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 ..utils import (
   9     int_or_none,
  10     sanitized_Request,
  11 )
  12
  13
  14 def _get_api_key(api_path):
  15     if api_path.endswith('?'):
  16         api_path = api_path[:-1]
  17
  18     api_key = 'fb5f58a820353bd7095de526253c14fd'
  19     a = '{0:}{1:}{2:}'.format(api_key, api_path, int(round(time.time() / 24 / 3600)))
  20     return hashlib.md5(a.encode('ascii')).hexdigest()
  21
  22
  23 class StreamCZIE(InfoExtractor):
  24     _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<id>[0-9]+)'
  25     _API_URL = 'http://www.stream.cz/API'
  26
  27     _TESTS = [{
  28         'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
  29         'md5': '934bb6a6d220d99c010783c9719960d5',
  30         'info_dict': {
  31             'id': '765767',
  32             'ext': 'mp4',
  33             'title': 'Peklo na talíři: Éčka pro děti',
  34             'description': 'Taška s grónskou pomazánkou a další pekelnosti ZDE',
  35             'thumbnail': 're:^http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
  36             'duration': 256,
  37         },
  38     }, {
  39         'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
  40         'md5': '849a88c1e1ca47d41403c2ba5e59e261',
  41         'info_dict': {
  42             'id': '10002447',
  43             'ext': 'mp4',
  44             'title': 'Kancelář Blaník: Tři roky pro Mazánka',
  45             'description': 'md5:3862a00ba7bf0b3e44806b544032c859',
  46             'thumbnail': 're:^http://im.stream.cz/episode/537f838c50c11f8d21320000',
  47             'duration': 368,
  48         },
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53         api_path = '/episode/%s' % video_id
  54
  55         req = sanitized_Request(self._API_URL + api_path)
  56         req.add_header('Api-Password', _get_api_key(api_path))
  57         data = self._download_json(req, video_id)
  58
  59         formats = []
  60         for quality, video in enumerate(data['video_qualities']):
  61             for f in video['formats']:
  62                 typ = f['type'].partition('/')[2]
  63                 qlabel = video.get('quality_label')
  64                 formats.append({
  65                     'format_note': '%s-%s' % (qlabel, typ) if qlabel else typ,
  66                     'format_id': '%s-%s' % (typ, f['quality']),
  67                     'url': f['source'],
  68                     'height': int_or_none(f['quality'].rstrip('p')),
  69                     'quality': quality,
  70                 })
  71         self._sort_formats(formats)
  72
  73         image = data.get('image')
  74         if image:
  75             thumbnail = self._proto_relative_url(
  76                 image.replace('{width}', '1240').replace('{height}', '697'),
  77                 scheme='http:',
  78             )
  79         else:
  80             thumbnail = None
  81
  82         stream = data.get('_embedded', {}).get('stream:show', {}).get('name')
  83         if stream:
  84             title = '%s: %s' % (stream, data['name'])
  85         else:
  86             title = data['name']
  87
  88         subtitles = {}
  89         srt_url = data.get('subtitles_srt')
  90         if srt_url:
  91             subtitles['cs'] = [{
  92                 'ext': 'srt',
  93                 'url': srt_url,
  94             }]
  95
  96         return {
  97             'id': video_id,
  98             'title': title,
  99             'thumbnail': thumbnail,
 100             'formats': formats,
 101             'description': data.get('web_site_text'),
 102             'duration': int_or_none(data.get('duration')),
 103             'view_count': int_or_none(data.get('views')),
 104             'subtitles': subtitles,
 105         }