全书网

import requests
import re
from lxml import etree
start_url ='http://www.quanshuwang.com/list/5_{}.html'
book_page=1
# 1到128页书的网址
for book_page in range(1):
    url =start_url.format(book_page)
    response =requests.get(url).content.decode('gbk')
    # print(response)
    book_html= ' <li><a target="_blank" href="(.*?)" class="l mr10">'

    # book_title ='alt="(.*?)"'
    book_title ='<a target="_blank" title="(.*?)" '
    re_html= re.findall(book_html,response)
    re_title =re.findall(book_title,response)
    # for title,html in  zip(re_title,re_html):
    #     print(title,html)

    #range(1,20)书的数量,1到20的书籍数量
    for j in range(1,20):

        response_book =requests.get(re_html[j]).content.decode('gbk')
        read_start=' <a href="(.*?)" class="reader" title="(.*?)">开始阅读</a>'
        read_menu=re.findall(read_start,response_book)
        print(read_menu[0][0])
        print(read_menu[0][1])
        menu_url =requests.get(read_menu[0][0]).content.decode('gbk')
        print(menu_url)
        book_mulu='<DIV class="dirtitone"><H2>(.*?)</H2></div>'
        print(re.findall(book_mulu,menu_url))