第一个爬虫和测试

访问搜狗主页

import requests
r=requests.get("https://www.sogou.com/")
print(r.status_code)
print(r.encoding)
print(r.apparent_encoding)
r.encoding='utf-8'
print(r.text)

爬取

import requests
def getHTMLText(url):
    try: 
        for i in range(0,20):                   
            r = requests.get(url, timeout=30)
        r.raise_for_status() 
        r.encoding = 'utf-8' 
        return r.status_code,r.text,type(r.text),type(r.content),len(r.text),len(r.content) 
    except:
        return ""
url = "https://www.sogou.com/"
print(getHTMLText(url))