又来一个奇书小说目录爬取表格查看
本帖最后由 fanvalen 于 2020-7-18 20:58 编辑#coding=utf-8
import requests
import re
import openpyxl
ld=openpyxl.load_workbook
book=ld("d:\\qishu.xlsx")
sheet1=book["Sheet1"]
hd={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}
p=1
while p<1234:
url="http://m.iqishu.la/full/"+str(p)+".html"
try:
dat=requests.get(url,headers=hd,timeout=60)
except BaseException:
dat=requests.get(url,headers=hd,timeout=60)
if dat.status_code==200:
with open("d:\\qishu.txt","a+",encoding="utf-8")as f:
f.write(dat.text)
f.close()
else:
pass
p=p+1
print(str(p))
s=open("d:\\qishu.txt",encoding="utf-8").read()
pat=r"<div class=\"full_content\"><p class=\"p1\">(.*?)</p><p class=\"p2\"> <a href=\"(.*?)\" class=\"blue\">(.*?)</a></p><p class=\"p3\"><a>(.*?)</a></p></div>"
r=re.findall(pattern=pat,string=s)
for i in range(len(r)):
x=r
print(x)
row=sheet1.max_row+1
for b in range(len(x)):
# print(row)
sheet1.cell(row,b+1).value=x
book.save("d:\\qishu.xlsx")
表格目录下载链接
https://fanvalen.lanzouj.com/i04d8eon9di
谢谢分享
页:
[1]