htm2 = requests.get(url,headers) soup = BeautifulSoup(htm2.content,'lxml') books_lst = [] name = soup.find('div',class_='listmain') #父div,子dl,孙dt(总标题)和dd(每一章) if name: dd_items = name.find('dl') dt_num = 0 for n in dd_items.children: ename = str(n.name).strip() if ename == 'dt': dt_num += 1 if ename != 'dd': continue books_info = {} if dt_num == 2: durls = n.find_all('a')[0] books_info['name'] = durls.get_text() books_info['url'] = 'http://www.biqukan.com' + durls.get('href') books_lst.append(books_info) return books_lst
