python 爬起点目录

#目标：书名，简介，作者,字数
#首先确定源代码的列表
import urllib.request
import re
from bs4 import BeautifulSoup
import random
import time

load=input("路径:")
num=input("输入页数：")




def gethtml(url):                     #获取页面源代码html
    page=urllib.request.urlopen(url)
    html=page.read().decode('utf-8')  #html是一个列表
    soup=BeautifulSoup(html,'html.parser')
    return soup

def getbook(soup,load):
    for i in range(1,21):

        xl=soup.find_all("li",{"data-rid":str(i)})
        sm = re.compile(r'<h4><a .*?>(.*?)</a></h4>')    #匹配书名
        sm1=sm.findall(str(xl))
        a="《"+sm1[0]+"》"

        ze = re.compile(r'<a class="name" .*?>(.*?)</a>')
        ze1 = ze.findall(str(xl))                        #匹配作者名
        b=ze1[0]

        jj=re.compile(r'<p class="intro">([sS]*?)</p>')
        jj1=jj.findall(str(xl))                          #匹配简介
        c=jj1[0]

        zs=re.compile(r'<span>(.*?)</span>')
        zs1=zs.findall(str(xl))
        d=zs1[1]
        content=[a,b,c,d]
        
        for j in range(0,4):
            
            with open(load, 'a') as f:
                if j == 3:
                    f.write(content[3])
                else:
                    f.write(content[j]+"
")
                
        with open(load, 'a') as f:
            f.write("

----------------------------------------------------------------------

")
def geturl(num):
    for page in range(1,int(num)+1):
        
        url="http://fin.qidian.com/?size=-1&sign=-1&tag=-1&chanId=-1&subCateId=-1&orderId=&update=-1&page=%d&month=-1&style=1&vip=0" % page
        
        soup=gethtml(url)
        getbook(soup,load)
        time.sleep(2.5)
        
        
geturl(num)

实现