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     remove_end,
  16     sanitized_Request,
  17     urlencode_postdata
  18 )
  19
  20
  21 class DramaFeverBaseIE(AMPIE):
  22     _LOGIN_URL = 'https://www.dramafever.com/accounts/login/'
  23     _NETRC_MACHINE = 'dramafever'
  24     _GEO_COUNTRIES = ['US', 'CA']
  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 = sanitized_Request(
  55             self._LOGIN_URL, urlencode_postdata(login_form))
  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)<h\d[^>]+\bclass="hidden-xs prompt"[^>]*>(.+?)</h\d',
  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     _TESTS = [{
  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',
  78             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
  79             'episode': 'Episode 1',
  80             'episode_number': 1,
  81             'thumbnail': r're:^https?://.*\.jpg',
  82             'timestamp': 1404336058,
  83             'upload_date': '20140702',
  84             'duration': 344,
  85         },
  86         'params': {
  87             # m3u8 download
  88             'skip_download': True,
  89         },
  90     }, {
  91         'url': 'http://www.dramafever.com/drama/4826/4/Mnet_Asian_Music_Awards_2015/?ap=1',
  92         'info_dict': {
  93             'id': '4826.4',
  94             'ext': 'flv',
  95             'title': 'Mnet Asian Music Awards 2015',
  96             'description': 'md5:3ff2ee8fedaef86e076791c909cf2e91',
  97             'episode': 'Mnet Asian Music Awards 2015 - Part 3',
  98             'episode_number': 4,
  99             'thumbnail': r're:^https?://.*\.jpg',
 100             'timestamp': 1450213200,
 101             'upload_date': '20151215',
 102             'duration': 5359,
 103         },
 104         'params': {
 105             # m3u8 download
 106             'skip_download': True,
 107         },
 108     }, {
 109         'url': 'https://www.dramafever.com/zh-cn/drama/4972/15/Doctor_Romantic/',
 110         'only_matching': True,
 111     }]
 112
 113     def _real_extract(self, url):
 114         video_id = self._match_id(url).replace('/', '.')
 115
 116         try:
 117             info = self._extract_feed_info(
 118                 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id)
 119         except ExtractorError as e:
 120             if isinstance(e.cause, compat_HTTPError):
 121                 self.raise_geo_restricted(
 122                     msg='Currently unavailable in your country',
 123                     countries=self._GEO_COUNTRIES)
 124             raise
 125
 126         # title is postfixed with video id for some reason, removing
 127         if info.get('title'):
 128             info['title'] = remove_end(info['title'], video_id).strip()
 129
 130         series_id, episode_number = video_id.split('.')
 131         episode_info = self._download_json(
 132             # We only need a single episode info, so restricting page size to one episode
 133             # and dealing with page number as with episode number
 134             r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
 135             % (self._consumer_secret, series_id, episode_number),
 136             video_id, 'Downloading episode info JSON', fatal=False)
 137         if episode_info:
 138             value = episode_info.get('value')
 139             if isinstance(value, list):
 140                 for v in value:
 141                     if v.get('type') == 'Episode':
 142                         subfile = v.get('subfile') or v.get('new_subfile')
 143                         if subfile and subfile != 'http://www.dramafever.com/st/':
 144                             info.setdefault('subtitles', {}).setdefault('English', []).append({
 145                                 'ext': 'srt',
 146                                 'url': subfile,
 147                             })
 148                         episode_number = int_or_none(v.get('number'))
 149                         episode_fallback = 'Episode'
 150                         if episode_number:
 151                             episode_fallback += ' %d' % episode_number
 152                         info['episode'] = v.get('title') or episode_fallback
 153                         info['episode_number'] = episode_number
 154                         break
 155
 156         return info
 157
 158
 159 class DramaFeverSeriesIE(DramaFeverBaseIE):
 160     IE_NAME = 'dramafever:series'
 161     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/(?:[^/]+/)?drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 162     _TESTS = [{
 163         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 164         'info_dict': {
 165             'id': '4512',
 166             'title': 'Cooking with Shin',
 167             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 168         },
 169         'playlist_count': 4,
 170     }, {
 171         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 172         'info_dict': {
 173             'id': '124',
 174             'title': 'IRIS',
 175             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 176         },
 177         'playlist_count': 20,
 178     }]
 179
 180     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 181
 182     def _real_extract(self, url):
 183         series_id = self._match_id(url)
 184
 185         series = self._download_json(
 186             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 187             % (self._consumer_secret, series_id),
 188             series_id, 'Downloading series JSON')['series'][series_id]
 189
 190         title = clean_html(series['name'])
 191         description = clean_html(series.get('description') or series.get('description_short'))
 192
 193         entries = []
 194         for page_num in itertools.count(1):
 195             episodes = self._download_json(
 196                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 197                 % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
 198                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 199             for episode in episodes.get('value', []):
 200                 episode_url = episode.get('episode_url')
 201                 if not episode_url:
 202                     continue
 203                 entries.append(self.url_result(
 204                     compat_urlparse.urljoin(url, episode_url),
 205                     'DramaFever', episode.get('guid')))
 206             if page_num == episodes['num_pages']:
 207                 break
 208
 209         return self.playlist_result(entries, series_id, title, description)