百度图片爬虫

最新推荐文章于 2024-11-08 13:43:44 发布

Andy12138

最新推荐文章于 2024-11-08 13:43:44 发布

阅读量104

点赞数

文章标签： python

本文链接：https://blog.csdn.net/qq_44328440/article/details/107737562

版权

import requests
import re
import os

word =input('请输入要爬取的内容：')
if not os.path.exists(word):
    os.mkdir(word)

i=0

num=int(input("请输入要爬取的页数（每页30张图片）："))

headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}
urls=['https://image.baidu.com/search/acjson?tn=resultjson_com&ipn=rj&ct=201326592&is=&fp=result&queryWord=%E5%A3%81%E7%BA%B8&cl=2&lm=-1&ie=utf-8&oe=utf-8&adpicid=&st=-1&z=&ic=&hd=&latest=&copyright=&word='+word+'&pn={}'.format(j) for j in range(30,num*30+1,30)]

def get_img(url):
    response=requests.get(url,headers)
    content=response.content.decode('utf-8')
    img_urls=re.findall('"thumbURL":"(.*?)"',content,re.S)
    global i
    for img_url in img_urls:
        response=requests.get(img_url,headers)
        content=response.content
        with open(word+'/'+'{}.jpg'.format(i+1),'wb') as f:
            f.write(content)
            print("正在爬取第{}张图片".format(i+1))
        i+=1
for url in urls:
    get_img(url)