python爬取糗事百科热门笑话及图片

很早之前写的简单爬虫直接上代码：

#!/usr/bin/python3
#-*- coding:utf-8 -*-
import requests
import time
from pyquery import PyQuery as pq
from lxml import etree

class QSBK:
    def __init__(self):
        self.page = 1
        self.li = []
        self.s = 1
        self.picnum = 0

    def get_page(self, page):
        if page == 1:
            url = 'http://www.qiushibaike.com/hot/'
        else:
            url = 'http://www.qiushibaike.com/hot/page/'+str(page)    
            # url = 'http://www.qiushibaike.com/imgrank/'+str(page)    
        r = requests.get(url)
        r = requests.get(url)
        return r.text
    
    def get_page_items(self):
        d = pq(self.get_page(self.page))
        es = d(".article, .block, .untagged, .mb15")
        picnum = 0
        for i in es.items():
            if i('.thumb img').attr('src') == None:
                #print(i('.content').html())
                self.li.append(i('.content').text())
            else:
                r = requests.get(i('.thumb img').attr('src'),\
                    stream=True)
                self.picnum += 1
                with open('./pic2/'+str(self.picnum)+'.jpeg', 'wb') as fd:
                    for chunk in r.iter_content():
                        fd.write(chunk)
                print('第%s 图片下载成功。' % self.picnum)
                                      
    def start(self):
        for i in range(35): # 目前共 35 页 range(35)
            self.get_page_items()
            self.page += 1
            time.sleep(2)
            print('第%s 页文字获取成功。' % self.page)

    def write_file(self):
        f = open('fun.txt', 'w')
        for pre in self.li: 
            f.write(pre+'\n\n')
        f.close()

QS = QSBK()
QS.start()
QS.write_file()

生成文件：

笑话文件：

该程序只为练习爬虫