import requests
import re
代码块儿可单独运行,需加模块导入
1.爬取商品内容
url="https://item.jd.com/6946605.html"
try:
r=requests.get(url)
print(r)
r.raise_for_status()
r.encoding=r.apparent_encoding
print(r.text[:1000])
except:
print("爬取失败")
get的信息提交
kv={'user-agent':'Mozailla/5.0'}
r=requests.get(url,headers=kv)
kevword="要提交的信息"
kv={'wd':kevword}
r=requests.get("http://www.baidu.com/s",params=kv)
爬取百度信息
keyword="CSDN流年博客"
try:
kv={'wd':keyword}
r=requests.get("http://www.baidu.com/s",params=kv)
print(r.request.url)
print(len(r.text))
except:
print("爬取失败")
爬取ip地址
url="http://www.ip138.com/ips138.asp?ip="
r=requests.get(url+'202.204.80.112')
r.raise_for_status()
r.encoding=r.apparent_encoding
zz=r.text
ze="<li>.*?</li>"
pp = re.findall(ze, zz)
print(pp)