爬虫作业

import requests

from bs4 import BeautifulSoup

def getHTMLText(url):

try:

r=requests.get(url,timeout=30)

soup=BeautifulSoup(r.text)

r.raise_for_status()

r.encoding='utf-8'

return r.text,r.status_code,len(r.text),r.encoding,len(soup.text)

except:

return ""

 

url="https://www.sogou.com"

for i in range(20):

print(i)

print(getHTMLText(url))