext': 'mp4', 'ext': 'mp4',
'duration': 1685,
'width': 512, 'width': 512,
'title': 'buten un binnen vom 22. Dezember', '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 +++', '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 +++',
@ -23,32 +25,32 @@ class RadioBremenIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('video_id')
meta_url = "http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s" % 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') meta_doc = self._download_webpage(meta_url, video_id, 'Downloading metadata')
title = self._html_search_regex("<h1.*>(?P<title>.+)</h1>", meta_doc, "title") title = self._html_search_regex("<h1.*>(?P<title>.+)</h1>", meta_doc, "title")
description = self._html_search_regex("<p>(?P<description>.*)</p>", meta_doc, "description") description = self._html_search_regex("<p>(?P<description>.*)</p>", meta_doc, "description")
duration = self._html_search_regex("L&auml;nge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>", meta_doc, "duration") duration = parse_duration(
self._html_search_regex("L&auml;nge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>", meta_doc, "duration"))
page_doc = self._download_webpage(url, video_id, 'Downloading video information') page_doc = self._download_webpage(url, video_id, 'Downloading video information')
pattern = "ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)" pattern = "ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)"
mobj = re.search(pattern, page_doc) 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 = (
video_url = "http://dl-ondemand.radiobremen.de/mediabase/{:}/{:}_{:}_{:}.mp4".format(video_id, video_id, secret, width) "http://dl-ondemand.radiobremen.de/mediabase/%s/%s_%s_%s.mp4" %
(video_id, video_id, mobj.group("secret"), mobj.group('width')))
formats = [{
'url': video_url,
'ext': 'mp4',
'width': int(mobj.group("width")),
}]
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': description,
'duration': duration, 'duration': duration,
'formats': [ 'formats': formats,
{'url': video_url, 'thumbnail': mobj.group('thumbnail'),
'ext': 'mp4',
'width': width,
'protocol': 'http'
}
],
'thumbnail': thumbnail,
} }