yt_dlp/extractor/folketinget.py

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