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

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 import re
   6 import json
   7 from .common import InfoExtractor
   8 from ..utils import (
   9         ExtractorError,
  10         js_to_json,
  11         unescapeHTML
  12 )
  13
  14
  15 class DVTVIE(InfoExtractor):
  16         IE_NAME = 'dvtv'
  17         IE_DESC = 'http://video.aktualne.cz/dvtv/'
  18
  19         _VALID_URL = r'http://video\.aktualne\.cz/dvtv/(?P<id>[a-z0-9-]+/r~[0-9a-f]{32})/?'
  20
  21         _TESTS = [{
  22                 'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
  23                 'md5': '75800f964fa0f82939a2914563301f72',
  24                 'info_dict': {
  25                         'id': 'e5efe9ca855511e4833a0025900fea04',
  26                         'ext': 'webm',
  27                         'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně'
  28                 }
  29         }, {
  30                 'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/',
  31                 'md5': 'd50455195a67a94c57f931360cc68a1b',
  32                 'info_dict': {
  33                         'id': '82ed4322849211e4a10c0025900fea04',
  34                         'ext': 'webm',
  35                         'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala'
  36                 }
  37         }]
  38
  39         def _real_extract(self, url):
  40                 video_id = self._match_id(url)
  41                 webpage = self._download_webpage(url, video_id)
  42
  43                 code = self._search_regex(r'embedData[0-9a-f]{32}\[\'asset\'\] = (\{.+?\});', webpage, 'video JSON', flags=re.DOTALL)
  44                 payload = self._parse_json(code, video_id, transform_source=js_to_json)
  45                 formats = []
  46                 for source in payload['sources']:
  47                         formats.append({
  48                                 'url': source['file'],
  49                                 'ext': source['type'][6:],
  50                                 'format': '%s %s' % (source['type'][6:], source['label']),
  51                                 'format_id': '%s-%s' % (source['type'][6:], source['label']),
  52                                 'resolution': source['label'],
  53                                 'fps': 25,
  54                                 'preference': -1 if source['type'][6:] == 'mp4' and source['label'] == '720p' else -2
  55                         })
  56
  57                 return {
  58                         'id': video_id[-32:],
  59                         'display_id': video_id[:-35],
  60                         'title': unescapeHTML(payload['title']),
  61                         'thumbnail': 'http:%s' % payload['image'],
  62                         'formats': formats
  63                 }