Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/karrierevideos.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_urlparse
   6 from ..utils import (
   7     fix_xml_ampersands,
   8     float_or_none,
   9     xpath_with_ns,
  10     xpath_text,
  11 )
  12
  13
  14 class KarriereVideosIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)'
  16     _TESTS = [{
  17         'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin',
  18         'info_dict': {
  19             'id': '32c91',
  20             'ext': 'flv',
  21             'title': 'AltenpflegerIn',
  22             'description': 'md5:dbadd1259fde2159a9b28667cb664ae2',
  23             'thumbnail': r're:^http://.*\.png',
  24         },
  25         'params': {
  26             # rtmp download
  27             'skip_download': True,
  28         }
  29     }, {
  30         # broken ampersands
  31         'url': 'http://www.karrierevideos.at/orientierung/vaeterkarenz-und-neue-chancen-fuer-muetter-baby-was-nun',
  32         'info_dict': {
  33             'id': '5sniu',
  34             'ext': 'flv',
  35             'title': 'Väterkarenz und neue Chancen für Mütter - "Baby - was nun?"',
  36             'description': 'md5:97092c6ad1fd7d38e9d6a5fdeb2bcc33',
  37             'thumbnail': r're:^http://.*\.png',
  38         },
  39         'params': {
  40             # rtmp download
  41             'skip_download': True,
  42         }
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47
  48         webpage = self._download_webpage(url, video_id)
  49
  50         title = (self._html_search_meta('title', webpage, default=None) or
  51                  self._search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'video title'))
  52
  53         video_id = self._search_regex(
  54             r'/config/video/(.+?)\.xml', webpage, 'video id')
  55         # Server returns malformed headers
  56         # Force Accept-Encoding: * to prevent gzipped results
  57         playlist = self._download_xml(
  58             'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id,
  59             video_id, transform_source=fix_xml_ampersands,
  60             headers={'Accept-Encoding': '*'})
  61
  62         NS_MAP = {
  63             'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'
  64         }
  65
  66         def ns(path):
  67             return xpath_with_ns(path, NS_MAP)
  68
  69         item = playlist.find('./tracklist/item')
  70         video_file = xpath_text(
  71             item, ns('./jwplayer:file'), 'video url', fatal=True)
  72         streamer = xpath_text(
  73             item, ns('./jwplayer:streamer'), 'streamer', fatal=True)
  74
  75         uploader = xpath_text(
  76             item, ns('./jwplayer:author'), 'uploader')
  77         duration = float_or_none(
  78             xpath_text(item, ns('./jwplayer:duration'), 'duration'))
  79
  80         description = self._html_search_regex(
  81             r'(?s)<div class="leadtext">(.+?)</div>',
  82             webpage, 'description')
  83
  84         thumbnail = self._html_search_meta(
  85             'thumbnail', webpage, 'thumbnail')
  86         if thumbnail:
  87             thumbnail = compat_urlparse.urljoin(url, thumbnail)
  88
  89         return {
  90             'id': video_id,
  91             'url': streamer.replace('rtmpt', 'rtmp'),
  92             'play_path': 'mp4:%s' % video_file,
  93             'ext': 'flv',
  94             'title': title,
  95             'description': description,
  96             'thumbnail': thumbnail,
  97             'uploader': uploader,
  98             'duration': duration,
  99         }