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     _GEO_COUNTRIES = ['US', 'CA']
  24
  25     _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
  26
  27     _consumer_secret = None
  28
  29     def _get_consumer_secret(self):
  30         mainjs = self._download_webpage(
  31             'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
  32             None, 'Downloading main.js', fatal=False)
  33         if not mainjs:
  34             return self._CONSUMER_SECRET
  35         return self._search_regex(
  36             r"var\s+cs\s*=\s*'([^']+)'", mainjs,
  37             'consumer secret', default=self._CONSUMER_SECRET)
  38
  39     def _real_initialize(self):
  40         self._login()
  41         self._consumer_secret = self._get_consumer_secret()
  42
  43     def _login(self):
  44         (username, password) = self._get_login_info()
  45         if username is None:
  46             return
  47
  48         login_form = {
  49             'username': username,
  50             'password': password,
  51         }
  52
  53         request = sanitized_Request(
  54             self._LOGIN_URL, urlencode_postdata(login_form))
  55         response = self._download_webpage(
  56             request, None, 'Logging in as %s' % username)
  57
  58         if all(logout_pattern not in response
  59                for logout_pattern in ['href="/accounts/logout/"', '>Log out<']):
  60             error = self._html_search_regex(
  61                 r'(?s)class="hidden-xs prompt"[^>]*>(.+?)<',
  62                 response, 'error message', default=None)
  63             if error:
  64                 raise ExtractorError('Unable to login: %s' % error, expected=True)
  65             raise ExtractorError('Unable to log in')
  66
  67
  68 class DramaFeverIE(DramaFeverBaseIE):
  69     IE_NAME = 'dramafever'
  70     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+/[0-9]+)(?:/|$)'
  71     _TESTS = [{
  72         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
  73         'info_dict': {
  74             'id': '4512.1',
  75             'ext': 'mp4',
  76             'title': 'Cooking with Shin 4512.1',
  77             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
  78             'episode': 'Episode 1',
  79             'episode_number': 1,
  80             'thumbnail': r're:^https?://.*\.jpg',
  81             'timestamp': 1404336058,
  82             'upload_date': '20140702',
  83             'duration': 343,
  84         },
  85         'params': {
  86             # m3u8 download
  87             'skip_download': True,
  88         },
  89     }, {
  90         'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
  91         'info_dict': {
  92             'id': '4826.4',
  93             'ext': 'mp4',
  94             'title': 'Mnet Asian Music Awards 2015 4826.4',
  95             'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
  96             'episode': 'Mnet Asian Music Awards 2015 - Part 3',
  97             'episode_number': 4,
  98             'thumbnail': r're:^https?://.*\.jpg',
  99             'timestamp': 1450213200,
 100             'upload_date': '20151215',
 101             'duration': 5602,
 102         },
 103         'params': {
 104             # m3u8 download
 105             'skip_download': True,
 106         },
 107     }, {
 108         'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
 109         'only_matching': True,
 110     }]
 111
 112     def _real_extract(self, url):
 113         video_id = self._match_id(url).replace('/', '.')
 114
 115         try:
 116             info = self._extract_feed_info(
 117                 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
 118         except ExtractorError as e:
 119             if isinstance(e.cause, compat_HTTPError):
 120                 self.raise_geo_restricted(
 121                     msg='Currently unavailable in your country',
 122                     countries=self._GEO_COUNTRIES)
 123             raise
 124
 125         series_id, episode_number = video_id.split('.')
 126         episode_info = self._download_json(
 127             # We only need a single episode info, so restricting page size to one episode
 128             # and dealing with page number as with episode number
 129             r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
 130             % (self._consumer_secret, series_id, episode_number),
 131             video_id, 'Downloading episode info JSON', fatal=False)
 132         if episode_info:
 133             value = episode_info.get('value')
 134             if isinstance(value, list):
 135                 for v in value:
 136                     if v.get('type') == 'Episode':
 137                         subfile = v.get('subfile') or v.get('new_subfile')
 138                         if subfile and subfile != 'http://www.dramafever.com/st/':
 139                             info.setdefault('subtitles', {}).setdefault('English', []).append({
 140                                 'ext': 'srt',
 141                                 'url': subfile,
 142                             })
 143                         episode_number = int_or_none(v.get('number'))
 144                         episode_fallback = 'Episode'
 145                         if episode_number:
 146                             episode_fallback += ' %d' % episode_number
 147                         info['episode'] = v.get('title') or episode_fallback
 148                         info['episode_number'] = episode_number
 149                         break
 150
 151         return info
 152
 153
 154 class DramaFeverSeriesIE(DramaFeverBaseIE):
 155     IE_NAME = 'dramafever:series'
 156     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 157     _TESTS = [{
 158         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 159         'info_dict': {
 160             'id': '4512',
 161             'title': 'Cooking with Shin',
 162             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 163         },
 164         'playlist_count': 4,
 165     }, {
 166         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 167         'info_dict': {
 168             'id': '124',
 169             'title': 'IRIS',
 170             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 171         },
 172         'playlist_count': 20,
 173     }]
 174
 175     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 176
 177     def _real_extract(self, url):
 178         series_id = self._match_id(url)
 179
 180         series = self._download_json(
 181             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 182             % (self._consumer_secret, series_id),
 183             series_id, 'Downloading series JSON')['series'][series_id]
 184
 185         title = clean_html(series['name'])
 186         description = clean_html(series.get('description') or series.get('description_short'))
 187
 188         entries = []
 189         for page_num in itertools.count(1):
 190             episodes = self._download_json(
 191                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 192                 % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
 193                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 194             for episode in episodes.get('value', []):
 195                 episode_url = episode.get('episode_url')
 196                 if not episode_url:
 197                     continue
 198                 entries.append(self.url_result(
 199                     compat_urlparse.urljoin(url, episode_url),
 200                     'DramaFever', episode.get('guid')))
 201             if page_num == episodes['num_pages']:
 202                 break
 203
 204         return self.playlist_result(entries, series_id, title, description)