From 2eb25b256bf38db9f35696822cee399099eb4777 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Thu, 3 Mar 2016 03:14:00 +0800 Subject: [PATCH] [letv] Merge LetvTvIE into LetvPlaylistIE And 1. Add more URL examples 2. Improve the matching pattern --- youtube_dl/extractor/__init__.py | 1 - youtube_dl/extractor/letv.py | 56 ++++++++++++++++++-------------- 2 files changed, 31 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b3bf73963..19c563172 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -354,7 +354,6 @@ from .lecture2go import Lecture2GoIE from .lemonde import LemondeIE from .letv import ( LetvIE, - LetvTvIE, LetvPlaylistIE, LetvCloudIE, ) diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py index ba8126f75..ce25bb4db 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/letv.py @@ -195,8 +195,9 @@ class LetvIE(InfoExtractor): } -class LetvTvIE(InfoExtractor): - _VALID_URL = r'http://www\.le\.com/tv/(?P\d+)\.html' +class LetvPlaylistIE(InfoExtractor): + _VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P[a-z0-9_]+)' + _TESTS = [{ 'url': 'http://www.le.com/tv/46177.html', 'info_dict': { @@ -205,29 +206,7 @@ class LetvTvIE(InfoExtractor): 'description': 'md5:395666ff41b44080396e59570dbac01c' }, 'playlist_count': 35 - }] - - def _real_extract(self, url): - playlist_id = self._match_id(url) - page = self._download_webpage(url, playlist_id) - - # Currently old domain names are still used in playlists - media_ids = orderedSet(re.findall( - r'http://www\.letv\.com/ptv/vplay/(\d+)\.html', page)) - entries = [self.url_result(LetvIE._URL_TEMPLATE % media_id, ie='Letv') - for media_id in media_ids] - - title = self._html_search_meta('keywords', page, - fatal=False).split(',')[0] - description = self._html_search_meta('description', page, fatal=False) - - return self.playlist_result(entries, playlist_id, playlist_title=title, - playlist_description=description) - - -class LetvPlaylistIE(LetvTvIE): - _VALID_URL = r'http://tv\.le\.com/[a-z]+/(?P[a-z]+)/index\.s?html' - _TESTS = [{ + }, { 'url': 'http://tv.le.com/izt/wuzetian/index.html', 'info_dict': { 'id': 'wuzetian', @@ -246,8 +225,35 @@ class LetvPlaylistIE(LetvTvIE): 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489' }, 'playlist_mincount': 7 + }, { + 'url': 'http://www.le.com/comic/92063.html', + 'only_matching': True, + }, { + 'url': 'http://list.le.com/listn/c1009_sc532002_d2_p1_o1.html', + 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if LetvIE.suitable(url) else super(LetvPlaylistIE, cls).suitable(url) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + page = self._download_webpage(url, playlist_id) + + # Currently old domain names are still used in playlists + media_ids = orderedSet(re.findall( + r']+href="http://www\.letv\.com/ptv/vplay/(\d+)\.html', page)) + entries = [self.url_result(LetvIE._URL_TEMPLATE % media_id, ie='Letv') + for media_id in media_ids] + + title = self._html_search_meta('keywords', page, + fatal=False).split(',')[0] + description = self._html_search_meta('description', page, fatal=False) + + return self.playlist_result(entries, playlist_id, playlist_title=title, + playlist_description=description) + class LetvCloudIE(InfoExtractor): IE_DESC = '乐视云'