python爬虫

 

import requests
def getHTMLText(url):
    try:
        r=requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return "产生异常"

if __name__ == "__main__":
    url = "http://www.baidu.com"
    print(getHTMLText(url))
    

import requests
r = requests.get("http://python123.io/ws/demo.html")
r.text
demo=r.text
from bs4 import BeautifulSoup
soup = BeautifulSoup(demo, "html.parser")
print(soup.prettify())