cf4b5764b5
1. P1: 合并双 Flask 服务 — web_executor.py 功能整合到 app.py - /fetch → 抓取控制台页面 - /api/fetch/status → 抓取状态查询 - /api/fetch/execute → 触发抓取(后台线程异步) - web_console.html API 路径已更新 2. P1: fetch_data.py 增加重试机制 + 请求间隔 - REQUEST_DELAY=2s, MAX_RETRIES=3, RETRY_DELAY=5s - 修复缩进 bug(try/except 块缩进错误) 3. P0: 修复 Excel 数据格式兼容性 - fetch_data.py: 跳过网页 header 行,使用标准列名保存 - app.py: 新增 load_history_dataframe() 智能加载函数 - 兼容新旧两种 Excel 格式(一行/两行 header) - 统一列名: 开奖时间|期数|号码|开机号|和值特征|奇偶比|大小比|奇偶形态|跨度|其他 4. 运维: 创建 lotto-app.service systemd 单元 5. 修复 .gitignore(排除运行时数据文件和备份) 6. 创建 requirements.txt
176 lines
5.5 KiB
Python
176 lines
5.5 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
双色球历史数据抓取脚本
|
|
从 https://www.55128.cn/kjh/fcssq-history-120.htm 抓取数据
|
|
更新「双色球历史数据.xlsx」文件
|
|
"""
|
|
|
|
import requests
|
|
import time
|
|
from bs4 import BeautifulSoup
|
|
import pandas as pd
|
|
from datetime import datetime
|
|
import os
|
|
import re
|
|
|
|
# 数据源 URL
|
|
URL = "https://www.55128.cn/kjh/fcssq-history-120.htm"
|
|
# 输出文件路径
|
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
OUTPUT_FILE = os.path.join(SCRIPT_DIR, "双色球历史数据.xlsx")
|
|
|
|
# 请求头,模拟浏览器
|
|
HEADERS = {
|
|
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
|
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
|
|
"Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
|
|
}
|
|
|
|
|
|
# 请求间隔(秒),避免被封 IP
|
|
REQUEST_DELAY = 2
|
|
# 最大重试次数
|
|
MAX_RETRIES = 3
|
|
# 重试间隔(秒)
|
|
RETRY_DELAY = 5
|
|
|
|
|
|
def fetch_lottery_data():
|
|
"""抓取双色球历史数据"""
|
|
print(f"[{datetime.now()}] 开始抓取数据...")
|
|
|
|
last_error = None
|
|
for attempt in range(1, MAX_RETRIES + 1):
|
|
try:
|
|
# 请求前等待,避免频繁请求
|
|
if attempt > 1:
|
|
print(f" 第 {attempt} 次重试,等待 {RETRY_DELAY} 秒...")
|
|
time.sleep(RETRY_DELAY)
|
|
else:
|
|
time.sleep(REQUEST_DELAY)
|
|
|
|
response = requests.get(URL, headers=HEADERS, timeout=30)
|
|
response.raise_for_status()
|
|
response.encoding = "utf-8"
|
|
|
|
soup = BeautifulSoup(response.text, "html.parser")
|
|
|
|
# 查找表格数据
|
|
table = soup.find("table")
|
|
if not table:
|
|
print("错误:未找到数据表格")
|
|
return None
|
|
|
|
# 解析表格
|
|
data_rows = []
|
|
rows = table.find_all("tr")
|
|
|
|
for row in rows:
|
|
cols = row.find_all(["td", "th"])
|
|
if len(cols) >= 8:
|
|
try:
|
|
row_data = [col.get_text(strip=True) for col in cols]
|
|
data_rows.append(row_data)
|
|
except Exception:
|
|
continue
|
|
|
|
if not data_rows:
|
|
print("错误:未解析到任何数据")
|
|
return None
|
|
|
|
print(f"成功解析 {len(data_rows)} 条数据")
|
|
return data_rows
|
|
|
|
except requests.exceptions.RequestException as e:
|
|
last_error = e
|
|
print(f"网络请求错误(第 {attempt} 次):{e}")
|
|
if attempt < MAX_RETRIES:
|
|
continue
|
|
return None
|
|
except Exception as e:
|
|
last_error = e
|
|
print(f"解析错误(第 {attempt} 次):{e}")
|
|
if attempt < MAX_RETRIES:
|
|
continue
|
|
return None
|
|
|
|
print(f"抓取失败,共尝试 {MAX_RETRIES} 次,最后错误:{last_error}")
|
|
return None
|
|
|
|
|
|
def save_to_excel(data_rows):
|
|
"""保存数据到 Excel 文件
|
|
|
|
输出格式与 lottery.py 和 app.py 兼容:
|
|
- 列名: 开奖时间 | 期数 | 号码 | 开机号 | 和值特征 | 奇偶比 | 大小比 | 奇偶形态 | 跨度 | 其他
|
|
- 号码列为 6 红球 + 1 蓝球的拼接字符串 (如 '09101316192108')
|
|
- 第一行为列名,数据从第二行开始
|
|
"""
|
|
if not data_rows:
|
|
print("无数据可保存")
|
|
return False
|
|
|
|
try:
|
|
# 跳过网页表格的 header 行 (第一行通常是中文标题)
|
|
# 检查第一行是否是 header (包含 '开奖时间' 或 '期数' 等关键词)
|
|
first_row = data_rows[0]
|
|
header_keywords = {'开奖时间', '期数', '号码', '开奖日期'}
|
|
if any(kw in str(first_row) for kw in header_keywords):
|
|
data_rows = data_rows[1:]
|
|
print(f"跳过 header 行,实际数据 {len(data_rows)} 条")
|
|
|
|
# 标准列名 (与 lottery.py 期望一致)
|
|
standard_columns = ['开奖时间', '期数', '号码', '开机号', '和值特征', '奇偶比', '大小比', '奇偶形态', '跨度', '其他']
|
|
|
|
# 统一每行列数
|
|
num_cols = min(len(row) for row in data_rows)
|
|
data_rows = [row[:num_cols] for row in data_rows]
|
|
|
|
# 使用标准列名 (截取或补全)
|
|
if num_cols <= len(standard_columns):
|
|
actual_columns = standard_columns[:num_cols]
|
|
else:
|
|
actual_columns = standard_columns + [f'列{i+1}' for i in range(num_cols - len(standard_columns))]
|
|
|
|
df = pd.DataFrame(data_rows, columns=actual_columns)
|
|
|
|
# 保存为 Excel
|
|
df.to_excel(OUTPUT_FILE, index=False, engine="openpyxl")
|
|
|
|
print(f"[{datetime.now()}] 数据已保存到:{OUTPUT_FILE}")
|
|
print(f"共保存 {len(df)} 条记录")
|
|
return True
|
|
|
|
except Exception as e:
|
|
print(f"保存 Excel 错误:{e}")
|
|
return False
|
|
|
|
|
|
def main():
|
|
"""主函数"""
|
|
print("=" * 60)
|
|
print("双色球历史数据抓取工具")
|
|
print("=" * 60)
|
|
|
|
# 抓取数据
|
|
data = fetch_lottery_data()
|
|
|
|
if data:
|
|
# 保存数据
|
|
success = save_to_excel(data)
|
|
if success:
|
|
print("=" * 60)
|
|
print("任务完成!")
|
|
print("=" * 60)
|
|
return 0
|
|
else:
|
|
print("保存失败")
|
|
return 1
|
|
else:
|
|
print("抓取失败")
|
|
return 1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
exit(main()) |