youtube_dl/extractor/faz.py

   1 # encoding: utf-8
   2 import re
   3 import xml.etree.ElementTree
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8 )
   9
  10
  11 class FazIE(InfoExtractor):
  12     IE_NAME = u'faz.net'
  13     _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+).html'
  14
  15     _TEST = {
  16         u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
  17         u'file': u'12610585.mp4',
  18         u'info_dict': {
  19             u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
  20             u'description': u'md5:1453fbf9a0d041d985a47306192ea253',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27         self.to_screen(video_id)
  28         webpage = self._download_webpage(url, video_id)
  29         config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
  30             u'config xml url')
  31         config_xml = self._download_webpage(config_xml_url, video_id,
  32             u'Downloading config xml')
  33         config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
  34
  35         encodings = config.find('ENCODINGS')
  36         formats = []
  37         for code in ['LOW', 'HIGH', 'HQ']:
  38             encoding = encodings.find(code)
  39             if encoding is None:
  40                 continue
  41             encoding_url = encoding.find('FILENAME').text
  42             formats.append({
  43                 'url': encoding_url,
  44                 'ext': determine_ext(encoding_url),
  45                 'format_id': code.lower(),
  46             })
  47
  48         descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
  49         info = {
  50             'id': video_id,
  51             'title': self._og_search_title(webpage),
  52             'formats': formats,
  53             'description': descr,
  54             'thumbnail': config.find('STILL/STILL_BIG').text,
  55         }
  56         # TODO: Remove when #980 has been merged
  57         info.update(formats[-1])
  58         return info