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