爬虫爬取京东某类书籍图片并保存到本地

爬虫爬取京东某类书籍图片并保存到本地"/>

爬虫爬取京东某类书籍图片并保存到本地

python爬虫爬取京东某类书籍图片并保存到本地
完整代码

#!/usr/bin/env python3
# -*- coding: utf-8 -*-import re
import urllib.request
import urllib.error
import urllib.parsesum = 0
def craw(url,page):req=urllib.request.Request(url)req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36')html1 = urllib.request.urlopen(req).read()html1=str(html1)pat1 = '<div id="J_goodsList".+?<span class="clr"></span>'result1=repile(pat1).findall(html1)result1=result1[0]pat2 = '<img width="" height="" data-img="1" src="//(.+?[\.jpg|\.png])"'imagelist=repile(pat2).findall(result1)x=1global sumfor imageurl in imagelist:imagename='E:/pythonProjects/paChong/jdBook/'+str(page)+'-'+str(x)+'.jpg'imageurl="http://"+imageurltry:urllib.request.urlretrieve(imageurl,filename=imagename)except urllib.error.URLError as e:if hasattr(e,'code') or hasattr(e,'reason'):x+=1print('成功爬取第%d页第%d张图片'%(page,x))x+=1sum+=1for i in range(1,20):url='.html?cat=1713,3287,3805&page='+str(i)craw(url,i)
print('爬取结束，总共保存了%d张图'%sum)