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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class FazIE(InfoExtractor):
   8     IE_NAME = 'faz.net'
   9     _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
  10
  11     _TESTS = [{
  12         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
  13         'info_dict': {
  14             'id': '12610585',
  15             'ext': 'mp4',
  16             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
  17             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
  18         },
  19     }, {
  20         'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  21         'only_matching': True,
  22     }, {
  23         'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  24         'only_matching': True,
  25     }, {
  26         'url': 'http://www.faz.net/-13659345.html',
  27         'only_matching': True,
  28     }, {
  29         'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
  30         'only_matching': True,
  31     }, {
  32         'url': 'http://www.faz.net/foobarblafasel-13659345.html',
  33         'only_matching': True,
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(url, video_id)
  40         config_xml_url = self._search_regex(
  41             r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
  42         config = self._download_xml(
  43             config_xml_url, video_id, 'Downloading config xml')
  44
  45         encodings = config.find('ENCODINGS')
  46         formats = []
  47         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
  48             encoding = encodings.find(code)
  49             if encoding is None:
  50                 continue
  51             encoding_url = encoding.find('FILENAME').text
  52             formats.append({
  53                 'url': encoding_url,
  54                 'format_id': code.lower(),
  55                 'quality': pref,
  56             })
  57         self._sort_formats(formats)
  58
  59         descr = self._html_search_regex(
  60             r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
  61         return {
  62             'id': video_id,
  63             'title': self._og_search_title(webpage),
  64             'formats': formats,
  65             'description': descr,
  66             'thumbnail': config.find('STILL/STILL_BIG').text,
  67         }