Requests 校花网图片爬取

纪念我们闹过的矛盾
import requests
import re
url = 'http://www.xiaohuar.com/list-1-%s.html'
for i in range(4):
    temp = url % i
    response =requests.get(temp)
    html = response.text

    #img_urls=re.findall(r"/d/file/\d+/\w+\.jpg",html)#取出图片URL
    #img_urls1 = re.findall(r"https://\w+.*?/\w+/\w+/\w+/\w+/\d+/\w+.*\.jpg", html)#取出图片URL
    #img_names = re.findall(r'<img \w+.*="\d+".*? alt="(.*?)"', html) #取出图片名称
    img=re.findall(r'<img \w+.*="\d+".*? alt="(.*?)".*"(/d/file/\d+/\w+\.jpg)"', html)
    for img_tupian in img:
        img_tupian_urls=img_tupian[-1]#取出图片Url
        img_name=img_tupian[0]#取出名称
        
        img_response=requests.get("http://www.xiaohuar.com%s" %img_tupian_urls)

        xiaohua=img_response.content
        name=("http://www.xiaohuar.com%s" %img_tupian_urls).split('/')[-1]
        print(houzui)
        with open(img_name +name,'wb') as f:
            f.write(xiaohua)

 

爬去结果还是有点不好，有空想想把那些乱码去掉