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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5
   6 from .common import InfoExtractor
   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     determine_ext,
  16     int_or_none,
  17     parse_iso8601,
  18     sanitized_Request,
  19 )
  20
  21
  22 class DramaFeverBaseIE(InfoExtractor):
  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 = sanitized_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     }
  85
  86     def _real_extract(self, url):
  87         video_id = self._match_id(url).replace('/', '.')
  88
  89         try:
  90             feed = self._download_json(
  91                 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
  92                 video_id, 'Downloading episode JSON')['channel']['item']
  93         except ExtractorError as e:
  94             if isinstance(e.cause, compat_HTTPError):
  95                 raise ExtractorError(
  96                     'Currently unavailable in your country.', expected=True)
  97             raise
  98
  99         media_group = feed.get('media-group', {})
 100
 101         formats = []
 102         for media_content in media_group['media-content']:
 103             src = media_content.get('@attributes', {}).get('url')
 104             if not src:
 105                 continue
 106             ext = determine_ext(src)
 107             if ext == 'f4m':
 108                 formats.extend(self._extract_f4m_formats(
 109                     src, video_id, f4m_id='hds'))
 110             elif ext == 'm3u8':
 111                 formats.extend(self._extract_m3u8_formats(
 112                     src, video_id, 'mp4', m3u8_id='hls'))
 113             else:
 114                 formats.append({
 115                     'url': src,
 116                 })
 117         self._sort_formats(formats)
 118
 119         title = media_group.get('media-title')
 120         description = media_group.get('media-description')
 121         duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
 122         thumbnail = self._proto_relative_url(
 123             media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
 124         timestamp = parse_iso8601(feed.get('pubDate'), ' ')
 125
 126         subtitles = {}
 127         for media_subtitle in media_group.get('media-subTitle', []):
 128             lang = media_subtitle.get('@attributes', {}).get('lang')
 129             href = media_subtitle.get('@attributes', {}).get('href')
 130             if not lang or not href:
 131                 continue
 132             subtitles[lang] = [{
 133                 'ext': 'ttml',
 134                 'url': href,
 135             }]
 136
 137         series_id, episode_number = video_id.split('.')
 138         episode_info = self._download_json(
 139             # We only need a single episode info, so restricting page size to one episode
 140             # and dealing with page number as with episode number
 141             r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1'
 142             % (self._consumer_secret, series_id, episode_number),
 143             video_id, 'Downloading episode info JSON', fatal=False)
 144         if episode_info:
 145             value = episode_info.get('value')
 146             if value:
 147                 subfile = value[0].get('subfile') or value[0].get('new_subfile')
 148                 if subfile and subfile != 'http://www.dramafever.com/st/':
 149                     subtitles.setdefault('English', []).append({
 150                         'ext': 'srt',
 151                         'url': subfile,
 152                     })
 153
 154         return {
 155             'id': video_id,
 156             'title': title,
 157             'description': description,
 158             'thumbnail': thumbnail,
 159             'timestamp': timestamp,
 160             'duration': duration,
 161             'formats': formats,
 162             'subtitles': subtitles,
 163         }
 164
 165
 166 class DramaFeverSeriesIE(DramaFeverBaseIE):
 167     IE_NAME = 'dramafever:series'
 168     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 169     _TESTS = [{
 170         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 171         'info_dict': {
 172             'id': '4512',
 173             'title': 'Cooking with Shin',
 174             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 175         },
 176         'playlist_count': 4,
 177     }, {
 178         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 179         'info_dict': {
 180             'id': '124',
 181             'title': 'IRIS',
 182             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 183         },
 184         'playlist_count': 20,
 185     }]
 186
 187     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 188
 189     def _real_extract(self, url):
 190         series_id = self._match_id(url)
 191
 192         series = self._download_json(
 193             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 194             % (self._consumer_secret, series_id),
 195             series_id, 'Downloading series JSON')['series'][series_id]
 196
 197         title = clean_html(series['name'])
 198         description = clean_html(series.get('description') or series.get('description_short'))
 199
 200         entries = []
 201         for page_num in itertools.count(1):
 202             episodes = self._download_json(
 203                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 204                 % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num),
 205                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 206             for episode in episodes.get('value', []):
 207                 episode_url = episode.get('episode_url')
 208                 if not episode_url:
 209                     continue
 210                 entries.append(self.url_result(
 211                     compat_urlparse.urljoin(url, episode_url),
 212                     'DramaFever', episode.get('guid')))
 213             if page_num == episodes['num_pages']:
 214                 break
 215
 216         return self.playlist_result(entries, series_id, title, description)