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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import time
   6 import hashlib
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     compat_urllib_request,
  11     compat_urllib_parse,
  12     ExtractorError,
  13     clean_html,
  14     unified_strdate,
  15     compat_str,
  16 )
  17
  18
  19 class NocoIE(InfoExtractor):
  20     _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
  21     _LOGIN_URL = 'http://noco.tv/do.php'
  22     _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
  23     _NETRC_MACHINE = 'noco'
  24
  25     _TEST = {
  26         'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
  27         'md5': '0a993f0058ddbcd902630b2047ef710e',
  28         'info_dict': {
  29             'id': '11538',
  30             'ext': 'mp4',
  31             'title': 'Ami Ami Idol - Hello! France',
  32             'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86',
  33             'upload_date': '20140412',
  34             'uploader': 'Nolife',
  35             'uploader_id': 'NOL',
  36             'duration': 2851.2,
  37         },
  38         'skip': 'Requires noco account',
  39     }
  40
  41     def _real_initialize(self):
  42         self._login()
  43
  44     def _login(self):
  45         (username, password) = self._get_login_info()
  46         if username is None:
  47             return
  48
  49         login_form = {
  50             'a': 'login',
  51             'cookie': '1',
  52             'username': username,
  53             'password': password,
  54         }
  55         request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
  56         request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
  57
  58         login = self._download_json(request, None, 'Logging in as %s' % username)
  59
  60         if 'erreur' in login:
  61             raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
  62
  63     def _call_api(self, path, video_id, note):
  64         ts = compat_str(int(time.time() * 1000))
  65         tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
  66         url = self._API_URL_TEMPLATE % (path, ts, tk)
  67
  68         resp = self._download_json(url, video_id, note)
  69
  70         if isinstance(resp, dict) and resp.get('error'):
  71             self._raise_error(resp['error'], resp['description'])
  72
  73         return resp
  74
  75     def _raise_error(self, error, description):
  76         raise ExtractorError(
  77             '%s returned error: %s - %s' % (self.IE_NAME, error, description),
  78             expected=True)
  79
  80     def _real_extract(self, url):
  81         mobj = re.match(self._VALID_URL, url)
  82         video_id = mobj.group('id')
  83
  84         medias = self._call_api(
  85             'shows/%s/medias' % video_id,
  86             video_id, 'Downloading video JSON')
  87
  88         qualities = self._call_api(
  89             'qualities',
  90             video_id, 'Downloading qualities JSON')
  91
  92         formats = []
  93
  94         for format_id, fmt in medias['fr']['video_list']['none']['quality_list'].items():
  95
  96             video = self._call_api(
  97                 'shows/%s/video/%s/fr' % (video_id, format_id.lower()),
  98                 video_id, 'Downloading %s video JSON' % format_id)
  99
 100             file_url = video['file']
 101             if not file_url:
 102                 continue
 103
 104             if file_url in ['forbidden', 'not found']:
 105                 popmessage = video['popmessage']
 106                 self._raise_error(popmessage['title'], popmessage['message'])
 107
 108             formats.append({
 109                 'url': file_url,
 110                 'format_id': format_id,
 111                 'width': fmt['res_width'],
 112                 'height': fmt['res_lines'],
 113                 'abr': fmt['audiobitrate'],
 114                 'vbr': fmt['videobitrate'],
 115                 'filesize': fmt['filesize'],
 116                 'format_note': qualities[format_id]['quality_name'],
 117                 'preference': qualities[format_id]['priority'],
 118             })
 119
 120         self._sort_formats(formats)
 121
 122         show = self._call_api(
 123             'shows/by_id/%s' % video_id,
 124             video_id, 'Downloading show JSON')[0]
 125
 126         upload_date = unified_strdate(show['online_date_start_utc'])
 127         uploader = show['partner_name']
 128         uploader_id = show['partner_key']
 129         duration = show['duration_ms'] / 1000.0
 130
 131         thumbnails = []
 132         for thumbnail_key, thumbnail_url in show.items():
 133             m = re.search(r'^screenshot_(?P<width>\d+)x(?P<height>\d+)$', thumbnail_key)
 134             if not m:
 135                 continue
 136             thumbnails.append({
 137                 'url': thumbnail_url,
 138                 'width': int(m.group('width')),
 139                 'height': int(m.group('height')),
 140             })
 141
 142         episode = show.get('show_TT') or show.get('show_OT')
 143         family = show.get('family_TT') or show.get('family_OT')
 144         episode_number = show.get('episode_number')
 145
 146         title = ''
 147         if family:
 148             title += family
 149         if episode_number:
 150             title += ' #' + compat_str(episode_number)
 151         if episode:
 152             title += ' - ' + episode
 153
 154         description = show.get('show_resume') or show.get('family_resume')
 155
 156         return {
 157             'id': video_id,
 158             'title': title,
 159             'description': description,
 160             'thumbnails': thumbnails,
 161             'upload_date': upload_date,
 162             'uploader': uploader,
 163             'uploader_id': uploader_id,
 164             'duration': duration,
 165             'formats': formats,
 166         }