youtube_dl/extractor/radiobremen.py



    1 # coding: utf-8
    2 
    3 from __future__ import unicode_literals
    4 
    5 import re
    6 
    7 from .common import InfoExtractor
    8 from ..utils import parse_duration
    9 
   10 
   11 class RadioBremenIE(InfoExtractor):
   12     _VALID_URL = r'http?://(?:www\.)?radiobremen\.de/mediathek/(?:index\.html)?\?id=(?P<id>[0-9]+)'
   13     IE_NAME = 'radiobremen'
   14 
   15     _TEST = {
   16         'url': 'http://www.radiobremen.de/mediathek/?id=141876',
   17         'info_dict': {
   18             'id': '141876',
   19             'ext': 'mp4',
   20             'duration': 178,
   21             'width': 512,
   22             'title': 'Druck auf Patrick Öztürk',
   23             'thumbnail': r're:https?://.*\.jpg$',
   24             'description': 'Gegen den SPD-Bürgerschaftsabgeordneten Patrick Öztürk wird wegen Beihilfe zum gewerbsmäßigen Betrug ermittelt. Am Donnerstagabend sollte er dem Vorstand des SPD-Unterbezirks Bremerhaven dazu Rede und Antwort stehen.',
   25         },
   26     }
   27 
   28     def _real_extract(self, url):
   29         video_id = self._match_id(url)
   30 
   31         meta_url = 'http://www.radiobremen.de/apps/php/mediathek/metadaten.php?id=%s' % video_id
   32         meta_doc = self._download_webpage(
   33             meta_url, video_id, 'Downloading metadata')
   34         title = self._html_search_regex(
   35             r'<h1.*>(?P<title>.+)</h1>', meta_doc, 'title')
   36         description = self._html_search_regex(
   37             r'<p>(?P<description>.*)</p>', meta_doc, 'description', fatal=False)
   38         duration = parse_duration(self._html_search_regex(
   39             r'L&auml;nge:</td>\s+<td>(?P<duration>[0-9]+:[0-9]+)</td>',
   40             meta_doc, 'duration', fatal=False))
   41 
   42         page_doc = self._download_webpage(
   43             url, video_id, 'Downloading video information')
   44         mobj = re.search(
   45             r"ardformatplayerclassic\(\'playerbereich\',\'(?P<width>[0-9]+)\',\'.*\',\'(?P<video_id>[0-9]+)\',\'(?P<secret>[0-9]+)\',\'(?P<thumbnail>.+)\',\'\'\)",
   46             page_doc)
   47         video_url = (
   48             "http://dl-ondemand.radiobremen.de/mediabase/%s/%s_%s_%s.mp4" %
   49             (video_id, video_id, mobj.group("secret"), mobj.group('width')))
   50 
   51         formats = [{
   52             'url': video_url,
   53             'ext': 'mp4',
   54             'width': int(mobj.group('width')),
   55         }]
   56         return {
   57             'id': video_id,
   58             'title': title,
   59             'description': description,
   60             'duration': duration,
   61             'formats': formats,
   62             'thumbnail': mobj.group('thumbnail'),
   63         }