实例4：网络图片的爬取和存储

Posted 2021-02-19 tingtin

网络图片链接的格式：http://www.example.com/picture.jpg

图片爬取代码

 

import requests
import os
#url = ‘https://image.baidu.com/search/detail?ct=503316480&z=&tn=baiduimagedetail&ipn=d&word=%E7%8B%97&step_word=&ie=utf-8&in=&cl=2&lm=-1&st=-1&hd=&latest=&copyright=&cs=3454764333,132856788&os=2732860056,534267934&simid=3414273181,65897104&pn=22&rn=1&di=47850&ln=1781&fr=&fmq=1589705073726_R&ic=&s=undefined&se=&sme=&tab=0&width=&height=&face=undefined&is=0,0&istype=2&ist=&jit=&bdtype=0&spn=0&pi=0&gsm=0&objurl=http%3A%2F%2Fwww.goumin.com%2Fattachments%2Fphoto%2F0%2F0%2F95%2F24365%2F6237648.jpg&rpstart=0&rpnum=0&adpicid=0&force=undefined‘
url = ‘http://img0.dili360.com/ga/M00/48/F7/wKgBy1llvmCAAQOVADC36j6n9bw622.tub.jpg‘
root  = ‘E://dasande//dasi//Graduation practice//Reptile//material//‘
#E:dasandedasiGraduation practiceReptile是错的
path = root + url.split(‘/‘)[-1]#wKgBy1llvmCAAQOVADC36j6n9bw622.tub.jpg
try:
    if not os.path.exists(root):
        os.mkdir(root)
    if not os.path.exists(path):
        r = requests.get(url)
        print(r.status_code)
        r.encoding = r.apparent_encoding
        print(r.text)
        r.raise_for_status()
        with open(path, ‘wb‘) as f:  # 以二进制写入的权限打开文件,图片是二进制格式
            f.write(r.content)  # 写入图片的二进制数据
            f.close()  # 关闭文件
            print("文件保存成功")
    else:
        print(‘文件已存在‘)
except:
    print(‘爬取失败‘)