python批量爬取猫咪图片

from bs4 import BeautifulSoup  # 贵族名宠网页爬虫
import requests
import urllib.request
# 网址
url = ‘http://www.hengdadog.com/sale-1.html‘
def allpage():  # 获得所有网页
    all_url = []
    for i in range(1, 8): #循环翻页次数
        each_url = url.replace(url[-6], str(i))  # 替换
        all_url.append(each_url)
    return (all_url)  # 返回地址列表

if __name__ == ‘__main__‘:
    img_url = allpage()  # 调用函数
    for url in img_url:
        # 获得网页源代码
        print(url)
        requ = requests.get(url)
        req = requ.text.encode(requ.encoding).decode()
        html = BeautifulSoup(req, ‘lxml‘)
        t = 0
        # 选择目标url
        img_urls = html.find_all(‘img‘)
        for k in img_urls:
            img = k.get(‘src‘)  # 图片
            print(img)
            name = str(k.get(‘alt‘))  # 名字，这里的强制类型转换很重要
            type(name)
            # 先本地新建一下文件夹，保存图片并且命名
            path = ‘F:\\CAT\\‘  # 路径
            file_name = path + name + ‘.jpg‘
            imgs = requests.get(img)     # 存储入文件                                                      
            try:
                urllib.request.urlretrieve(img, file_name)  # 打开图片地址，下载图片保存在本地，
            except:
                print("error")