From 2a551d882bbc19b86d000cf6327cb5d953973745 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 8 Jul 2012 09:26:27 +0530 Subject: [PATCH] Fix #1022163 (Updated recipe for Adventure Gamers) --- recipes/adventuregamers.recipe | 59 ++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 28 deletions(-) diff --git a/recipes/adventuregamers.recipe b/recipes/adventuregamers.recipe index d08eca1723..b82bb7d02d 100644 --- a/recipes/adventuregamers.recipe +++ b/recipes/adventuregamers.recipe @@ -1,5 +1,5 @@ __license__ = 'GPL v3' -__copyright__ = '2009-2010, Darko Miletic ' +__copyright__ = '2009-2012, Darko Miletic ' ''' www.adventuregamers.com ''' @@ -14,24 +14,24 @@ class AdventureGamers(BasicNewsRecipe): publisher = 'Adventure Gamers' category = 'news, games, adventure, technology' oldest_article = 10 - delay = 10 + #delay = 10 max_articles_per_feed = 100 no_stylesheets = True - encoding = 'cp1252' + encoding = 'utf8' remove_javascript = True use_embedded_content = False INDEX = u'http://www.adventuregamers.com' extra_css = """ .pageheader_type{font-size: x-large; font-weight: bold; color: #828D74} - .pageheader_title{font-size: xx-large; color: #394128} + .pageheader_title,.page_title{font-size: xx-large; color: #394128} .pageheader_byline{font-size: small; font-weight: bold; color: #394128} .score_bg {display: inline; width: 100%; margin-bottom: 2em} .score_column_1{ padding-left: 10px; font-size: small; width: 50%} .score_column_2{ padding-left: 10px; font-size: small; width: 50%} .score_column_3{ padding-left: 10px; font-size: small; width: 50%} - .score_header{font-size: large; color: #50544A} - .bodytext{display: block} - body{font-family: Helvetica,Arial,sans-serif} + .score_header{font-size: large; color: #50544A} + img{margin-bottom: 1em;} + body{font-family: 'Open Sans',Helvetica,Arial,sans-serif} """ conversion_options = { @@ -41,35 +41,38 @@ class AdventureGamers(BasicNewsRecipe): , 'language' : language } - keep_only_tags = [ - dict(name='div', attrs={'class':'content_middle'}) - ] - + keep_only_tags = [dict(name='div', attrs={'class':'cleft_inn'})] remove_tags = [ - dict(name=['object','link','embed','form']) - ,dict(name='div', attrs={'class':['related-stories','article_leadout','prev','next','both']}) + dict(name=['object','link','embed','form','iframe','meta']) + ,dict(name='a', attrs={'href':'http://www.adventuregamers.com/about/scoring'}) + ,dict(name='a', attrs={'href':'http://www.adventuregamers.com/about/policies'}) ] - - remove_tags_after = [dict(name='div', attrs={'class':'toolbar_fat'})] + remove_tags_after = [dict(name='div', attrs={'class':'bodytext'})] remove_attributes = ['width','height'] - feeds = [(u'Articles', u'http://feeds2.feedburner.com/AdventureGamers')] + feeds = [(u'Articles', u'http://www.adventuregamers.com/rss/')] def get_article_url(self, article): - return article.get('guid', None) + url = BasicNewsRecipe.get_article_url(self, article) + if '/videos/' in url or '/hypeometer/' in url: + return None + return url def append_page(self, soup, appendtag, position): - pager = soup.find('div',attrs={'class':'toolbar_fat_next'}) + pager = soup.find('div', attrs={'class':'pagination_big'}) if pager: - nexturl = self.INDEX + pager.a['href'] - soup2 = self.index_to_soup(nexturl) - texttag = soup2.find('div', attrs={'class':'bodytext'}) - for it in texttag.findAll(style=True): - del it['style'] - newpos = len(texttag.contents) - self.append_page(soup2,texttag,newpos) - texttag.extract() - appendtag.insert(position,texttag) + nextpage = soup.find('a', attrs={'class':'next-page'}) + if nextpage: + nexturl = nextpage['href'] + soup2 = self.index_to_soup(nexturl) + texttag = soup2.find('div', attrs={'class':'bodytext'}) + for it in texttag.findAll(style=True): + del it['style'] + newpos = len(texttag.contents) + self.append_page(soup2,texttag,newpos) + texttag.extract() + pager.extract() + appendtag.insert(position,texttag) def preprocess_html(self, soup): @@ -78,7 +81,7 @@ class AdventureGamers(BasicNewsRecipe): for item in soup.findAll('div', attrs={'class':'floatright'}): item.extract() self.append_page(soup, soup.body, 3) - pager = soup.find('div',attrs={'class':'toolbar_fat'}) + pager = soup.find('div',attrs={'class':'pagination_big'}) if pager: pager.extract() return self.adeify_images(soup)