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_urllib_request,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     ExtractorError,
  15     clean_html,
  16     determine_ext,
  17     int_or_none,
  18     parse_iso8601,
  19 )
  20
  21
  22 class DramaFeverBaseIE(AMPIE):
  23     _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
  24     _NETRC_MACHINE = 'dramafever'
  25
  26     _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
  27
  28     _consumer_secret = None
  29
  30     def _get_consumer_secret(self):
  31         mainjs = self._download_webpage(
  32             'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
  33             None, 'Downloading main.js', fatal=False)
  34         if not mainjs:
  35             return self._CONSUMER_SECRET
  36         return self._search_regex(
  37             r"var\s+cs\s*=\s*'([^']+)'", mainjs,
  38             'consumer secret', default=self._CONSUMER_SECRET)
  39
  40     def _real_initialize(self):
  41         self._login()
  42         self._consumer_secret = self._get_consumer_secret()
  43
  44     def _login(self):
  45         (username, password) = self._get_login_info()
  46         if username is None:
  47             return
  48
  49         login_form = {
  50             'username': username,
  51             'password': password,
  52         }
  53
  54         request = compat_urllib_request.Request(
  55             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
  56         response = self._download_webpage(
  57             request, None, 'Logging in as %s' % username)
  58
  59         if all(logout_pattern not in response
  60                for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
  61             error = self._html_search_regex(
  62                 r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
  63                 response, 'error message', default=None)
  64             if error:
  65                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  66             raise ExtractorError('Unable to log in')
  67
  68
  69 class DramaFeverIE(DramaFeverBaseIE):
  70     IE_NAME = 'dramafever'
  71     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
  72     _TEST = {
  73         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
  74         'info_dict': {
  75             'id': '4512.1',
  76             'ext': 'flv',
  77             'title': 'Cooking with Shin 4512.1',
  78             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
  79             'thumbnail': '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
  90     def _real_extract(self, url):
  91         video_id = self._match_id(url).replace('/', '.')
  92
  93         try:
  94             info = self._extract_feed_info('http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
  95         except ExtractorError as e:
  96             if isinstance(e.cause, compat_HTTPError):
  97                 raise ExtractorError(
  98                     'Currently unavailable in your country.', expected=True)
  99             raise
 100
 101         series_id, episode_number = video_id.split('.')
 102         episode_info = self._download_json(
 103             # We only need a single episode info, so restricting page size to one episode
 104             # and dealing with page number as with episode number
 105             r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
 106             % (self._consumer_secret, series_id, episode_number),
 107             video_id, 'Downloading episode info JSON', fatal=False)
 108         if episode_info:
 109             value = episode_info.get('value')
 110             if value:
 111                 subfile = value[0].get('subfile') or value[0].get('new_subfile')
 112                 if subfile and subfile != 'http://www.dramafever.com/st/':
 113                     info['subtitiles'].setdefault('English', []).append({
 114                         'ext': 'srt',
 115                         'url': subfile,
 116                     })
 117
 118         return info
 119
 120
 121 class DramaFeverSeriesIE(DramaFeverBaseIE):
 122     IE_NAME = 'dramafever:series'
 123     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 124     _TESTS = [{
 125         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 126         'info_dict': {
 127             'id': '4512',
 128             'title': 'Cooking with Shin',
 129             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 130         },
 131         'playlist_count': 4,
 132     }, {
 133         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 134         'info_dict': {
 135             'id': '124',
 136             'title': 'IRIS',
 137             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 138         },
 139         'playlist_count': 20,
 140     }]
 141
 142     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 143
 144     def _real_extract(self, url):
 145         series_id = self._match_id(url)
 146
 147         series = self._download_json(
 148             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 149             % (self._consumer_secret, series_id),
 150             series_id, 'Downloading series JSON')['series'][series_id]
 151
 152         title = clean_html(series['name'])
 153         description = clean_html(series.get('description') or series.get('description_short'))
 154
 155         entries = []
 156         for page_num in itertools.count(1):
 157             episodes = self._download_json(
 158                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 159                 % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
 160                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 161             for episode in episodes.get('value', []):
 162                 episode_url = episode.get('episode_url')
 163                 if not episode_url:
 164                     continue
 165                 entries.append(self.url_result(
 166                     compat_urlparse.urljoin(url, episode_url),
 167                     'DramaFever', episode.get('guid')))
 168             if page_num == episodes['num_pages']:
 169                 break
 170
 171         return self.playlist_result(entries, series_id, title, description)