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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     float_or_none,
  14     parse_duration,
  15     str_to_int,
  16     urlencode_postdata,
  17 )
  18
  19
  20 class PandoraTVIE(InfoExtractor):
  21     IE_NAME = 'pandora.tv'
  22     IE_DESC = '판도라TV'
  23     _VALID_URL = r'''(?x)
  24                         https?://
  25                             (?:
  26                                 (?:www\.)?pandora\.tv/view/(?P<user_id>[^/]+)/(?P<id>\d+)|  # new format
  27                                 (?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?|        # old format
  28                                 m\.pandora\.tv/?\?                                          # mobile
  29                             )
  30                     '''
  31     _TESTS = [{
  32         'url': 'http://jp.channel.pandora.tv/channel/video.ptv?c1=&prgid=53294230&ch_userid=mikakim&ref=main&lot=cate_01_2',
  33         'info_dict': {
  34             'id': '53294230',
  35             'ext': 'flv',
  36             'title': '頭を撫でてくれる？',
  37             'description': '頭を撫でてくれる？',
  38             'thumbnail': r're:^https?://.*\.jpg$',
  39             'duration': 39,
  40             'upload_date': '20151218',
  41             'uploader': 'カワイイ動物まとめ',
  42             'uploader_id': 'mikakim',
  43             'view_count': int,
  44             'like_count': int,
  45         }
  46     }, {
  47         'url': 'http://channel.pandora.tv/channel/video.ptv?ch_userid=gogoucc&prgid=54721744',
  48         'info_dict': {
  49             'id': '54721744',
  50             'ext': 'flv',
  51             'title': '[HD] JAPAN COUNTDOWN 170423',
  52             'description': '[HD] JAPAN COUNTDOWN 170423',
  53             'thumbnail': r're:^https?://.*\.jpg$',
  54             'duration': 1704.9,
  55             'upload_date': '20170423',
  56             'uploader': 'GOGO_UCC',
  57             'uploader_id': 'gogoucc',
  58             'view_count': int,
  59             'like_count': int,
  60         },
  61         'params': {
  62             # Test metadata only
  63             'skip_download': True,
  64         },
  65     }, {
  66         'url': 'http://www.pandora.tv/view/mikakim/53294230#36797454_new',
  67         'only_matching': True,
  68     }, {
  69         'url': 'http://m.pandora.tv/?c=view&ch_userid=mikakim&prgid=54600346',
  70         'only_matching': True,
  71     }]
  72
  73     def _real_extract(self, url):
  74         mobj = re.match(self._VALID_URL, url)
  75         user_id = mobj.group('user_id')
  76         video_id = mobj.group('id')
  77
  78         if not user_id or not video_id:
  79             qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  80             video_id = qs.get('prgid', [None])[0]
  81             user_id = qs.get('ch_userid', [None])[0]
  82             if any(not f for f in (video_id, user_id,)):
  83                 raise ExtractorError('Invalid URL', expected=True)
  84
  85         data = self._download_json(
  86             'http://m.pandora.tv/?c=view&m=viewJsonApi&ch_userid=%s&prgid=%s'
  87             % (user_id, video_id), video_id)
  88
  89         info = data['data']['rows']['vod_play_info']['result']
  90
  91         formats = []
  92         for format_id, format_url in info.items():
  93             if not format_url:
  94                 continue
  95             height = self._search_regex(
  96                 r'^v(\d+)[Uu]rl$', format_id, 'height', default=None)
  97             if not height:
  98                 continue
  99
 100             play_url = self._download_json(
 101                 'http://m.pandora.tv/?c=api&m=play_url', video_id,
 102                 data=urlencode_postdata({
 103                     'prgid': video_id,
 104                     'runtime': info.get('runtime'),
 105                     'vod_url': format_url,
 106                 }),
 107                 headers={
 108                     'Origin': url,
 109                     'Content-Type': 'application/x-www-form-urlencoded',
 110                 })
 111             format_url = play_url.get('url')
 112             if not format_url:
 113                 continue
 114
 115             formats.append({
 116                 'format_id': '%sp' % height,
 117                 'url': format_url,
 118                 'height': int(height),
 119             })
 120         self._sort_formats(formats)
 121
 122         return {
 123             'id': video_id,
 124             'title': info['subject'],
 125             'description': info.get('body'),
 126             'thumbnail': info.get('thumbnail') or info.get('poster'),
 127             'duration': float_or_none(info.get('runtime'), 1000) or parse_duration(info.get('time')),
 128             'upload_date': info['fid'].split('/')[-1][:8] if isinstance(info.get('fid'), compat_str) else None,
 129             'uploader': info.get('nickname'),
 130             'uploader_id': info.get('upload_userid'),
 131             'view_count': str_to_int(info.get('hit')),
 132             'like_count': str_to_int(info.get('likecnt')),
 133             'formats': formats,
 134         }