Python 一个抓取糗百的段子的小程序

Posted 2020-10-07 幽冥狂_七

import requests
import re
#糗事百科爬虫类
class QSBK:
    #初始化方法，定义一些变量
    def __init__(self):
        self.headers={
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/61.0.3163.79 Safari/537.36"
        }
        #存放段子的变量，每一个元素是每一页的段子们
        self.stories=[]
        #存放程序是否继续运行的变量
        self.enable =False

    def getPage(self,page):
        try:
            url = ‘http://www.qiushibaike.com/hot/page/‘ + str(page)
            print(url)
            response = requests.get(url,headers=self.headers)
            html_content = response.content.decode(‘UTF-8‘)
            #print(html_content)
            # regex=re.compile(‘<div class="article block untagged mb15\s\S+" id="\S+">.*?</div>‘)
            regex = re.compile(‘<h2>(.*?)</h2>.*?<div class="content">\W+<span>(.*?)</span>‘, re.S)
            #regex = re.compile(‘<h2>‘, re.S)
            regex_content = re.findall(regex, html_content)
            print(regex_content)
            for i in regex_content:
                self.stories.append(i[0].replace(‘\n‘, ‘‘),i[1].replace(‘\n‘, ‘‘))
            return self.stories
        except Exception as e:
            print(‘异常：%s‘ % e)



js = QSBK()

for i in range(100):
    lists = js.getPage(i)

    print(‘============================================ 第 ‘+str(i)+‘ 页 =============================================‘)
    print(lists)

如果发现不能用，那就是糗百又改规则了