Python爬虫实例（一）

1.直接上代码，本爬虫实例是糗事百科网站为URL的

import requests
from bs4 import  BeautifulSoup

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

#获取网站的html文档

def getHtml():

    response=requests.get(url);

    response.encoding="utf-8";

    return response.text

#解析html文档对象，返回soup 对象

def parseHtml(html):

    soup=BeautifulSoup(html);

    #joke_content = soup.select('div.content')[0].get_text()
    joke_content = soup.find_all("div",attrs="content")

    for i in joke_content:
         print (i.get_text())


text=getHtml()

joke=parseHtml(text)

2.运行结果如下所示