__license__ = 'GPL v3' __copyright__ = '2010, Hiroshi Miura ' ''' http://ameblo.jp/ ''' import re from calibre.web.feeds.news import BasicNewsRecipe class SakuraBlog(BasicNewsRecipe): title = u'chou chou blog' __author__ = 'Hiroshi Miura' oldest_article = 4 publication_type = 'blog' max_articles_per_feed = 20 description = 'Japanese popular dog blog' publisher = '' category = 'dog, pet, japan' language = 'ja' encoding = 'utf-8' use_embedded_content = True feeds = [(u'blog', u'http://feedblog.ameba.jp/rss/ameblo/chouchou1218/rss20.xml')] def parse_feeds(self): feeds = BasicNewsRecipe.parse_feeds(self) for curfeed in feeds: delList = [] for a,curarticle in enumerate(curfeed.articles): if re.search(r'rssad.jp', curarticle.url): delList.append(curarticle) if len(delList)>0: for d in delList: index = curfeed.articles.index(d) curfeed.articles[index:index+1] = [] return feeds