python获取彩票开奖结果统计（双色球）

请求头：https://www.cwl.gov.cn/cwl_admin/front/cwlkj/search/kjxx/findDrawNotice?

载荷：

params = {
    "name": "ssq",
    "issueCount": "",
    "issueStart": "",
    "issueEnd": "",
    "dayStart": "",
    "dayEnd": "",
    "pageNo": "1",
    "pageSize": "30",
    "week": "",
    "systemType": "PC"
}

按期数查询，issueCount，最近1000期即1000

按期号查询，issueStart，issueEnd。比如2020001-2024001

按日期查询，dayStart，dayEnd，比如2020-01-01到2024-01-01

可以自定义输入，也可写好在参数里，另外添加标头和cookies自行添加

header = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36",
    "cookie": ""
}

响应是json

def fetch_data(url, params):
    try:
        response = requests.get(url, headers=header, params=params)
        response.raise_for_status()  # Raises HTTPError for bad responses (4xx and 5xx)
        response.encoding = 'utf-8'
        return response.json()
    except requests.RequestException as e:
        print(f"请求发生错误: {e}")
        return None
    except json.JSONDecodeError:
        print("无法解码 JSON 数据")
        return None

获取响应中的页数用来作请求的次数

# 获取数据
res = fetch_data(url, params)
if res is None:
    exit()

pagenum = res.get("pageNum", 0)
print(f"总页数: {pagenum}")

data = []
for i in range(1, int(pagenum) + 1):
    params["pageNo"] = str(i)
    jsondata = fetch_data(url, params)
    if jsondata is None or "result" not in jsondata:
        continue

    for result in jsondata["result"]:
        code = result["code"]
        red = result["red"].split(',')
        blue = result["blue"]
        date = result["date"]
        week = result["week"]
        print(f"期数：{code} 红球：{red} 蓝球：{blue} 日期：{date} 星期：{week}")
        data.append([code, date, week] + red + [blue])

保存到excel

# 创建 DataFrame
columns = ["期数", "日期", "星期", "红球号码1", "红球号码2", "红球号码3", "红球号码4", "红球号码5", "红球号码6", "蓝球号码"]
df = pd.DataFrame(data, columns=columns)

output_path = "双色球结果和统计.xlsx"

# 保存开奖结果
try:
    book = load_workbook(output_path)
    with pd.ExcelWriter(output_path, engine='openpyxl', mode='a', if_sheet_exists='replace') as writer:
        writer.book = book
        writer.sheets = {ws.title: ws for ws in book.worksheets}
        df.to_excel(writer, sheet_name="开奖结果", index=False)
except FileNotFoundError:
    df.to_excel(output_path, sheet_name="开奖结果", index=False)
except InvalidFileException:
    df.to_excel(output_path, sheet_name="开奖结果", index=False)

print(f"开奖结果已保存到 {output_path}")

 完整代码，运行生成红球和蓝球的热力图，分布图及excel表格，需要自己去网站链接复制一个cookies如果需要

import requests
import json
import pandas as pd
from openpyxl import load_workbook
from openpyxl.utils.exceptions import InvalidFileException
from openpyxl.styles import PatternFill
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.font_manager as fm
import random

# Configuration
header = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36",
    "cookie": ""
}
url = "https://www.cwl.gov.cn/cwl_admin/front/cwlkj/search/kjxx/findDrawNotice?"

# 获取用户输入的查询参数
query_type = input("1: 按期数查询\n2: 按期号查询\n3: 按日期查询\n请选择查询方式:")
params = {
    "name": "ssq",
    "issueCount": "",
    "issueStart": "",
    "issueEnd": "",
    "dayStart": "",
    "dayEnd": "",
    "pageNo": "1",
    "pageSize": "30",
    "week": "",
    "systemType": "PC"
}
if query_type == '1':
    params["issueCount"] = input("最近100期即100\n请输入期数：")
elif query_type == '2':
    params["issueStart"] = input("请输入起始期号：")
    params["issueEnd"] = input("请输入结束期号：")
elif query_type == '3':
    params["dayStart"] = input("请输入起始日期（格式：YYYY-MM-DD）：")
    params["dayEnd"] = input("请输入结束日期（格式：YYYY-MM-DD）：")
else:
    print("无效的选择")
    exit()

def fetch_data(url, params):
    try:
        response = requests.get(url, headers=header, params=params)
        response.raise_for_status()  # Raises HTTPError for bad responses (4xx and 5xx)
        response.encoding = 'utf-8'
        return response.json()
    except requests.RequestException as e:
        print(f"请求发生错误: {e}")
        return None
    except json.JSONDecodeError:
        print("无法解码 JSON 数据")
        return None

# 获取数据
res = fetch_data(url, params)
if res is None:
    exit()

pagenum = res.get("pageNum", 0)
print(f"总页数: {pagenum}")

data = []
for i in range(1, int(pagenum) + 1):
    params["pageNo"] = str(i)
    jsondata = fetch_data(url, params)
    if jsondata is None or "result" not in jsondata:
        continue

    for result in jsondata["result"]:
        code = result["code"]
        red = result["red"].split(',')
        blue = result["blue"]
        date = result["date"]
        week = result["week"]
        print(f"期数：{code} 红球：{red} 蓝球：{blue} 日期：{date} 星期：{week}")
        data.append([code, date, week] + red + [blue])

# 创建 DataFrame
columns = ["期数", "日期", "星期", "红球号码1", "红球号码2", "红球号码3", "红球号码4", "红球号码5", "红球号码6", "蓝球号码"]
df = pd.DataFrame(data, columns=columns)

output_path = "双色球结果和统计.xlsx"

# 保存开奖结果
try:
    book = load_workbook(output_path)
    with pd.ExcelWriter(output_path, engine='openpyxl', mode='a', if_sheet_exists='replace') as writer:
        writer.book = book
        writer.sheets = {ws.title: ws for ws in book.worksheets}
        df.to_excel(writer, sheet_name="开奖结果", index=False)
except FileNotFoundError:
    df.to_excel(output_path, sheet_name="开奖结果", index=False)
except InvalidFileException:
    df.to_excel(output_path, sheet_name="开奖结果", index=False)

print(f"开奖结果已保存到 {output_path}")

# Step 2: 统计和保存结果到一个 Excel 文件中的单个工作表
try:
    df = pd.read_excel(output_path, sheet_name="开奖结果")
except Exception as e:
    print(f"读取文件时发生错误: {e}")
    exit()

# 初始化统计字典
red_counts = {str(i): {f"位置{j+1}": 0 for j in range(6)} for i in range(1, 34)}
blue_counts = {str(i): 0 for i in range(1, 17)}

# 初始化星期二、四、日统计字典
weekdays = {"星期二": "二", "星期四": "四", "星期日": "日"}
red_counts_week = {day: {str(i): {f"位置{j+1}": 0 for j in range(6)} for i in range(1, 34)} for day in weekdays.values()}
blue_counts_week = {day: {str(i): 0 for i in range(1, 17)} for day in weekdays.values()}

# 统计每个数字的出现次数
for index, row in df.iterrows():
    red_numbers = row[3:9].dropna().astype(int)
    blue_number = row[9]
    week = row[2]
    
    for j, num in enumerate(red_numbers):
        num_str = str(num).strip()
        if num_str in red_counts:
            red_counts[num_str][f"位置{j+1}"] += 1
        if week in weekdays.values():
            if num_str in red_counts_week[week]:
                red_counts_week[week][num_str][f"位置{j+1}"] += 1
    
    blue_number_str = str(blue_number).strip()
    if blue_number_str in blue_counts:
        blue_counts[blue_number_str] += 1
    if week in weekdays.values():
        if blue_number_str in blue_counts_week[week]:
            blue_counts_week[week][blue_number_str] += 1

# 计算总期数
total_periods = len(df)
if total_periods == 0:
    print("数据为空，没有统计结果。")
    exit()

# 计算每个数字的概率并将其保存到 DataFrame
red_data = []
for num, counts in red_counts.items():
    row = {"号码": num}
    for pos, count in counts.items():
        row[f"{pos}次"] = count
        row[f"{pos}概率"] = count / total_periods
    red_data.append(row)

blue_data = []
for num, count in blue_counts.items():
    row = {"号码": num, "蓝球次数": count, "蓝球概率": count / total_periods}
    blue_data.append(row)

# 计算星期二、四、日的统计
red_data_week = {day: [] for day in weekdays.values()}
blue_data_week = {day: [] for day in weekdays.values()}

for day in weekdays.values():
    total_periods_week = len(df[df["星期"] == day])
    for num, counts in red_counts_week[day].items():
        row = {"号码": num}
        for pos, count in counts.items():
            row[f"{pos}次（星期{day}）"] = count
            row[f"{pos}概率（星期{day}）"] = count / total_periods_week
        red_data_week[day].append(row)
    
    for num, count in blue_counts_week[day].items():
        row = {"号码": num, f"蓝球次数（星期{day}）": count, f"蓝球概率（星期{day}）": count / total_periods_week}
        blue_data_week[day].append(row)

# 合并红球和蓝球数据
for red in red_data:
    num = red["号码"]
    for blue in blue_data:
        if blue["号码"] == num:
            red["蓝球次数"] = blue["蓝球次数"]
            red["蓝球概率"] = blue["蓝球概率"]
            break
    else:
        red["蓝球次数"] = 0
        red["蓝球概率"] = 0.0

# 合并星期二、四、日的红球和蓝球数据
for day in weekdays.values():
    for red in red_data_week[day]:
        num = red["号码"]
        for blue in blue_data_week[day]:
            if blue["号码"] == num:
                red[f"蓝球次数（星期{day}）"] = blue[f"蓝球次数（星期{day}）"]
                red[f"蓝球概率（星期{day}）"] = blue[f"蓝球概率（星期{day}）"]
                break
        else:
            red[f"蓝球次数（星期{day}）"] = 0
            red[f"蓝球概率（星期{day}）"] = 0.0

red_counts_df = pd.DataFrame(red_data)
red_counts_week_dfs = {day: pd.DataFrame(data) for day, data in red_data_week.items()}

# 保存结果到新的 Excel 文件中的统计结果sheet
try:
    with pd.ExcelWriter(output_path, engine='openpyxl', mode='a', if_sheet_exists='replace') as writer:
        red_counts_df.to_excel(writer, sheet_name="统计结果", index=False)
        for day, df in red_counts_week_dfs.items():
            df.to_excel(writer, sheet_name=f"星期{day}统计结果", index=False)
    print(f"统计结果已保存到 {output_path}")
except Exception as e:
    print(f"保存文件时发生错误: {e}")

# 加载保存后的Excel文件，进行高亮处理
try:
    book = load_workbook(output_path)
    sheet = book["统计结果"]
    
    yellow_fill = PatternFill(start_color="FFFF00", end_color="FFFF00", fill_type="solid")
    red_fill = PatternFill(start_color="FF0000", end_color="FF0000", fill_type="solid")

    for col in range(3, 12, 2):  # 概率列
        values = [cell[0].value for cell in sheet.iter_cols(min_row=2, min_col=col, max_col=col, values_only=True)]
        if not values:  # 如果没有值，继续下一列
            continue
        max_value = max(values)
        min_value = min(values)

        for cell in sheet.iter_cols(min_row=2, min_col=col, max_col=col):
            for c in cell:
                if c.value == max_value:
                    c.fill = red_fill
                elif c.value == min_value:
                    c.fill = yellow_fill

    # 保存带有高亮的Excel文件
    book.save(output_path)
    print(f"高亮处理已完成并保存到 {output_path}")
except Exception as e:
    print(f"高亮处理时发生错误: {e}")


# 设置中文字体
plt.rcParams['font.sans-serif'] = ['SimHei']  # 指定默认字体
plt.rcParams['axes.unicode_minus'] = False    # 正常显示负号

# 创建红球号码出现频率的热力图
red_heatmap_data = pd.DataFrame(red_counts).T.astype(int)
plt.figure(figsize=(12, 8))
sns.heatmap(red_heatmap_data, annot=True, fmt="d", cmap="YlGnBu")
plt.title('红球号码热力图')
plt.savefig('红球号码出现频率热力图.png')  # 自动保存图表
#plt.show()
plt.close()

# 创建蓝球号码出现频率的热力图
blue_heatmap_data = pd.DataFrame.from_dict(blue_counts, orient='index', columns=['次数']).astype(int)
plt.figure(figsize=(8, 6))
sns.heatmap(blue_heatmap_data.T, annot=True, fmt="d", cmap="YlGnBu")
plt.title('蓝球号码热力图')
plt.savefig('蓝球号码出现频率热力图.png')  # 自动保存图表
#plt.show()
plt.close()

# 创建红球号码出现频率的分布图
red_numbers_total_counts = {str(i): 0 for i in range(1, 34)}
for num, pos_counts in red_counts.items():
    for pos, count in pos_counts.items():
        red_numbers_total_counts[num] += count

red_numbers_series = pd.Series(red_numbers_total_counts).sort_index().astype(int)
plt.figure(figsize=(12, 8))
sns.barplot(x=red_numbers_series.index, y=red_numbers_series.values)
plt.title('红球号码分布')
plt.xlabel('号码')
plt.ylabel('频率')
plt.savefig('红球号码分布.png')  # 自动保存图表
plt.close()

# 创建蓝球号码出现频率的分布图
blue_numbers_series = pd.Series(blue_counts).sort_index().astype(int)
plt.figure(figsize=(8, 6))
sns.barplot(x=blue_numbers_series.index, y=blue_numbers_series.values)
plt.title('蓝球号码分布')
plt.xlabel('号码')
plt.ylabel('频率')
plt.savefig('蓝球号码分布.png')  # 自动保存图表
plt.close()

# 生成推荐号码组合
def generate_recommendations(red_counts, blue_counts, n=5):
    recommendations = []
    red_nums = list(red_counts.keys())
    blue_nums = list(blue_counts.keys())
    
    for _ in range(n):
        red_comb = random.sample(red_nums, 6)
        blue_comb = random.choice(blue_nums)
        recommendations.append((sorted(red_comb), blue_comb))
    
    return recommendations

# 根据统计数据生成推荐号码组合
recommendations = generate_recommendations(red_counts, blue_counts)
print("推荐号码组合:")
for red_comb, blue_comb in recommendations:
    print(f"红球: {red_comb}, 蓝球: {blue_comb}")