简单爬虫获取排列三开奖号码

直接上代码

import requests
from bs4 import BeautifulSoup

class Spider:
    def getHtmlData(self):
        url = "http://datachart.500.com/pls/history/inc/history.php?limit=100"
        response = requests.get(url)
        # html = response.content.decode("utf8")
        html = response.content
        self.getDataFromHtml(html)

    def getDataFromHtml(self,html):
        soup = BeautifulSoup(html,"html.parser")
        cfont2_list = soup.select(".chart .t_tr1 .cfont2")
        for number in cfont2_list:
            # print(number.string)
            self.saveData(number.string)

    def saveData(self,numberStr):
        with open("number_info.txt",'a',encoding="utf8") as f:
            f.write(numberStr)
            f.write("\n")
            f.flush()

    def beginSpider(self):
        self.getHtmlData()

if __name__=="__main__":
    spider = Spider()
    spider.beginSpider()

使用Google浏览器打开网址：http://datachart.500.com/pls/history/history.shtml

然后点击右键-检查，如下图显示：