diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/radiobremen.py | 30 |
1 files changed, 16 insertions, 14 deletions
diff --git a/youtube_dl/extractor/radiobremen.py b/youtube_dl/extractor/radiobremen.py index 6d130d3d9..9f7e6af15 100644 --- a/youtube_dl/extractor/radiobremen.py +++ b/youtube_dl/extractor/radiobremen.py @@ -5,10 +5,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import parse_duration 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' _TEST = { @@ -16,6 +17,7 @@ class RadioBremenIE(InfoExtractor): 'info_dict': { 'id': '114720', 'ext': 'mp4', + 'duration': 1685, '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 +++', @@ -23,32 +25,32 @@ class RadioBremenIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) 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("<h1.*>(?P<title>.+)</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") + duration = parse_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) + video_url = ( + "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 { 'id': video_id, 'title': title, 'description': description, 'duration': duration, - 'formats': [ - {'url': video_url, - 'ext': 'mp4', - 'width': width, - 'protocol': 'http' - } - ], - 'thumbnail': thumbnail, + 'formats': formats, + 'thumbnail': mobj.group('thumbnail'), } |