home *** CD-ROM | disk | FTP | other *** search
- __license__ = 'GPL v3'
- __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
- '''
- www.adventuregamers.com
- '''
-
- from calibre.web.feeds.news import BasicNewsRecipe
-
- class AdventureGamers(BasicNewsRecipe):
- title = u'Adventure Gamers'
- language = 'en'
- __author__ = 'Darko Miletic'
- description = 'Adventure games portal'
- publisher = 'Adventure Gamers'
- category = 'news, games, adventure, technology'
- oldest_article = 10
- delay = 10
- max_articles_per_feed = 100
- no_stylesheets = True
- encoding = 'cp1252'
- 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_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}
- """
-
- conversion_options = {
- 'comment' : description
- , 'tags' : category
- , 'publisher' : publisher
- , 'language' : language
- }
-
- keep_only_tags = [
- dict(name='div', attrs={'class':'content_middle'})
- ]
-
- remove_tags = [
- dict(name=['object','link','embed','form'])
- ,dict(name='div', attrs={'class':['related-stories','article_leadout','prev','next','both']})
- ]
-
- remove_tags_after = [dict(name='div', attrs={'class':'toolbar_fat'})]
- remove_attributes = ['width','height']
-
- feeds = [(u'Articles', u'http://feeds2.feedburner.com/AdventureGamers')]
-
- def get_article_url(self, article):
- return article.get('guid', None)
-
- def append_page(self, soup, appendtag, position):
- pager = soup.find('div',attrs={'class':'toolbar_fat_next'})
- 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)
-
-
- def preprocess_html(self, soup):
- for item in soup.findAll(style=True):
- del item['style']
- 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'})
- if pager:
- pager.extract()
- return self.adeify_images(soup)
-