X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fadobetv.py;h=008c98e51ead3ffcad7bb350fcf928a945b91e35;hb=56667d622c3f6e7594a04f8cd5f4371875940725;hp=383c89485080f7b44c73c92e14addddcdf38682c;hpb=402ca40c9d0b20f1d04a0035b4cda0cc1184c689;p=youtube-dl diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 383c89485..008c98e51 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( parse_duration, unified_strdate, @@ -14,7 +15,11 @@ from ..utils import ( ) -class AdobeTVIE(InfoExtractor): +class AdobeTVBaseIE(InfoExtractor): + _API_BASE_URL = 'http://tv.adobe.com/api/v4/' + + +class AdobeTVIE(AdobeTVBaseIE): _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?watch/(?P[^/]+)/(?P[^/]+)' _TEST = { @@ -25,7 +30,7 @@ class AdobeTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop', 'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311', - 'thumbnail': 're:https?://.*\.jpg$', + 'thumbnail': r're:https?://.*\.jpg$', 'upload_date': '20110914', 'duration': 60, 'view_count': int, @@ -38,7 +43,7 @@ class AdobeTVIE(InfoExtractor): language = 'en' video_data = self._download_json( - 'http://tv.adobe.com/api/v4/episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), + self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), urlname)['data'][0] formats = [{ @@ -51,7 +56,7 @@ class AdobeTVIE(InfoExtractor): self._sort_formats(formats) return { - 'id': str(video_data['id']), + 'id': compat_str(video_data['id']), 'title': video_data['title'], 'description': video_data.get('description'), 'thumbnail': video_data.get('thumbnail'), @@ -62,6 +67,77 @@ class AdobeTVIE(InfoExtractor): } +class AdobeTVPlaylistBaseIE(AdobeTVBaseIE): + 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(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0] + + return self.playlist_result( + self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname), + compat_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(self._API_BASE_URL + 'show/?%s' % query, channel_urlname), + channel_urlname) + + class AdobeTVVideoIE(InfoExtractor): _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P\d+)' @@ -80,7 +156,10 @@ class AdobeTVVideoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - video_data = self._download_json(url + '?format=json', video_id) + webpage = self._download_webpage(url, video_id) + + video_data = self._parse_json(self._search_regex( + r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id) formats = [{ 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),