youtube_dl/extractor/kanalplay.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     float_or_none,
  10     srt_subtitles_timecode,
  11 )
  12
  13
  14 class KanalPlayIE(InfoExtractor):
  15     IE_DESC = 'Kanal 5/9/11 Play'
  16     _VALID_URL = r'https?://(?:www\.)?kanal(?P<channel_id>5|9|11)play\.se/(?:#!/)?(?:play/)?program/\d+/video/(?P<id>\d+)'
  17     _TESTS = [{
  18         'url': 'http://www.kanal5play.se/#!/play/program/3060212363/video/3270012277',
  19         'info_dict': {
  20             'id': '3270012277',
  21             'ext': 'flv',
  22             'title': 'Saknar både dusch och avlopp',
  23             'description': 'md5:6023a95832a06059832ae93bc3c7efb7',
  24             'duration': 2636.36,
  25         },
  26         'params': {
  27             # rtmp download
  28             'skip_download': True,
  29         }
  30     }, {
  31         'url': 'http://www.kanal9play.se/#!/play/program/335032/video/246042',
  32         'only_matching': True,
  33     }, {
  34         'url': 'http://www.kanal11play.se/#!/play/program/232835958/video/367135199',
  35         'only_matching': True,
  36     }]
  37
  38     def _fix_subtitles(self, subs):
  39         return '\r\n\r\n'.join(
  40             '%s\r\n%s --> %s\r\n%s'
  41             % (
  42                 num,
  43                 srt_subtitles_timecode(item['startMillis'] / 1000.0),
  44                 srt_subtitles_timecode(item['endMillis'] / 1000.0),
  45                 item['text'],
  46             ) for num, item in enumerate(subs, 1))
  47
  48     def _get_subtitles(self, channel_id, video_id):
  49         subs = self._download_json(
  50             'http://www.kanal%splay.se/api/subtitles/%s' % (channel_id, video_id),
  51             video_id, 'Downloading subtitles JSON', fatal=False)
  52         return {'sv': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} if subs else {}
  53
  54     def _real_extract(self, url):
  55         mobj = re.match(self._VALID_URL, url)
  56         video_id = mobj.group('id')
  57         channel_id = mobj.group('channel_id')
  58
  59         video = self._download_json(
  60             'http://www.kanal%splay.se/api/getVideo?format=FLASH&videoId=%s' % (channel_id, video_id),
  61             video_id)
  62
  63         reasons_for_no_streams = video.get('reasonsForNoStreams')
  64         if reasons_for_no_streams:
  65             raise ExtractorError(
  66                 '%s returned error: %s' % (self.IE_NAME, '\n'.join(reasons_for_no_streams)),
  67                 expected=True)
  68
  69         title = video['title']
  70         description = video.get('description')
  71         duration = float_or_none(video.get('length'), 1000)
  72         thumbnail = video.get('posterUrl')
  73
  74         stream_base_url = video['streamBaseUrl']
  75
  76         formats = [{
  77             'url': stream_base_url,
  78             'play_path': stream['source'],
  79             'ext': 'flv',
  80             'tbr': float_or_none(stream.get('bitrate'), 1000),
  81             'rtmp_real_time': True,
  82         } for stream in video['streams']]
  83         self._sort_formats(formats)
  84
  85         subtitles = {}
  86         if video.get('hasSubtitle'):
  87             subtitles = self.extract_subtitles(channel_id, video_id)
  88
  89         return {
  90             'id': video_id,
  91             'title': title,
  92             'description': description,
  93             'thumbnail': thumbnail,
  94             'duration': duration,
  95             'formats': formats,
  96             'subtitles': subtitles,
  97         }