爬双se球

免责声明:本文仅做分享...

url = 'https://kaijiang.500.com/ssq.shtml'

import requests
from lxml import etree
import openpyxl

wb = openpyxl.Workbook()
sheet = wb.active
sheet.title = 'xxx'
res = requests.get(url)
# 响应编码的设置
# 响应对象.encoding = '页面中charset值'
res.encoding = 'gb2312'
# 数据解析 使用xpath
tree = etree.HTML(res.text)
# 获取开奖号码
nums = tree.xpath('//div[@class="ball_box01"]//li/text()')
# ['06', '11', '12', '27', '29', '30', '13']
sheet.append(['开奖号码', ','.join(nums)])
# 开奖顺序
sort_nums = tree.xpath('//td[@align="left"]//tr[2]/td[2]/text()')[0].replace('\r\n\t\t\t\t\t\t\t', '')
sheet.append(['开奖顺序', sort_nums])
# print(sort_nums)
# 本期销量
span = tree.xpath('//span[@class="cfont1 "]/text()')
sales = span[0]
sheet.append(['本期销量', sales])
# 奖金滚存
price = span[1]
sheet.append(['奖金滚存', price])
# 奖项
jx = tree.xpath('//table[@class="kj_tablelist02"][2]//tr[@align="center"]')[1:]
sheet.append(['奖项','中奖注数','单注奖金（元）'])
# jx = [tr,tr,tr,tr,tr,tr]
for tr in jx:
    ls = []  # 创建一个空列表
    td = tr.xpath('./td/text()') # td= [一等奖,9,212564]
    for i in td:
        # [一等奖,9,7278585]
        ls.append(i.replace('\r\n\t\t\t\t', '').replace(',', ''))
    # 添加到excel中
    sheet.append(ls)
wb.save('双色球数据2.xlsx')

---