Python爬虫实战(六)：爬取糗事百科段子

直接上代码：

#coding=utf-8
import requests
from bs4 import Tag
from bs4 import BeautifulSoup

def getHtml(url):  
    page = requests.get(url)  
    html = page.text  
    return html

def getImg(html):
    get_text = Tag.get_text
    soup = BeautifulSoup(html, 'html.parser')
    
    info = soup.find_all('h2')
    user = (x.get_text() for x in info)   #使用生成器代替list(map(get_text,info))
                    
    info = soup.find_all('span',class_="stats-vote")
    vote = (x.get_text() for x in info)   #使用生成器代替list(map(get_text,info))  

    info = soup.find_all('div',class_="content")
    text = (x.get_text() for x in info)   #使用生成器代替list(map(get_text,info))  
    
    for x in zip(user,text,vote):         #zip函数同时遍历
        Enter = input()
        if Enter == 'Q' or Enter == 'q':
            return -1
        print("\n".join((s.strip() for s in x))) #使用生成器代替list(map(str.strip,x))
    return 1
 
if __name__=='__main__':
    url = "https://www.qiushibaike.com/hot/"
    html,i = getHtml(url),2
    print("开始读取数据，请按回车键...按Q键退出\n")
    while (getImg(html) == 1):
        print("\n第{}页\n".format(i))
        url = ("https://www.qiushibaike.com/hot/page/%s/" % str(i))
        html,i = getHtml(url),i+1
   

缺点：无法过滤掉既有文本，又有图片的内容。

待以后优化更新。