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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     xpath_element,
   7     xpath_text,
   8     int_or_none,
   9 )
  10
  11
  12 class FazIE(InfoExtractor):
  13     IE_NAME = 'faz.net'
  14     _VALID_URL = r'https?://(?:www\.)?faz\.net/(?:[^/]+/)*.*?-(?P<id>\d+)\.html'
  15
  16     _TESTS = [{
  17         'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
  18         'info_dict': {
  19             'id': '12610585',
  20             'ext': 'mp4',
  21             'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
  22             'description': 'md5:1453fbf9a0d041d985a47306192ea253',
  23         },
  24     }, {
  25         'url': 'http://www.faz.net/aktuell/politik/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  26         'only_matching': True,
  27     }, {
  28         'url': 'http://www.faz.net/berlin-gabriel-besteht-zerreissprobe-ueber-datenspeicherung-13659345.html',
  29         'only_matching': True,
  30     }, {
  31         'url': 'http://www.faz.net/-13659345.html',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.faz.net/aktuell/politik/-13659345.html',
  35         'only_matching': True,
  36     }, {
  37         'url': 'http://www.faz.net/foobarblafasel-13659345.html',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         video_id = self._match_id(url)
  43
  44         webpage = self._download_webpage(url, video_id)
  45         description = self._og_search_description(webpage)
  46         config_xml_url = self._search_regex(
  47             r'videoXMLURL\s*=\s*"([^"]+)', webpage, 'config xml url')
  48         config = self._download_xml(
  49             config_xml_url, video_id, 'Downloading config xml')
  50
  51         encodings = xpath_element(config, 'ENCODINGS', 'encodings', True)
  52         formats = []
  53         for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
  54             encoding = xpath_element(encodings, code)
  55             if encoding is not None:
  56                 encoding_url = xpath_text(encoding, 'FILENAME')
  57                 if encoding_url:
  58                     formats.append({
  59                         'url': encoding_url,
  60                         'format_id': code.lower(),
  61                         'quality': pref,
  62                         'tbr': int_or_none(xpath_text(encoding, 'AVERAGEBITRATE')),
  63                     })
  64         self._sort_formats(formats)
  65
  66         return {
  67             'id': video_id,
  68             'title': self._og_search_title(webpage),
  69             'formats': formats,
  70             'description': description.strip() if description else None,
  71             'thumbnail': xpath_text(config, 'STILL/STILL_BIG'),
  72             'duration': int_or_none(xpath_text(config, 'DURATION')),
  73         }