python爬取双色球以往开奖号码

最新推荐文章于 2024-10-11 14:13:13 发布

一褛云烟

最新推荐文章于 2024-10-11 14:13:13 发布

阅读量650

点赞数

分类专栏： Python

本文链接：https://blog.csdn.net/qq_42659926/article/details/104605508

版权

Python 专栏收录该内容

4 篇文章 1 订阅

订阅专栏


"""爬取双色球开奖号码"""
import requests
import re

def Crawl_twoball(page = 10001):
"""爬取网页路径"""
    url = 'http://kaijiang.500.com/shtml/ssq/' + str(page) + '.shtml'
    reponse = requests.get(url)
    html = reponse.text
  """检测是否有这期"""
    notfound = re.findall('<head><title>(.*?) Not Found</title></head>', html)
    if notfound:
        return 0
"""获取红球，蓝球号码"""
    blueball = re.findall('<li class="ball_blue">(.*?)</li>', html)
    redball = re.findall('li class="ball_red">(.*?)</li>', html)
    twoball = redball + blueball
"""‘保存数据"""
    with open('twoball.txt', 'a+') as f:
        f.write(str(page) + '\000')#期号
        for i in twoball:
           f.write(i + '\000')
        f.write('\n')
    return 1


j = 10001 #起始期号
while j < 20010: #结束期号
    a = Crawl_twoball(j)
    #一年有153期左右，跳过中间空白
    if a == 0:
        j = (j//1000 + 1) * 1000
    j += 1