1 #!/usr/bin/env python2 2 # vim:fileencoding=utf-8 3 from __future__ import unicode_literals, division, absolute_import, print_function 4 from calibre.web.feeds.news import BasicNewsRecipe 5 6 class rdzs(BasicNewsRecipe): 7 title = ‘儒道至圣‘ 8 description = ‘这是一个读书人掌握天地之力的世界。 才气在身,诗可杀敌,词能灭军,文章安天下。 秀才提笔,纸上谈兵;举人杀敌,出口成章;进士一怒,唇枪舌剑。 圣人驾临,口诛笔伐,可诛人,可判天子无道,以一敌国。 此时,圣院把持文位,国君掌官位,十国相争,蛮族虎视,群妖作乱。 此时,无唐诗大兴,无宋词鼎盛,无创新文章,百年无新圣。 一个默默无闻的寒门子弟,被人砸破头后,挟传世诗词,书惊圣文章,踏上至圣之路。‘ 9 max_articles_per_feed = 20000 10 fileName = ‘xx/rdzs.txt‘ 11 cover_url = ‘http://www.50zw.la/files/article/image/2/2806/2806s.jpg‘ 12 no_stylesheets = True 13 keep_only_tags = [dict(name=‘div‘, attrs={‘class‘:‘h1title‘}),dict(name=‘div‘, attrs={‘id‘:‘htmlContent‘})] 14 url_prefix = ‘http://www.xxbiquge.com‘ 15 no_stylesheets = True 16 keep_only_tags = [dict(name=‘div‘, attrs={‘class‘:‘bookname‘}),dict(name=‘div‘, attrs={‘id‘:‘content‘})] 17 file_object = open(fileName,‘r‘) 18 lastHref = file_object.read() 19 file_object.close() 20 hasLoad = bool(lastHref) 21 22 def get_title(self, link): 23 return link.contents[0].strip() 24 25 def parse_index(self): 26 soup = self.index_to_soup(self.url_prefix+"/5_5690") 27 28 div = soup.find(‘div‘, { ‘id‘: ‘list‘ }) 29 lastHref =self.lastHref 30 articles = [] 31 for link in div.findAll(‘a‘): 32 til = self.get_title(link) 33 href = link[‘href‘] 34 self.lastHref = href 35 if href == lastHref: 36 self.hasLoad = False 37 if self.hasLoad: 38 continue 39 else: 40 url = self.url_prefix + href 41 a = { ‘title‘: til, ‘url‘: url } 42 articles.append(a) 43 44 tutorial = [(self.title, articles)] 45 file_write = open(self.fileName,‘w‘) 46 file_write.write(self.lastHref) 47 file_write.flush() 48 file_write.close() 49 return tutorial
说明:
fileName :是为了简单的记录一下最后一次更新的网址,避免每次都全部更新 上述代码的详细讲解可以看:http://abirdcfly.github.io/2016/03/07/calibre2mobi/
时间: 2024-10-27 11:51:24