python爬取实例

import requests#导入第三方库，必须

url = "https://item.jd.com/2967929.html"#网站
try:
    r = requests.get(url)
    print(r.status_code)  # 200成功，404错误
    # r.encoding = ‘utf-8‘
    r.encoding =r.apparent_encoding
    print(r.text[:1000])#爬取前1000字节
except:
    print("爬取失败")

import requests
import os
url="http://a0.att.hudong.com/16/12/01300535031999137270128786964.jpg"
root="D://Other//Picture//"#存放地址
path=root+url.split(‘/‘)[-1]
try:
    if not os.path.exists(root):
        os.major(root)
    if not os.path.exists(path):
        r=requests.get(url)
        with open(path,‘wb‘) as f:
            f.write(r.content)
            f.close()
            print("保存成功")
    else:
        print("文件已存在")
except:
    print("爬取失败")