python关键字爬取京东图片

最新推荐文章于 2024-06-11 16:22:35 发布

不爱学习的笨蛋

最新推荐文章于 2024-06-11 16:22:35 发布

阅读量478

点赞数 1

分类专栏： python编程

本文链接：https://blog.csdn.net/u011624019/article/details/102988052

版权

python编程专栏收录该内容

16 篇文章 0 订阅

订阅专栏

import re
import urllib.request
import os
import numpy as np
def craw(url,page,savedir):
    html1=urllib.request.urlopen(url).read()
    html1=str(html1)
    pat1='<div id="J_goodsList".*<div class="p-commit">'
    result1=re.compile(pat1).findall(html1)
    result1=result1[0]
    pat2 ='source-data-lazy-img="(//.*?jpg)'
    imag = re.compile(pat2).findall(result1)
    x = 1
    for imagurl in imag:
        imagname = savedir + '第'+str(page)+'页' + '第'+str(x)+'个' + '.jpg'
        imagurl = 'https:' + imagurl
        try:
            urllib.request.urlretrieve(imagurl,filename=imagname)
            print('已输出第',page,'页，第',x,'个')
        except urllib.error.URLError as e:
            if hasattr(e,'code'):
                x+=1
            if hasattr(e,'reason'):
                x+=1
        x+=1
if __name__ =="__main__":
    page_= 45
    key = ['衬衫','马甲衬衫','马甲','女生职业装','女士西服']
    for k in range(len(key)):
        if os.path.exists('./img/' + key[k]) == False:
            os.makedirs('./img/' + key[k])
        savedir = './img/' + key[k] + '/'
        name    = key[k]
        for i in range(1,2*page_+1):
            if i%2==0:
                key2=i/2+0.5
            else:
                key2=(i+1)/2
            key1=name
            key_temp=urllib.request.quote(key1)
            url2='https://search.jd.com/Search?keyword='+key_temp +'&enc=utf-8&page='+ str(i)
            # 模拟浏览器
            req = urllib.request.Request(url2)
            req.add_header("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8")
            req.add_header("Accept-Encoding","gzip, deflate, br")
            req.add_header("Accept-Language","zh-CN,zh;q=0.9")
            req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36")
            url=urllib.request.Request(url2)
            craw(url,key2,savedir)

本代码为网上所找，网址不记得了。原作可见请告知。