爬取京东商城商品封面图片

最新推荐文章于 2022-08-29 21:14:46 发布

sky藏锋

最新推荐文章于 2022-08-29 21:14:46 发布

阅读量454

点赞数 3

本文链接：https://blog.csdn.net/qq_44666628/article/details/105249378

版权

import requests as rq
import re,os
url="https://search.jd.com/Search"
params={"keyword":"耳机","enc":"utf-8"}
params2={"keyword":"鲁冰逊飘流记","enc":"utf-8","wq":"鲁冰逊飘流记"}
head={"user-agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36"}
content=rq.get(url,params=params,headers=head).content.decode('utf-8')
# print(content)
compile2=re.compile(r'<img width="\d{3}" height="\d{3}" class="err-product" data-img="1" source-data-lazy-img="(.+?)" />')
compile=re.compile(r'<img width="200" height="200" data-img="1" source-data-lazy-img="" data-lazy-img="done" src="(.+?)">')
picturl=compile2.findall(content)
print(picturl)
count=0
if not os.path.exists(r'C:\Users\yagf1hz1\Desktop\pict\{}'.format(params.get('keyword'))):
    os.mkdir(r'C:\Users\yagf1hz1\Desktop\pict\{}'.format(params.get('keyword')))
for i in picturl:
    count+=1
    pictcontent=rq.get("http:"+i,headers=head).content
    # print(pictcontent)
    with open(r'C:\Users\yagf1hz1\Desktop\pict\{}'.format(params.get('keyword'))+"\\"+params.get('keyword')+str(count)+".jpg",'wb') as f:
        f.write(pictcontent)