From 2a0f6bbeaea9a16b5b1c207cea3ef35afbe00b0b Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 27 Jul 2013 07:42:51 +0530 Subject: [PATCH] Update Something Awful --- recipes/something_awful.recipe | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-) diff --git a/recipes/something_awful.recipe b/recipes/something_awful.recipe index 006cfdc9b2..636d306a6d 100644 --- a/recipes/something_awful.recipe +++ b/recipes/something_awful.recipe @@ -1,4 +1,3 @@ -import re from calibre.web.feeds.news import BasicNewsRecipe class SomethingAwfulRecipe(BasicNewsRecipe): @@ -6,8 +5,7 @@ class SomethingAwfulRecipe(BasicNewsRecipe): __author__ = 'atordo' description = 'The Internet Makes You Stupid' cover_url = 'http://i.somethingawful.com/core/head-logo-bluegren.png' - masthead_url = 'http://i.somethingawful.com/core/head-logo-bluegren.png' - oldest_article = 7 + oldest_article = 15 max_articles_per_feed = 50 auto_cleanup = False no_stylesheets = True @@ -16,27 +14,21 @@ class SomethingAwfulRecipe(BasicNewsRecipe): use_embedded_content = False remove_empty_feeds = True publication_type = 'magazine' + reverse_article_order = True recursions = 1 - match_regexps = [r'\?page=\d+$'] + match_regexps = [r'^http://www.somethingawful.com/.+/.+/\d{1,2}/$'] - preprocess_regexps = [ - (re.compile(r'.*', re.DOTALL), lambda match: '') - ] - - remove_attributes = [ 'align', 'alt', 'valign' ] + remove_attributes = ['align', 'alt', 'valign'] keep_only_tags = [ - dict(name='div', attrs={'class':'content_area'}) -# ,dict(name='p', attrs={'class':'pagebar'}) - ] - remove_tags = [ - dict(name='div', attrs={'class':['column_box','featurenav','social']}) - ,dict(name='div', attrs={'id':'sidebar'}) - ,dict(name='a', attrs={'class':'curpage'}) + dict(name='div', attrs={'class':'article_head'}) + ,dict(name='div', attrs={'class':'organ article'}) + ,dict(name='ul', attrs={'class':'pager'}) ] extra_css = ''' + .author{font-size:small} .date{font-size:small} .byline{font-size:small} .font_big{font-size:large} .compat5{font-weight:bold} .accentbox{background-color:#E3E3E3; border:solid black} img{margin-bottom:0.4em; display:block; margin-left: auto; margin-right:auto} @@ -53,7 +45,7 @@ class SomethingAwfulRecipe(BasicNewsRecipe): ,('The Great Goon Database', 'http://www.somethingawful.com/rss/great-goon-database.rss.xml') ,('Livejournal Theater', 'http://www.somethingawful.com/rss/livejournal-theater.rss.xml') ,('Joystick Token Healthpack', 'http://www.somethingawful.com/rss/token-healthpack.rss.xml') - #,('Webcam Ward', 'http://www.somethingawful.com/rss/webcam-ward.rss.xml') + ,('Webcam Ward', 'http://www.somethingawful.com/rss/webcam-ward.rss.xml') ,('Features / Articles', 'http://www.somethingawful.com/rss/feature-articles.rss.xml') ,('Guides', 'http://www.somethingawful.com/rss/guides.rss.xml') ,('Legal Threats', 'http://www.somethingawful.com/rss/legal-threats.rss.xml') @@ -77,6 +69,7 @@ class SomethingAwfulRecipe(BasicNewsRecipe): ,('Johnston Checks In', 'http://www.somethingawful.com/rss/levi-johnston.rss.xml') ,('Twitter Tuesday', 'http://www.somethingawful.com/rss/twitter-tuesday.rss.xml') ,('Music Article', 'http://www.somethingawful.com/rss/music-article.rss.xml') + ,('The Everdraed Showcase', 'http://www.somethingawful.com/rss/everdraed-showcase.xml') ,('Reviews [Games]', 'http://www.somethingawful.com/rss/game-reviews.rss.xml') ,('Reviews [Movies]', 'http://www.somethingawful.com/rss/movie-reviews.rss.xml') ,('Rom Pit', 'http://www.somethingawful.com/rss/rom-pit.rss.xml') @@ -92,4 +85,6 @@ class SomethingAwfulRecipe(BasicNewsRecipe): ,('Garbage Day', 'http://www.somethingawful.com/rss/garbage-day.rss.xml') ,('WTF, D&D!?', 'http://www.somethingawful.com/rss/dungeons-and-dragons.rss.xml') ,('Current Releases', 'http://www.somethingawful.com/rss/current-movie-reviews.rss.xml') + ,('Awful Things for Sale', 'http://www.somethingawful.com/rss/awful-things-sale.xml') ] +