大乐透爬虫脚本python

借鉴别人代码改编的

import gzip
import re
from urllib import request

import xlwt
from bs4 import BeautifulSoup


# 参数说明：
#   period: 开奖期数
#   redo_num: 重试次数，默认是0，每错误一次回调时会+1，默认就好
#   max：最大重试次数，默认5
def get_pls(period, redo_num=0, redo_max=5) -> dict:
    try:
        #url = 'http://kaijiang.500.com/shtml/pls/%05d.shtml' % period https://kaijiang.500.com/shtml/dlt/21047.shtml
        url = 'http://kaijiang.500.com/shtml/dlt/%05d.shtml' % period
        req = request.Request(url)
        

        # 设置一下头，不设置返回结果不正确
        req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                                     'Chrome/79.0.3945.117 Safari/537.36')
        req.add_header('Accept',
                       'text/html,application/xhtml+xml,application/xml;q=0.9,ima