youtube_dl/extractor/dramafever.py

   1 # encoding: 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_urllib_parse,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     clean_html,
  15     int_or_none,
  16     sanitized_Request,
  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, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  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     _TEST = {
  71         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
  72         'info_dict': {
  73             'id': '4512.1',
  74             'ext': 'flv',
  75             'title': 'Cooking with Shin 4512.1',
  76             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
  77             'thumbnail': 're:^https?://.*\.jpg',
  78             'timestamp': 1404336058,
  79             'upload_date': '20140702',
  80             'duration': 343,
  81         },
  82         'params': {
  83             # m3u8 download
  84             'skip_download': True,
  85         },
  86     }
  87
  88     def _real_extract(self, url):
  89         video_id = self._match_id(url).replace('/', '.')
  90
  91         try:
  92             info = self._extract_feed_info(
  93                 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
  94         except ExtractorError as e:
  95             if isinstance(e.cause, compat_HTTPError):
  96                 raise ExtractorError(
  97                     'Currently unavailable in your country.', expected=True)
  98             raise
  99
 100         series_id, episode_number = video_id.split('.')
 101         episode_info = self._download_json(
 102             # We only need a single episode info, so restricting page size to one episode
 103             # and dealing with page number as with episode number
 104             r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
 105             % (self._consumer_secret, series_id, episode_number),
 106             video_id, 'Downloading episode info JSON', fatal=False)
 107         if episode_info:
 108             value = episode_info.get('value')
 109             if isinstance(value, list):
 110                 for v in value:
 111                     if v.get('type') == 'Episode':
 112                         subfile = v.get('subfile') or v.get('new_subfile')
 113                         if subfile and subfile != 'http://www.dramafever.com/st/':
 114                             info.setdefault('subtitles', {}).setdefault('English', []).append({
 115                                 'ext': 'srt',
 116                                 'url': subfile,
 117                             })
 118                         info['episode_number'] = int_or_none(v.get('number'))
 119                         break
 120
 121         return info
 122
 123
 124 class DramaFeverSeriesIE(DramaFeverBaseIE):
 125     IE_NAME = 'dramafever:series'
 126     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 127     _TESTS = [{
 128         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 129         'info_dict': {
 130             'id': '4512',
 131             'title': 'Cooking with Shin',
 132             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 133         },
 134         'playlist_count': 4,
 135     }, {
 136         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 137         'info_dict': {
 138             'id': '124',
 139             'title': 'IRIS',
 140             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 141         },
 142         'playlist_count': 20,
 143     }]
 144
 145     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 146
 147     def _real_extract(self, url):
 148         series_id = self._match_id(url)
 149
 150         series = self._download_json(
 151             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 152             % (self._consumer_secret, series_id),
 153             series_id, 'Downloading series JSON')['series'][series_id]
 154
 155         title = clean_html(series['name'])
 156         description = clean_html(series.get('description') or series.get('description_short'))
 157
 158         entries = []
 159         for page_num in itertools.count(1):
 160             episodes = self._download_json(
 161                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 162                 % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
 163                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 164             for episode in episodes.get('value', []):
 165                 episode_url = episode.get('episode_url')
 166                 if not episode_url:
 167                     continue
 168                 entries.append(self.url_result(
 169                     compat_urlparse.urljoin(url, episode_url),
 170                     'DramaFever', episode.get('guid')))
 171             if page_num == episodes['num_pages']:
 172                 break
 173
 174         return self.playlist_result(entries, series_id, title, description)