youtube_dl/extractor/dramafever.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class DramaFeverIE(InfoExtractor):
  10     IE_NAME = 'dramafever'
  11     _VALID_URL = r'^https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+/[0-9]+)/'
  12     _TESTS = [{
  13         'url': 'http://www.dramafever.com/drama/4512/1/Cooking_with_Shin/',
  14         'info_dict': {
  15             'id': '4512.1',
  16             'ext': 'flv',
  17             'title': 'Cooking with Shin 4512.1',
  18             'upload_date': '20140702',
  19             'description': 'Served at all special occasions and featured in the hit drama Heirs, Shin cooks Red Bean Rice.',
  20         }
  21     }]
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url).replace("/", ".")
  25
  26         consumer_secret = self._get_consumer_secret(video_id)
  27
  28         ep_json = self._download_json(
  29             "http://www.dramafever.com/amp/episode/feed.json?guid=%s" % video_id,
  30             video_id, note='Downloading episode metadata',
  31             errnote="Video may not be available for your location")["channel"]["item"]
  32
  33         title = ep_json["media-group"]["media-title"]
  34         description = ep_json["media-group"]["media-description"]
  35         thumbnail = ep_json["media-group"]["media-thumbnail"]["@attributes"]["url"]
  36         duration = int(ep_json["media-group"]["media-content"][0]["@attributes"]["duration"])
  37         mobj = re.match(r"([0-9]{4})-([0-9]{2})-([0-9]{2})", ep_json["pubDate"])
  38         upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) if mobj is not None else None
  39
  40         formats = []
  41         for vid_format in ep_json["media-group"]["media-content"]:
  42             src = vid_format["@attributes"]["url"]
  43             if '.f4m' in src:
  44                 formats.extend(self._extract_f4m_formats(src, video_id))
  45
  46         self._sort_formats(formats)
  47         video_subtitles = self.extract_subtitles(video_id, consumer_secret)
  48
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'description': description,
  53             'thumbnail': thumbnail,
  54             'upload_date': upload_date,
  55             'duration': duration,
  56             'formats': formats,
  57             'subtitles': video_subtitles,
  58         }
  59
  60     def _get_consumer_secret(self, video_id):
  61         df_js = self._download_webpage(
  62             "http://www.dramafever.com/static/126960d/v2/js/plugins/jquery.threadedcomments.js", video_id)
  63         return self._search_regex(r"'cs': '([0-9a-zA-Z]+)'", df_js, "cs")
  64
  65     def _get_episodes(self, series_id, consumer_secret, episode_filter=None):
  66         _PAGE_SIZE = 60
  67
  68         curr_page = 1
  69         max_pages = curr_page + 1
  70         results = []
  71         while max_pages >= curr_page:
  72             page_url = "http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d" % \
  73                        (consumer_secret, series_id, _PAGE_SIZE, curr_page)
  74             series = self._download_json(
  75                 page_url, series_id, note="Downloading series json page #%d" % curr_page)
  76             max_pages = series['num_pages']
  77             results.extend([ep for ep in series['value'] if episode_filter is None or episode_filter(ep)])
  78             curr_page += 1
  79         return results
  80
  81     def _get_subtitles(self, video_id, consumer_secret):
  82
  83         def match_episode(ep):
  84             return ep['guid'] == video_id
  85
  86         res = None
  87         info = self._get_episodes(
  88             video_id.split(".")[0], consumer_secret, episode_filter=match_episode)
  89         if len(info) == 1 and info[0]['subfile'] != '':
  90             res = {'en': [{'url': info[0]['subfile'], 'ext': 'srt'}]}
  91         return res
  92
  93
  94 class DramaFeverSeriesIE(DramaFeverIE):
  95     IE_NAME = 'dramafever:series'
  96     _VALID_URL = r'^https?://(?:www\.)?dramafever\.com/drama/(?P<id>[0-9]+)/\d*[a-zA-Z_][a-zA-Z0-9_]*/'
  97     _TESTS = [{
  98         'url': 'http://www.dramafever.com/drama/4512/Cooking_with_Shin/',
  99         'info_dict': {
 100             'id': '4512',
 101             'title': 'Cooking with Shin',
 102             'description': 'Professional chef and cooking instructor Shin Kim takes some of the delicious dishes featured in your favorite dramas and shows you how to make them right at home.',
 103         },
 104         'playlist_count': 4,
 105     }, {
 106         'url': 'http://www.dramafever.com/drama/124/IRIS/',
 107         'info_dict': {
 108             'id': '124',
 109             'title': 'IRIS',
 110             'description': 'Lee Byung Hun and Kim Tae Hee star in this powerhouse drama and ratings megahit of action, intrigue and romance.',
 111         },
 112         'playlist_count': 20,
 113     }]
 114
 115     def _real_extract(self, url):
 116         series_id = self._match_id(url)
 117         consumer_secret = self._get_consumer_secret(series_id)
 118
 119         series_json = self._download_json(
 120             "http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s" % (consumer_secret, series_id),
 121             series_id, note='Downloading series metadata')["series"][series_id]
 122
 123         title = series_json["name"]
 124         description = series_json["description_short"]
 125
 126         episodes = self._get_episodes(series_id, consumer_secret)
 127         entries = []
 128         for ep in episodes:
 129             entries.append(self.url_result(
 130                 'http://www.dramafever.com%s' % ep['episode_url'], 'DramaFever', ep['guid']))
 131         return self.playlist_result(entries, series_id, title, description)