我的第一个的python抓取 单页面爬虫

Posted 2020-10-23

爬取豆瓣推荐书籍页的图书的图片保存到本地

# -*- coding UTF-8 -*- 

import re
import requests
import os

def getsite(url):
    website=requests.get(url)

url="https://book.douban.com/tag/%E7%BC%96%E7%A8%8B"
website=requests.get(url)

links=re.findall("(https:\/\/img3.doubanio.com\/mpic\/(\w+\.jpg))",website.text)

dir="test/"
if not os.path.exists(dir):
    os.makedirs(dir)
count=0
for link,name in links:
    with open(dir+name,‘wb‘) as img:
        file=requests.get(link)
        img.write(file.content)
        img.close()
        count+=1
        print("已抓取%s张图片"%(count))