数据集 | 10米分辨率全球土地覆盖产品

import requests
from bs4 import BeautifulSoup
import time

url='http://data.ess.tsinghua.edu.cn/fromglc10_2017v01.html'
head = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) \
Chrome/80.0.3987.132 Safari/537.36'}

url_data=requests.get(url)
contend = BeautifulSoup(url_data.content,'lxml')
trs = contend.find_all('tr')
tif_url=[i.find_all('td')[1].find('a')['href']  for i in trs]

#毕竟下载那么多数据，总有失败的，把下载失败的链接保存起来，接下来可以重新下载
fail_url=[]

for i in tif_url:       
    try:
        tif_data = requests.get(i, headers=head, stream=True, timeout=15)
        open(r'替换为你的路径\{}'.format(i.split('/')[-1]), 'wb').write(tif_data.content)
        del tif_data
        print("done")        
    except requests.exceptions.RequestException as e:                
        print(i.split('/')[-1],'失败')
        fail_url.append(i)
        continue              
    time.sleep(3)

#对失败的链接重新下载
for i in fail_url:
        try:
        tif_data = requests.get(i, headers=head, stream=True, timeout=15)
        open(r'替换为你的路径\{}'.format(i.split('/')[-1]), 'wb').write(tif_data.content)
        del tif_data
        print("done")        
    except requests.exceptions.RequestException as e:                
        print(i.split('/')[-1],'又失败了，就先不下载它了')
        continue              
    time.sleep(3)