Python教程：使用API高效抓取GBGB赛狗结果数据（指定日期与赛道）

from datetime import datetime, timedelta
import requests
import json

# 定义数据存储列表
json_list = []

# API基础URL和固定参数
base_url = "https://api.gbgb.org.uk/api/results"
params = {
    'page': '1',
    'itemsPerPage': '200', # 假设每页最多200条，可根据实际情况调整
    'race_type': 'race'
}

# 定义抓取数据的年份和日期范围
year_to_scrape = 2023
start_month = 10
end_month = 12 # 包含结束月份

for month in range(start_month, end_month + 1):
    # 计算当前月份的天数
    # 简化处理，不考虑闰年，2月固定28天
    if month == 2:
        get_days_in_month = 28
    elif month in [4, 6, 9, 11]:
        get_days_in_month = 30
    else:
        get_days_in_month = 31

    for day in range(1, get_days_in_month + 1):
        # 格式化日期为 YYYY-MM-DD
        # 使用 f-string 的 :02d 格式化保证月份和日期始终是两位数
        params['date'] = f'{year_to_scrape}-{month:02d}-{day:02d}'
        # ... 后续进行API请求

        try:
            # 使用requests发送GET请求
            response = requests.get(base_url, params=params)
            response.raise_for_status()  # 检查HTTP请求是否成功 (200 OK)

            # 将响应转换为Python字典
            page_context_dict = response.json()
            items = page_context_dict.get('items', []) # 获取'items'列表，若不存在则为空列表

            # ... 后续进行数据筛选
        except requests.exceptions.HTTPError as errh:
            print(f"HTTP Error for date {params['date']}: {errh}")
        except requests.exceptions.ConnectionError as errc:
            print(f"Error Connecting for date {params['date']}: {errc}")
        except requests.exceptions.Timeout as errt:
            print(f"Timeout Error for date {params['date']}: {errt}")
        except requests.exceptions.RequestException as err:
            print(f"Oops: Something Else for date {params['date']}: {err}")
        except json.JSONDecodeError as json_err:
            print(f"JSON Decode Error for date {params['date']}: {json_err}")

            specific_track_items = []
            desired_track = "Swindon" # 指定您想要抓取的赛道名称

            for item in items:
                # 检查'trackName'是否存在且与目标赛道匹配
                if "trackName" in item and item["trackName"] == desired_track:
                    specific_track_items.append(item)

            # 将筛选后的数据添加到总列表中
            json_list.extend(specific_track_items)

import requests
import json
from datetime import datetime, timedelta
import calendar # 用于更精确地获取月份天数

json_list = []

base_url = "https://api.gbgb.org.uk/api/results"
params = {
    'page': '1',
    'itemsPerPage': '200', # 可根据API限制和需求调整
    'race_type': 'race'
}

# --- 配置抓取参数 ---
year_to_scrape = 2023
start_month = 10
end_month = 12 # 包含结束月份
desired_track = "Swindon" # 替换为您想要抓取的赛道名称
output_filename = 'gbgb_results_swindon.json' # 输出文件名

print(f"开始抓取 {year_to_scrape} 年 {start_month} 月到 {end_month} 月，赛道：{desired_track} 的数据...")

for month in range(start_month, end_month + 1):
    # 使用calendar模块获取指定月份的天数，考虑闰年
    num_days_in_month = calendar.monthrange(year_to_scrape, month)[1]

    for day in range(1, num_days_in_month + 1):
        # 格式化日期字符串
        params['date'] = f'{year_to_scrape}-{month:02d}-{day:02d}'
        print(f"正在请求数据：{params['date']}")

        try:
            response = requests.get(base_url, params=params)
            response.raise_for_status()

            page_context_dict = response.json()
            items = page_context_dict.get('items', [])

            specific_track_items = []
            for item in items:
                if "trackName" in item and item["trackName"] == desired_track:
                    specific_track_items.append(item)

            if specific_track_items:
                json_list.extend(specific_track_items)
                print(f"  - 成功抓取到 {len(specific_track_items)} 条 {desired_track} 赛道数据。")
            else:
                print(f"  - {desired_track} 赛道在 {params['date']} 没有数据或数据为空。")

        except requests.exceptions.HTTPError as errh:
            print(f"  - HTTP Error for date {params['date']}: {errh}")
        except requests.exceptions.ConnectionError as errc:
            print(f"  - Error Connecting for date {params['date']}: {errc}")
        except requests.exceptions.Timeout as errt:
            print(f"  - Timeout Error for date {params['date']}: {errt}")
        except requests.exceptions.RequestException as err:
            print(f"  - Oops: Something Else for date {params['date']}: {err}")
        except json.JSONDecodeError as json_err:
            print(f"  - JSON Decode Error for date {params['date']}: {json_err}")

# 将所有抓取到的数据写入JSON文件
if json_list:
    with open(output_filename, 'w', encoding='utf-8') as f:
        json.dump(json_list, f, ensure_ascii=False, indent=4)
    print(f"\n数据抓取完成！共抓取到 {len(json_list)} 条数据，已保存至 {output_filename}")
else:
    print("\n没有抓取到任何数据。请检查日期范围、赛道名称或API连接。")