From 9a605c8859e5ecf164719b890ea62b76afb0b874 Mon Sep 17 00:00:00 2001 From: remitamine Date: Thu, 29 Oct 2015 20:00:27 +0100 Subject: [PATCH] [adobetv] add support for show and channel extraction --- youtube_dl/extractor/__init__.py | 2 + youtube_dl/extractor/adobetv.py | 72 ++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6318ac4a2..d4b42dc25 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -6,6 +6,8 @@ from .addanime import AddAnimeIE from .adobetv import ( AdobeTVIE, + AdobeTVShowIE, + AdobeTVChannelIE, AdobeTVVideoIE, ) from .adultswim import AdultSwimIE diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 383c89485..d0bfafa45 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -62,6 +62,78 @@ def _real_extract(self, url): } +class AdobeTVPlaylistBaseIE(InfoExtractor): + def _parse_page_data(self, page_data): + return [self.url_result(self._get_element_url(element_data)) for element_data in page_data] + + def _extract_playlist_entries(self, url, display_id): + page = self._download_json(url, display_id) + entries = self._parse_page_data(page['data']) + for page_num in range(2, page['paging']['pages'] + 1): + entries.extend(self._parse_page_data( + self._download_json(url + '&page=%d' % page_num, display_id)['data'])) + return entries + + +class AdobeTVShowIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?show/(?P[^/]+)' + + _TEST = { + 'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost', + 'info_dict': { + 'id': '36', + 'title': 'The Complete Picture with Julieanne Kost', + 'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27', + }, + 'playlist_mincount': 136, + } + + def _get_element_url(self, element_data): + return element_data['urls'][0] + + def _real_extract(self, url): + language, show_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&show_urlname=%s' % (language, show_urlname) + + show_data = self._download_json( + 'http://tv.adobe.com/api/v4/show/get/?%s' % query, show_urlname)['data'][0] + + return self.playlist_result( + self._extract_playlist_entries('http://tv.adobe.com/api/v4/episode/?%s' % query, show_urlname), + str(show_data['id']), + show_data['show_name'], + show_data['show_description']) + + +class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): + _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?channel/(?P[^/]+)(?:/(?P[^/]+))?' + + _TEST = { + 'url': 'http://tv.adobe.com/channel/development', + 'info_dict': { + 'id': 'development', + }, + 'playlist_mincount': 96, + } + + def _get_element_url(self, element_data): + return element_data['url'] + + def _real_extract(self, url): + language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups() + if not language: + language = 'en' + query = 'language=%s&channel_urlname=%s' % (language, channel_urlname) + if category_urlname: + query += '&category_urlname=%s' % category_urlname + + return self.playlist_result( + self._extract_playlist_entries('http://tv.adobe.com/api/v4/show/?%s' % query, channel_urlname), + channel_urlname) + + class AdobeTVVideoIE(InfoExtractor): _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P\d+)'