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

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7 )
   8
   9
  10 class StreamCZIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)'
  12
  13     _TESTS = [{
  14         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
  15         'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
  16         'info_dict': {
  17             'id': '765767',
  18             'ext': 'mp4',
  19             'title': 'Peklo na talíři: Éčka pro děti',
  20             'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE',
  21             'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
  22             'duration': 256,
  23         },
  24     }, {
  25         'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
  26         'md5': 'e54a254fb8b871968fd8403255f28589',
  27         'info_dict': {
  28             'id': '10002447',
  29             'ext': 'mp4',
  30             'title': 'Kancelář Blaník: Tři roky pro Mazánka',
  31             'description': 'md5:3862a00ba7bf0b3e44806b544032c859',
  32             'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000',
  33             'duration': 368,
  34         },
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39         data = self._download_json(
  40             'http://www.stream.cz/API/episode/%s' % video_id, video_id)
  41
  42         formats = []
  43         for quality, video in enumerate(data['video_qualities']):
  44             for f in video['formats']:
  45                 typ = f['type'].partition('/')[2]
  46                 qlabel = video.get('quality_label')
  47                 formats.append({
  48                     'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ,
  49                     'format_id': '%s-%s' % (typ, f['quality']),
  50                     'url': f['source'],
  51                     'height': int_or_none(f['quality'].rstrip('p')),
  52                     'quality': quality,
  53                 })
  54         self._sort_formats(formats)
  55
  56         image = data.get('image')
  57         if image:
  58             thumbnail = self._proto_relative_url(
  59                 image.replace('{width}', '1240').replace('{height}', '697'),
  60                 scheme='http:',
  61             )
  62         else:
  63             thumbnail = None
  64
  65         stream = data.get('_embedded', {}).get('stream:show', {}).get('name')
  66         if stream:
  67             title = '%s: %s' % (stream, data['name'])
  68         else:
  69             title = data['name']
  70
  71         return {
  72             'id': video_id,
  73             'title': title,
  74             'thumbnail': thumbnail,
  75             'formats': formats,
  76             'description': data.get('web_site_text'),
  77             'duration': int_or_none(data.get('duration')),
  78             'view_count': int_or_none(data.get('views')),
  79         }