_ Git - youtube-dl/blob - youtube_dl/extractor/noco.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10     ExtractorError,
  11     clean_html,
  12     unified_strdate,
  13     compat_str,
  14 )
  15
  16
  17 class NocoIE(InfoExtractor):
  18     _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
  19     _LOGIN_URL = 'http://noco.tv/do.php'
  20     _NETRC_MACHINE = 'noco'
  21
  22     _TEST = {
  23         'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
  24         'md5': '0a993f0058ddbcd902630b2047ef710e',
  25         'info_dict': {
  26             'id': '11538',
  27             'ext': 'mp4',
  28             'title': 'Ami Ami Idol - Hello! France',
  29             'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86',
  30             'upload_date': '20140412',
  31             'uploader': 'Nolife',
  32             'uploader_id': 'NOL',
  33             'duration': 2851.2,
  34         },
  35         'skip': 'Requires noco account',
  36     }
  37
  38     def _real_initialize(self):
  39         self._login()
  40
  41     def _login(self):
  42         (username, password) = self._get_login_info()
  43         if username is None:
  44             return
  45
  46         login_form = {
  47             'a': 'login',
  48             'cookie': '1',
  49             'username': username,
  50             'password': password,
  51         }
  52         request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
  53         request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
  54
  55         login = self._download_json(request, None, 'Logging in as %s' % username)
  56
  57         if 'erreur' in login:
  58             raise  ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
  59
  60     def _real_extract(self, url):
  61         mobj = re.match(self._VALID_URL, url)
  62         video_id = mobj.group('id')
  63
  64         medias = self._download_json(
  65             'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
  66
  67         formats = []
  68
  69         for fmt in medias['fr']['video_list']['default']['quality_list']:
  70             format_id = fmt['quality_key']
  71
  72             file = self._download_json(
  73                 'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
  74                 video_id, 'Downloading %s video JSON' % format_id)
  75
  76             file_url = file['file']
  77             if not file_url:
  78                 continue
  79
  80             if file_url == 'forbidden':
  81                 raise ExtractorError(
  82                     '%s returned error: %s - %s' % (
  83                         self.IE_NAME, file['popmessage']['title'], file['popmessage']['message']),
  84                     expected=True)
  85
  86             formats.append({
  87                 'url': file_url,
  88                 'format_id': format_id,
  89                 'width': fmt['res_width'],
  90                 'height': fmt['res_lines'],
  91                 'abr': fmt['audiobitrate'],
  92                 'vbr': fmt['videobitrate'],
  93                 'filesize': fmt['filesize'],
  94                 'format_note': fmt['quality_name'],
  95                 'preference': fmt['priority'],
  96             })
  97
  98         self._sort_formats(formats)
  99
 100         show = self._download_json(
 101             'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
 102
 103         upload_date = unified_strdate(show['indexed'])
 104         uploader = show['partner_name']
 105         uploader_id = show['partner_key']
 106         duration = show['duration_ms'] / 1000.0
 107         thumbnail = show['screenshot']
 108
 109         episode = show.get('show_TT') or show.get('show_OT')
 110         family = show.get('family_TT') or show.get('family_OT')
 111         episode_number = show.get('episode_number')
 112
 113         title = ''
 114         if family:
 115             title += family
 116         if episode_number:
 117             title += ' #' + compat_str(episode_number)
 118         if episode:
 119             title += ' - ' + episode
 120
 121         description = show.get('show_resume') or show.get('family_resume')
 122
 123         return {
 124             'id': video_id,
 125             'title': title,
 126             'description': description,
 127             'thumbnail': thumbnail,
 128             'upload_date': upload_date,
 129             'uploader': uploader,
 130             'uploader_id': uploader_id,
 131             'duration': duration,
 132             'formats': formats,
 133         }