From b0d619fde2b187f2b36b077a1eb11d766429f88c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 20 May 2015 21:28:04 +0600 Subject: [PATCH] [viki:channel] Extract title from JSON --- youtube_dl/extractor/viki.py | 40 +++++++++++++++++++++--------------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 9bdbdc3e4..fc585c299 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -23,7 +23,7 @@ class VikiIE(InfoExtractor): # iPad2 _USER_AGENT = 'Mozilla/5.0(iPad; U; CPU OS 4_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8F191 Safari/6533.18.5' - _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P[0-9]+v)' + _VALID_URL = r'https?://(?:www\.)?viki\.com/videos/(?P[0-9]+v)' _TESTS = [{ 'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14', 'info_dict': { @@ -149,7 +149,7 @@ def _get_subtitles(self, video_id, info_webpage): class VikiChannelIE(InfoExtractor): IE_NAME = 'viki:channel' - _VALID_URL = r'^https?://(?:www\.)?viki\.com/tv/(?P[0-9]+c)' + _VALID_URL = r'https?://(?:www\.)?viki\.com/tv/(?P[0-9]+c)' _TESTS = [{ 'url': 'http://www.viki.com/tv/50c-boys-over-flowers', 'info_dict': { @@ -167,27 +167,35 @@ class VikiChannelIE(InfoExtractor): }, 'playlist_count': 127, }] + _API_BASE = 'http://api.viki.io/v4/containers' + _APP = '100000a' _PER_PAGE = 25 def _real_extract(self, url): - show_id = self._match_id(url) - show_page = self._download_webpage(url, show_id, 'Download show page') + channel_id = self._match_id(url) - title = self._og_search_title(show_page) - description = self._og_search_description(show_page) + channel = self._download_json( + '%s/%s.json?app=%s' % (self._API_BASE, channel_id, self._APP), + channel_id, 'Downloading channel JSON') + + titles = channel['titles'] + title = titles.get('en') or titles[titles.keys()[0]] + + descriptions = channel['descriptions'] + description = descriptions.get('en') or descriptions[descriptions.keys()[0]] entries = [] - for video_type in ['episodes', 'clips']: - json_url = 'http://api.viki.io/v4/containers/%s/%s.json?app=100000a&per_page=%d&sort=number&direction=asc&with_paging=true&page=1' % (show_id, video_type, self._PER_PAGE) - while json_url is not None: - show_json = self._download_json( - json_url, show_id, - note='Downloading %s json page #%s' % - (video_type, re.search(r'[?&]page=([0-9]+)', json_url).group(1))) - for video in show_json['response']: + for video_type in ('episodes', 'clips'): + page_url = '%s/%s/%s.json?app=%s&per_page=%d&sort=number&direction=asc&with_paging=true&page=1' % (self._API_BASE, channel_id, video_type, self._APP, self._PER_PAGE) + while page_url: + page = self._download_json( + page_url, channel_id, + 'Downloading %s JSON page #%s' + % (video_type, re.search(r'[?&]page=([0-9]+)', page_url).group(1))) + for video in page['response']: video_id = video['id'] entries.append(self.url_result( 'http://www.viki.com/videos/%s' % video_id, 'Viki', video_id)) - json_url = show_json['pagination']['next'] + page_url = page['pagination']['next'] - return self.playlist_result(entries, show_id, title, description) + return self.playlist_result(entries, channel_id, title, description)