yt_dlp/extractor/karrierevideos.py

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