youtube_dl/extractor/folketinget.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_parse_qs
   6 from ..utils import (
   7     int_or_none,
   8     parse_duration,
   9     parse_iso8601,
  10     xpath_text,
  11 )
  12
  13
  14 class FolketingetIE(InfoExtractor):
  15     IE_DESC = 'Folketinget (ft.dk; Danish parliament)'
  16     _VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx'
  17     _TEST = {
  18         'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player',
  19         'md5': '6269e8626fa1a891bf5369b386ae996a',
  20         'info_dict': {
  21             'id': '1165642',
  22             'ext': 'mp4',
  23             'title': 'Åbent samråd i Erhvervsudvalget',
  24             'description': 'Åbent samråd med erhvervs- og vækstministeren om regeringens politik på teleområdet',
  25             'view_count': int,
  26             'width': 768,
  27             'height': 432,
  28             'tbr': 928000,
  29             'timestamp': 1416493800,
  30             'upload_date': '20141120',
  31             'duration': 3960,
  32         },
  33         'params': {
  34             # rtmp download
  35             'skip_download': True,
  36         },
  37     }
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41         webpage = self._download_webpage(url, video_id)
  42
  43         title = self._og_search_title(webpage)
  44         description = self._html_search_regex(
  45             r'(?s)<div class="video-item-agenda"[^>]*>(.*?)<',
  46             webpage, 'description', fatal=False)
  47
  48         player_params = compat_parse_qs(self._search_regex(
  49             r'<embed src="http://ft\.arkena\.tv/flash/ftplayer\.swf\?([^"]+)"',
  50             webpage, 'player params'))
  51         xml_url = player_params['xml'][0]
  52         doc = self._download_xml(xml_url, video_id)
  53
  54         timestamp = parse_iso8601(xpath_text(doc, './/date'))
  55         duration = parse_duration(xpath_text(doc, './/duration'))
  56         width = int_or_none(xpath_text(doc, './/width'))
  57         height = int_or_none(xpath_text(doc, './/height'))
  58         view_count = int_or_none(xpath_text(doc, './/views'))
  59
  60         formats = [{
  61             'format_id': n.attrib['bitrate'],
  62             'url': xpath_text(n, './url', fatal=True),
  63             'tbr': int_or_none(n.attrib['bitrate']),
  64         } for n in doc.findall('.//streams/stream')]
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': video_id,
  69             'title': title,
  70             'formats': formats,
  71             'description': description,
  72             'timestamp': timestamp,
  73             'width': width,
  74             'height': height,
  75             'duration': duration,
  76             'view_count': view_count,
  77         }