diff --git a/recipes/lwn_weekly.recipe b/recipes/lwn_weekly.recipe index cc80c42da2..d6e9fa129c 100644 --- a/recipes/lwn_weekly.recipe +++ b/recipes/lwn_weekly.recipe @@ -7,6 +7,7 @@ lwn.net ''' from calibre.web.feeds.news import BasicNewsRecipe +from calibre.ebooks.BeautifulSoup import BeautifulSoup import re class WeeklyLWN(BasicNewsRecipe): @@ -14,8 +15,11 @@ class WeeklyLWN(BasicNewsRecipe): description = 'Weekly summary of what has happened in the free software world.' __author__ = 'Davide Cavalca' language = 'en' + site_url = 'http://lwn.net' - cover_url = 'http://lwn.net/images/lcorner.png' + extra_css = 'pre,code,samp,kbd,tt { font-size: 80% }\nblockquote {margin-left:0 }\n* { color: black }\n' + + cover_url = site_url + '/images/lcorner.png' #masthead_url = 'http://lwn.net/images/lcorner.png' publication_type = 'magazine' @@ -43,32 +47,51 @@ class WeeklyLWN(BasicNewsRecipe): br.submit() return br + def print_version(self, url): + + # Strip off anchor + url = url.split('#')[0] + + # Prepend site_url + if url[0:len(self.site_url)] != self.site_url: + url = self.site_url + url + + # Append printable URL parameter + print_param = '?format=printable' + if url[-len(print_param):] != print_param: + url += print_param + + #import sys + #print >>sys.stderr, "*** print_version(url):", url + return url + def parse_index(self): if self.username is not None and self.password is not None: - index_url = 'http://lwn.net/current/bigpage?format=printable' + index_url = self.print_version('/current/bigpage') else: - index_url = 'http://lwn.net/free/bigpage?format=printable' + index_url = self.print_version('/free/bigpage') soup = self.index_to_soup(index_url) body = soup.body articles = {} ans = [] + old_section = None url_re = re.compile('^/Articles/') while True: - tag_title = body.findNext(name='p', attrs={'class':'SummaryHL'}) + tag_title = body.findNext(attrs={'class':'SummaryHL'}) if tag_title == None: break - tag_section = tag_title.findPrevious(name='p', attrs={'class':'Cat1HL'}) + tag_section = tag_title.findPrevious(attrs={'class':'Cat1HL'}) if tag_section == None: section = 'Front Page' else: section = tag_section.string - tag_section2 = tag_title.findPrevious(name='p', attrs={'class':'Cat2HL'}) + tag_section2 = tag_title.findPrevious(attrs={'class':'Cat2HL'}) if tag_section2 != None: - if tag_section2.findPrevious(name='p', attrs={'class':'Cat1HL'}) == tag_section: + if tag_section2.findPrevious(attrs={'class':'Cat1HL'}) == tag_section: section = "%s: %s" %(section, tag_section2.string) if section not in articles.keys(): @@ -82,7 +105,7 @@ class WeeklyLWN(BasicNewsRecipe): if tag_url == None: break body = tag_url - if tag_url.string == None: + if tag_url.string == None: continue elif tag_url.string == 'Full Story': break @@ -93,10 +116,11 @@ class WeeklyLWN(BasicNewsRecipe): if tag_url == None: break + article = dict( title=self.tag_to_string(tag_title), - url= 'http://lwn.net' + tag_url['href'].split('#')[0] + '?format=printable', + url=tag_url['href'], description='', content='', date='') articles[section].append(article)