python_爬虫限制

import requests
def cr_amaze(url):
    kv={"user-agent":"Mozilla/5.0"}
    try:
        r=requests.get(url,headers=kv)#改变请求头信息
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return print(r.text[200:4000])
    except:
        return print("失败")



url="https://www.amazon.cn/ASICS-亚瑟士-男-跑步鞋GEL-GALAXY-9-T6G0N-4901-蓝色-白色-黄色-41-5/dp/B06VVY1T73/ref=lp_1897086071_1_1?s=shoes&ie=UTF8&qid=1498642523&sr=1-1&nodeID=1897086071&psd=1"
cr_amaze(url)



百度搜素：
import requests
kv={}
kv["wd"]= input("请输入搜索内容")
try:
    r=requests.get("http://www.baidu.com/s",params=kv)
    print (r.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("失败")
爬取图片：
import requests
import os
url="https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1498662852777&di=7e160ccc431f257866cc5bf355b4116e&imgtype=0&src=http%3A%2F%2Fn.sinaimg.cn%2Feladies%2Ftransform%2F20160823%2ForrG-fxvcsrm2264890.jpg"
root="D://path//"
path=root+str("4.jpg")
#try:
#1.下载路径不存在创建路径
if not os.path.exists(root):
        os.mkdir(root)
#1下载的路径文件如果不存在下载
if not os.path.exists(path):
    r=requests.get(url)
    with open(path,'wb')as f:
            f.write(r.content)
            f.close()
else:
    print("文件已经存在")
#except:
 #   print("爬取失败")