_ Git - youtube-dl/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_urlparse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     clean_html,
  14     determine_ext,
  15     int_or_none,
  16     parse_iso8601,
  17 )
  18
  19
  20 class DramaFeverIE(InfoExtractor):
  21     IE_NAME = 'dramafever'
  22     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)'
  23     _TEST = {
  24         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
  25         'info_dict': {
  26             'id': '4512.1',
  27             'ext': 'flv',
  28             'title': 'Cooking with Shin 4512.1',
  29             'description': 'md5:a8eec7942e1664a6896fcd5e1287bfd0',
  30             'thumbnail': 're:^https?://.*\.jpg',
  31             'timestamp': 1404336058,
  32             'upload_date': '20140702',
  33             'duration': 343,
  34         }
  35     }
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url).replace('/', '.')
  39
  40         try:
  41             feed = self._download_json(
  42                 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id,
  43                 video_id, 'Downloading episode JSON')['channel']['item']
  44         except ExtractorError as e:
  45             if isinstance(e.cause, compat_HTTPError):
  46                 raise ExtractorError(
  47                     'Currently unavailable in your country.', expected=True)
  48             raise
  49
  50         media_group = feed.get('media-group', {})
  51
  52         formats = []
  53         for media_content in media_group['media-content']:
  54             src = media_content.get('@attributes', {}).get('url')
  55             if not src:
  56                 continue
  57             ext = determine_ext(src)
  58             if ext == 'f4m':
  59                 formats.extend(self._extract_f4m_formats(
  60                     src, video_id, f4m_id='hds'))
  61             elif ext == 'm3u8':
  62                 formats.extend(self._extract_m3u8_formats(
  63                     src, video_id, 'mp4', m3u8_id='hls'))
  64             else:
  65                 formats.append({
  66                     'url': src,
  67                 })
  68         self._sort_formats(formats)
  69
  70         title = media_group.get('media-title')
  71         description = media_group.get('media-description')
  72         duration = int_or_none(media_group['media-content'][0].get('@attributes', {}).get('duration'))
  73         thumbnail = self._proto_relative_url(
  74             media_group.get('media-thumbnail', {}).get('@attributes', {}).get('url'))
  75         timestamp = parse_iso8601(feed.get('pubDate'), ' ')
  76
  77         subtitles = {}
  78         for media_subtitle in media_group.get('media-subTitle', []):
  79             lang = media_subtitle.get('@attributes', {}).get('lang')
  80             href = media_subtitle.get('@attributes', {}).get('href')
  81             if not lang or not href:
  82                 continue
  83             subtitles[lang] = [{
  84                 'ext': 'ttml',
  85                 'url': href,
  86             }]
  87
  88         return {
  89             'id': video_id,
  90             'title': title,
  91             'description': description,
  92             'thumbnail': thumbnail,
  93             'timestamp': timestamp,
  94             'duration': duration,
  95             'formats': formats,
  96             'subtitles': subtitles,
  97         }
  98
  99
 100 class DramaFeverSeriesIE(InfoExtractor):
 101     IE_NAME = 'dramafever:series'
 102     _VALID_URL = r'https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)(?:/(?:(?!\d+(?:/|$)).+)?)?$'
 103     _TESTS = [{
 104         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
 105         'info_dict': {
 106             'id': '4512',
 107             'title': 'Cooking with Shin',
 108             'description': 'md5:84a3f26e3cdc3fb7f500211b3593b5c1',
 109         },
 110         'playlist_count': 4,
 111     }, {
 112         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 113         'info_dict': {
 114             'id': '124',
 115             'title': 'IRIS',
 116             'description': 'md5:b3a30e587cf20c59bd1c01ec0ee1b862',
 117         },
 118         'playlist_count': 20,
 119     }]
 120
 121     _CONSUMER_SECRET = 'DA59dtVXYLxajktV'
 122     _PAGE_SIZE = 60  # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-)
 123
 124     def _get_consumer_secret(self, video_id):
 125         mainjs = self._download_webpage(
 126             'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js',
 127             video_id, 'Downloading main.js', fatal=False)
 128         if not mainjs:
 129             return self._CONSUMER_SECRET
 130         return self._search_regex(
 131             r"var\s+cs\s*=\s*'([^']+)'", mainjs,
 132             'consumer secret', default=self._CONSUMER_SECRET)
 133
 134     def _real_extract(self, url):
 135         series_id = self._match_id(url)
 136
 137         consumer_secret = self._get_consumer_secret(series_id)
 138
 139         series = self._download_json(
 140             'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s'
 141             % (consumer_secret, series_id),
 142             series_id, 'Downloading series JSON')['series'][series_id]
 143
 144         title = clean_html(series['name'])
 145         description = clean_html(series.get('description') or series.get('description_short'))
 146
 147         entries = []
 148         for page_num in itertools.count(1):
 149             episodes = self._download_json(
 150                 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d'
 151                 % (consumer_secret, series_id, self._PAGE_SIZE, page_num),
 152                 series_id, 'Downloading episodes JSON page #%d' % page_num)
 153             for episode in episodes.get('value', []):
 154                 entries.append(self.url_result(
 155                     compat_urlparse.urljoin(url, episode['episode_url']),
 156                     'DramaFever', episode.get('guid')))
 157             if page_num == episodes['num_pages']:
 158                 break
 159
 160         return self.playlist_result(entries, series_id, title, description)