_ Git - youtube-dl/blob - youtube_dl/extractor/dhm.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 import urllib2
   7 import xml.etree.ElementTree as ET
   8 import re
   9
  10
  11 class DHMIE(InfoExtractor):
  12     _VALID_URL = r'http://www\.dhm\.de/filmarchiv/(?P<id>.*?)'
  13
  14     _TEST = {
  15         'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
  16         'md5': '11c475f670209bf6acca0b2b7ef51827',
  17         'info_dict': {
  18             'id': 'marshallwg',
  19             'ext': 'flv',
  20             'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
  21             'thumbnail': 'http://www.dhm.de/filmarchiv/video/mpworkwg.jpg',
  22         }
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = ''
  27         webpage = self._download_webpage(url, video_id)
  28
  29         title = self._html_search_regex(
  30             r'dc:title=\"(.*?)\"', webpage, 'title')
  31
  32         playlist_url = self._html_search_regex(
  33             r'file: \'(.*?)\'', webpage, 'playlist URL')
  34
  35         xml_file = urllib2.urlopen(playlist_url)
  36         data = xml_file.read()
  37         xml_file.close()
  38
  39         root = ET.fromstring(data)
  40         video_url = root[0][0][0].text
  41         thumbnail = root[0][0][2].text
  42
  43         m = re.search('video/(.+?).flv', video_url)
  44         if m:
  45             video_id = m.group(1)
  46
  47         return {
  48             'id': video_id,
  49             'title': title,
  50             'url': video_url,
  51             'thumbnail': thumbnail,
  52         }