数据获取 | 如何下载指定时间范围的1°分辨率的FNL数据

用户11172986

发布于 2024-12-05 07:36:49

16000

代码可运行

文章被收录于专栏：气python风雨气python风雨

运行总次数：0

代码可运行

温馨提示

由于可视化代码过长隐藏，可点击运行Fork查看若没有成功加载可视化图，点击运行可以查看 ps:隐藏代码在【代码已被隐藏】所在行，点击所在行，可以看到该行的最右角，会出现个三角形，点击查看即可

前言

近来有读者来信说我之前写的fnl下载脚本不管用了

我测试一下，确实如此

去官网一看是网址改了，于是有了这期

近来真是挺多新闻的，昨天韩国上演第五共和国复刻活动，今天又刷到琼瑶轻生啥的

那么言归正传

项目目标

本项目旨在解决下载指定时间范围的FNL数据

官方的示例下载脚本如下

#!/usr/bin/env python  
"""  
Python script to download selected files from rda.ucar.edu.  
After you save the file, don't forget to make it executable  
i.e. - "chmod 755 <name_of_script>"  
"""  
import sys, os  
from urllib.request import build_opener  

opener = build_opener()  

filelist = [  
  'https://data.rda.ucar.edu/d083002/grib2/2024/2024.09/fnl_20240901_00_00.grib2',  
  'https://data.rda.ucar.edu/d083002/grib2/2024/2024.09/fnl_20240901_06_00.grib2',  
  'https://data.rda.ucar.edu/d083002/grib2/2024/2024.09/fnl_20240901_12_00.grib2',  
  'https://data.rda.ucar.edu/d083002/grib2/2024/2024.09/fnl_20240901_18_00.grib2'  
]  

for file in filelist:  
    ofile = os.path.basename(file)  
    sys.stdout.write("downloading " + ofile + " ... ")  
    sys.stdout.flush()  
    infile = opener.open(file)  
    outfile = open(ofile, "wb")  
    outfile.write(infile.read())  
    outfile.close()  
    sys.stdout.write("done\n")

那么我们只需要根据其网址编写字符，变动一下日期即可

脚本

import sys
import os
import datetime
from urllib.request import urlretrieve

def generate_gdas1_urls(start_date, end_date):
    """生成指定日期范围内的GDAS1数据文件URL列表"""
    base_url = "https://data.rda.ucar.edu/d083002/grib2/{year}/{year}.{month:02d}/fnl_{year}{month:02d}{day:02d}_{hour:02d}_00.grib2"
    urls = []
    current_date = start_date
    while current_date <= end_date:
        # 每6小时一个文件，分别对应00, 06, 12, 18小时的文件
        for hour in [0, 6, 12, 18]:  
            url = base_url.format(year=current_date.year, month=current_date.month, day=current_date.day, hour=hour)
            urls.append(url)
            print(url)
        current_date += datetime.timedelta(days=1)  # 每天一个日期
    return urls

def download_files(urls):
    """下载文件列表中的所有文件"""
    for url in urls:
        filename = os.path.basename(url)
        print(f"Downloading {filename} ... ", end='', flush=True)
        try:
            urlretrieve(url, filename)
            print("done")
        except Exception as e:
            print(f"Failed: {e}")

if __name__ == "__main__":
    start_date = datetime.datetime(2024, 9, 1)  # 下载开始日期
    end_date = datetime.datetime(2024, 9, 2)    # 下载结束日期
    
    file_urls = generate_gdas1_urls(start_date, end_date)
    download_files(file_urls)

传参型脚本

那么在服务器上大家会习惯使用传参进行下载，这样方便很多用法: python download_gdas1.py <start_date> <end_date> 日期格式： YYYYMMDDHH, for example: 2024090100

import sys
import os
from datetime import datetime, timedelta
from urllib.request import urlretrieve

def generate_gdas1_urls(start_date, end_date):
    """Generate URLs for the 1° resolution GDAS1 files within the specified date range."""
    base_url = "https://data.rda.ucar.edu/d083002/grib2/{year}/{year}.{month:02d}/fnl_{year}{month:02d}{day:02d}_{hour:02d}_00.grib2"
    urls = []
    current_date = start_date
    while current_date <= end_date:
        # 每6小时一个文件，分别对应00, 06, 12, 18小时的文件
        for hour in [0, 6, 12, 18]:
            if current_date.hour == hour:
                url = base_url.format(
                    year=current_date.year,
                    month=current_date.month,
                    day=current_date.day,
                    hour=hour
                )
                urls.append(url)
                print(url)
        current_date += timedelta(hours=6)  # 每6小时一个时间点
    return urls

def download_files(urls):
    """Download all files listed in the URLs."""
    for url in urls:
        filename = os.path.basename(url)
        print(f"Downloading {filename} ... ", end='', flush=True)
        try:
            urlretrieve(url, filename)
            print("done")
        except Exception as e:
            print(f"Failed: {e}")

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: python download_gdas1.py <start_date> <end_date>")
        print("Date format should be YYYYMMDDHH, for example: 2024090100")
        sys.exit(1)

    start_str = sys.argv[1]
    end_str = sys.argv[2]

    try:
        # 解析命令行参数为datetime对象
        start_date = datetime.strptime(start_str, "%Y%m%d%H")
        end_date = datetime.strptime(end_str, "%Y%m%d%H")

        # 确保开始日期不超过结束日期
        if start_date > end_date:
            print("Error: Start date must not be later than end date.")
            sys.exit(1)

        file_urls = generate_gdas1_urls(start_date, end_date)
        download_files(file_urls)

    except ValueError as e:
        print(f"Invalid date format: {e}")
        print("Date format should be YYYYMMDDHH, for example: 2024090100")
        sys.exit(1)