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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5
   6 from .amp import AMPIE
   7 from ..compat import (
   8     compat_HTTPError,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     clean_html,
  14     int_or_none,
  15     sanitized_Request,
  16     urlencode_postdata
  17 )
  18
  19
  20 class DramaFeverBaseIE(AMPIE):
  21     _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
  22     _NETRC_MACHINE = 'dramafever'
  23
  24     _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
  25
  26     _consumer_secret = None
  27
  28     def _get_consumer_secret(self):
  29         mainjs = self._download_webpage(
  30             'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
  31             None, 'Downloading main.js', fatal=False)
  32         if not mainjs:
  33             return self._CONSUMER_SECRET
  34         return self._search_regex(
  35             r"var\s+cs\s*=\s*'([^']+)'", mainjs,
  36             'consumer secret', default=self._CONSUMER_SECRET)
  37
  38     def _real_initialize(self):
  39         self._login()
  40         self._consumer_secret = self._get_consumer_secret()
  41
  42     def _login(self):
  43         (username, password) = self._get_login_info()
  44         if username is None:
  45             return
  46
  47         login_form = {
  48             'username': username,
  49             'password': password,
  50         }
  51
  52         request = sanitized_Request(
  53             self._LOGIN_URL, urlencode_postdata(login_form))
  54         response = self._download_webpage(
  55             request, None, 'Logging in as %s' % username)
  56
  57         if all(logout_pattern not in response
  58                for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
  59             error = self._html_search_regex(
  60                 r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
  61                 response, 'error message', default=None)
  62             if error:
  63                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  64             raise ExtractorError('Unable to log in')
  65
  66
  67 class DramaFeverIE(DramaFeverBaseIE):
  68     IE_NAME = 'dramafever'
  69     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
  70     _TESTS = [{
  71         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
  72         'info_dict': {
  73             'id': '4512.1',
  74             'ext': 'mp4',
  75             'title': 'Cooking with Shin 4512.1',
  76             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
  77             'episode': 'Episode 1',
  78             'episode_number': 1,
  79             'thumbnail': r're:^https?://.*\.jpg',
  80             'timestamp': 1404336058,
  81             'upload_date': '20140702',
  82             'duration': 343,
  83         },
  84         'params': {
  85             # m3u8 download
  86             'skip_download': True,
  87         },
  88     }, {
  89         'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
  90         'info_dict': {
  91             'id': '4826.4',
  92             'ext': 'mp4',
  93             'title': 'Mnet Asian Music Awards 2015 4826.4',
  94             'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
  95             'episode': 'Mnet Asian Music Awards 2015 - Part 3',
  96             'episode_number': 4,
  97             'thumbnail': r're:^https?://.*\.jpg',
  98             'timestamp': 1450213200,
  99             'upload_date': '20151215',
 100             'duration': 5602,
 101         },
 102         'params': {
 103             # m3u8 download
 104             'skip_download': True,
 105         },
 106     }, {
 107         'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
 108         'only_matching': True,
 109     }]
 110
 111     def _real_extract(self, url):
 112         video_id = self._match_id(url).replace('/', '.')
 113
 114         try:
 115             info = self._extract_feed_info(
 116                 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
 117         except ExtractorError as e:
 118             if isinstance(e.cause, compat_HTTPError):
 119                 raise ExtractorError(
 120                     'Currently unavailable in your country.', expected=True)
 121             raise
 122
 123         series_id, episode_number = video_id.split('.')
 124         episode_info = self._download_json(
 125             # We only need a single episode info, so restricting page size to one episode
 126             # and dealing with page number as with episode number
 127             r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
 128             % (self._consumer_secret, series_id, episode_number),
 129             video_id, 'Downloading episode info JSON', fatal=False)
 130         if episode_info:
 131             value = episode_info.get('value')
 132             if isinstance(value, list):
 133                 for v in value:
 134                     if v.get('type') == 'Episode':
 135                         subfile = v.get('subfile') or v.get('new_subfile')
 136                         if subfile and subfile != 'http://www.dramafever.com/st/':
 137                             info.setdefault('subtitles', {}).setdefault('English', []).append({
 138                                 'ext': 'srt',
 139                                 'url': subfile,
 140                             })
 141                         episode_number = int_or_none(v.get('number'))
 142                         episode_fallback = 'Episode'
 143                         if episode_number:
 144                             episode_fallback += ' %d' % episode_number
 145                         info['episode'] = v.get('title') or episode_fallback
 146                         info['episode_number'] = episode_number
 147                         break
 148
 149         return info
 150
 151
 152 class DramaFeverSeriesIE(DramaFeverBaseIE):
 153     IE_NAME = 'dramafever:series'
 154     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 155     _TESTS = [{
 156         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 157         'info_dict': {
 158             'id': '4512',
 159             'title': 'Cooking with Shin',
 160             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 161         },
 162         'playlist_count': 4,
 163     }, {
 164         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 165         'info_dict': {
 166             'id': '124',
 167             'title': 'IRIS',
 168             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 169         },
 170         'playlist_count': 20,
 171     }]
 172
 173     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 174
 175     def _real_extract(self, url):
 176         series_id = self._match_id(url)
 177
 178         series = self._download_json(
 179             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 180             % (self._consumer_secret, series_id),
 181             series_id, 'Downloading series JSON')['series'][series_id]
 182
 183         title = clean_html(series['name'])
 184         description = clean_html(series.get('description') or series.get('description_short'))
 185
 186         entries = []
 187         for page_num in itertools.count(1):
 188             episodes = self._download_json(
 189                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 190                 % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
 191                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 192             for episode in episodes.get('value', []):
 193                 episode_url = episode.get('episode_url')
 194                 if not episode_url:
 195                     continue
 196                 entries.append(self.url_result(
 197                     compat_urlparse.urljoin(url, episode_url),
 198                     'DramaFever', episode.get('guid')))
 199             if page_num == episodes['num_pages']:
 200                 break
 201
 202         return self.playlist_result(entries, series_id, title, description)