From 73e7ddcefefbfdc28c4f148900bcebaca1268ce7 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Thu, 17 Oct 2013 13:10:16 +0530 Subject: [PATCH] Update WSJ some more --- recipes/wsj.recipe | 13 +------------ recipes/wsj_free.recipe | 14 +------------- 2 files changed, 2 insertions(+), 25 deletions(-) diff --git a/recipes/wsj.recipe b/recipes/wsj.recipe index c138fb2a04..16a523baec 100644 --- a/recipes/wsj.recipe +++ b/recipes/wsj.recipe @@ -19,19 +19,8 @@ class WallStreetJournal(BasicNewsRecipe): max_articles_per_feed = 1000 timefmt = ' [%a, %b %d, %Y]' no_stylesheets = True + ignore_duplicate_articles = {'url'} - extra_css = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; } - h2{color:#474537; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;} - .subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;} - .insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small } - .targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif} - .article{font-family :Arial,Helvetica,sans-serif; font-size:x-small} - .tagline {color:#333333; font-size:xx-small} - .dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif} - h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small} - .byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small} - h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; } - .paperLocation{color:#666666; font-size:xx-small}''' keep_only_tags = [ dict(name='h1'), dict(name='h2', attrs={'class':['subhead', 'subHed deck']}), dict(name='span', itemprop='author', rel='author'), diff --git a/recipes/wsj_free.recipe b/recipes/wsj_free.recipe index eea9789f79..c8857b60d7 100644 --- a/recipes/wsj_free.recipe +++ b/recipes/wsj_free.recipe @@ -19,19 +19,7 @@ class WallStreetJournal(BasicNewsRecipe): max_articles_per_feed = 1000 timefmt = ' [%a, %b %d, %Y]' no_stylesheets = True - - extra_css = '''h1{color:#093D72 ; font-size:large ; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; } - h2{color:#474537; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;} - .subhead{color:gray; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small; font-style:italic;} - .insettipUnit {color:#666666; font-family:Arial,Sans-serif;font-size:xx-small } - .targetCaption{ font-size:x-small; color:#333333; font-family:Arial,Helvetica,sans-serif} - .article{font-family :Arial,Helvetica,sans-serif; font-size:x-small} - .tagline {color:#333333; font-size:xx-small} - .dateStamp {color:#666666; font-family:Arial,Helvetica,sans-serif} - h3{color:blue ;font-family:Arial,Helvetica,sans-serif; font-size:xx-small} - .byline{color:blue;font-family:Arial,Helvetica,sans-serif; font-size:xx-small} - h6{color:#333333; font-family:Georgia,"Century Schoolbook","Times New Roman",Times,serif; font-size:small;font-style:italic; } - .paperLocation{color:#666666; font-size:xx-small}''' + ignore_duplicate_articles = {'url'} keep_only_tags = [ dict(name='h1'), dict(name='h2', attrs={'class':['subhead', 'subHed deck']}),