双色球爬取并存txt

双色球爬取并存txt"/>

双色球爬取并存txt

import sys
import requests
from lxml import etreedef get_url(url):  # 请求url的方法，返回htmlheaders = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36',}response = requests.get(url, headers=headers)  # 获取请求的返回数据response.encoding = 'utf-8'  # 定义编码，不然中文输出会乱码；if response.status_code == 200:  # 如果请求成功，则返回；return response.textreturn Nonefor q in range(1, 125):  # for循环，一共124页；url = '.html' % (q)  # 定义请求的链接html = get_url(url)  # 请求url获取返回代码xpath_html = etree.HTML(html)  # xpath初始化html代码dates = xpath_html.xpath('//table[@class="wqhgt"]//tr//td[1]//text()')  # 获取开奖日期result = xpath_html.xpath('//table[@class="wqhgt"]//tr//em//text()')  # 获取上色球号issues = xpath_html.xpath('//table[@class="wqhgt"]//tr//td[2]//text()')  # 获取期号# print(result)       #输出所有双色球的列# print(len(result)//7)    #输出有几组双色球# print(dates)# print(issues)sta = 0end = 7for n in range(len(result) // 7):  # 双色球7个号一组，print("开奖日期:" + str(dates[n]) + " --- " + "期号:" + str(issues[n]) + " --- " + str(result[sta:end]))f = open('test.txt', 'a')f.write('\n' +str(dates[n]) +  str(result[sta:end]))f.close()# print(str(result[sta:end]))sta = sta + 7end = end + 7