Python爬虫学习100练001

# -*- coding:utf-8 -*-

# 2018年3月24日

# 爬取菜鸟教程最新文章列表并写入Excel中

# 第一步，导入爬虫库,正则库、Excel库（截取文本用的）

from urllib import request

import re

from openpyxl import Workbook

wenjian=[["标题","链接"]]

#爬取功能

def gettitle():

response=request.urlopen(url)

html=response.read().decode("utf-8")

re_zz=re.compile(r'.*?href="(.*?)">(.*?)

list=re_zz.findall(html)

for address,title in list:

wenjian.append([title,address])

#存储功能

def cunchu():

wb=Workbook()

sheet=wb.active

sheet.title="菜鸟教程"

for i in range(0,len(wenjian)):

for j in range(0,2):

sheet.cell(row=i+1, column=j+1).value = wenjian[i][j]

wb.save("菜鸟教程.xlsx")

#入口函数

if __name__ == "__main__":

for i in range(1,26):

print("正在爬去第%s页....."%i)

url="https://c.runoob.com/examples/page/%s" %i

gettitle()

print("第%s页爬取完毕!"%i)

print("开始存储")

cunchu()

print("写入完毕！")