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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     fix_xml_ampersands,
   8 )
   9
  10
  11 class BildIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
  13     IE_DESC = 'Bild.de'
  14     _TEST = {
  15         'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
  16         'md5': 'dd495cbd99f2413502a1713a1156ac8a',
  17         'info_dict': {
  18             'id': '38184146',
  19             'ext': 'mp4',
  20             'title': 'BILD hat sie getestet',
  21             'thumbnail': 're:^https?://.*\.jpg$',
  22             'duration': 196,
  23             'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29
  30         xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
  31         doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
  32
  33         duration = int_or_none(doc.attrib.get('duration'), scale=1000)
  34
  35         return {
  36             'id': video_id,
  37             'title': doc.attrib['ueberschrift'],
  38             'description': doc.attrib.get('text'),
  39             'url': doc.attrib['src'],
  40             'thumbnail': doc.attrib.get('img'),
  41             'duration': duration,
  42         }