youtube_dl/extractor/streamcz.py

   1 # -*- coding: utf-8 -*-
   2 from __future__ import unicode_literals
   3
   4 import hashlib
   5 import time
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     int_or_none,
  13 )
  14
  15
  16 def _get_api_key(api_path):
  17     if api_path.endswith('?'):
  18         api_path = api_path[:-1]
  19
  20     api_key = 'fb5f58a820353bd7095de526253c14fd'
  21     a = '{0:}{1:}{2:}'.format(api_key, api_path, int(round(time.time() / 24 / 3600)))
  22     return hashlib.md5(a.encode('ascii')).hexdigest()
  23
  24
  25 class StreamCZIE(InfoExtractor):
  26     _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)'
  27     _API_URL = 'http://www.stream.cz/API'
  28
  29     _TESTS = [{
  30         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
  31         'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
  32         'info_dict': {
  33             'id': '765767',
  34             'ext': 'mp4',
  35             'title': 'Peklo na talíři: Éčka pro děti',
  36             'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE',
  37             'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
  38             'duration': 256,
  39         },
  40     }, {
  41         'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
  42         'md5': 'e54a254fb8b871968fd8403255f28589',
  43         'info_dict': {
  44             'id': '10002447',
  45             'ext': 'mp4',
  46             'title': 'Kancelář Blaník: Tři roky pro Mazánka',
  47             'description': 'md5:3862a00ba7bf0b3e44806b544032c859',
  48             'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000',
  49             'duration': 368,
  50         },
  51     }]
  52
  53     def _real_extract(self, url):
  54         video_id = self._match_id(url)
  55         api_path = '/episode/%s' % video_id
  56
  57         req = compat_urllib_request.Request(self._API_URL + api_path)
  58         req.add_header('Api-Password', _get_api_key(api_path))
  59         data = self._download_json(req, video_id)
  60
  61         formats = []
  62         for quality, video in enumerate(data['video_qualities']):
  63             for f in video['formats']:
  64                 typ = f['type'].partition('/')[2]
  65                 qlabel = video.get('quality_label')
  66                 formats.append({
  67                     'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ,
  68                     'format_id': '%s-%s' % (typ, f['quality']),
  69                     'url': f['source'],
  70                     'height': int_or_none(f['quality'].rstrip('p')),
  71                     'quality': quality,
  72                 })
  73         self._sort_formats(formats)
  74
  75         image = data.get('image')
  76         if image:
  77             thumbnail = self._proto_relative_url(
  78                 image.replace('{width}', '1240').replace('{height}', '697'),
  79                 scheme='http:',
  80             )
  81         else:
  82             thumbnail = None
  83
  84         stream = data.get('_embedded', {}).get('stream:show', {}).get('name')
  85         if stream:
  86             title = '%s: %s' % (stream, data['name'])
  87         else:
  88             title = data['name']
  89
  90         return {
  91             'id': video_id,
  92             'title': title,
  93             'thumbnail': thumbnail,
  94             'formats': formats,
  95             'description': data.get('web_site_text'),
  96             'duration': int_or_none(data.get('duration')),
  97             'view_count': int_or_none(data.get('views')),
  98         }