from selenium import webdriver
from time import sleep
import tempfile
import os,sys
import pandas as pd
import geopandas as gpd
import time
# 构建查询地址
def GetURL(ProductID,StartTime,EndTime,search_file):
# 查询边界
data = gpd.GeoDataFrame.from_file(search_file)
bbox = (data.bounds.values)[0].tolist()
# 研究区范围，左上角和右下角。根据需要构造字符串
Area = str(round(bbox[0],1))+','+str(round(bbox[3],1))+','+str(round(bbox[2],1))+','+str(round(bbox[1],1))
# 输入 MODIS 轨道矢量
modis_grid_file = 'E:\***\modis_WGS84_grid_world.shp'
modis_grid = gpd.GeoDataFrame.from_file(modis_grid_file)
# 查询边界覆盖的轨道中心坐标
modis_intersection = modis_grid[modis_grid.intersects(data.geometry[0])]
path_row = 'Tile:'
for mv in modis_intersection.values:
path_row += "H"+str(mv[1])+"V"+str(mv[2])+","
# 根据以上信息构建 Search 页的网址
path_row = path_row[0:-1]
url='
return url
# 使用 Selenium 查询影像
def SearchFileList(url):
# 创建文件夹，命名规则为程序运行的时刻
# 将使用 selenium 下载的文件使用该文件夹存储
csvdir = 'E:\\***\\' + str(time.time()).replace('.','')
os.mkdir(csvdir)
# 配置 selenium 的参数
options = webdriver.ChromeOptions()
prefs = {'profile.default_content_settings.popups': 0, 'download.default_directory': csvdir}
options.add_experimental_option('prefs', prefs)
chromedriver = r"C:\***\Google\Chrome\Application\chromedriver.exe"#chromedriver.exe 的本地路径
# options.add_argument('--headless') # 有无浏览器界面模式，根据需要设置
driver = webdriver.Chrome(executable_path=chromedriver,options=options)
# 自动打开 Search 页
driver.get(url)
# 浏览器打开 Search 页后，外汇跟单gendan5.com还要留足时间让服务器进行数据检索
# 所以这里 sleep50 秒，可以根据网速自行设定
sleep(50)
# 当然也可以判断搜索结果，也就是包含 csv 的标签是否出现
# WebDriverWait(driver,
# 下载 csv 文件
# 找到文本包含 csv 的标签
# csvElement = driver.find_element_by_link_text('csv')
csvElement = driver.find_element_by_xpath('// *[ @ id = "tab4download"] / a[2]')
# 点击下载
csvElement.click()
# 留下下载 csv 文件的时间
sleep(20)
# 关闭浏览器
driver.quit()
return csvdir
# 下载影像
def MODISDown(FileDir):
# 获取下载的 csv 文件的文件名
csvfilename = os.listdir(FileDir)[0]
# 构造文件路径
csvfilepath = os.path.join(FileDir, csvfilename)
# print(csvfilepath)
csvvalues = pd.read_csv(csvfilepath).values
os.remove(csvfilepath)
os.rmdir(FileDir)
# 下载数据
file_count = 0
for cv in csvvalues:
file_count += 1
# 构建数据的下载链接
modislink='[1]
outdir = 'E:/***/MODIS/'+(cv[1].split("/"))[5]
# outdir = 'E:/Temp/' + (cv[1].split("/"))[5]
if not os.path.isdir(outdir):
os.mkdir(outdir)
path = outdir + '/' + (cv[1].split("/"))[7]
if not os.path.exists(path):
print("({0}/{1}) Downloading {2}".format(file_count, len(csvvalues), modislink.split("/")[-1]))
with open(path, 'w+b') as out:
geturl(modislink, out)
# 获取下载链接并下载影像数据
def geturl(url,out=None):
USERAGENT = 'tis/download.py_1.0--' + sys.version.replace('\n', '').replace('\r', '')
headers = { 'user-agent' : USERAGENT }
token = '******' # 你的 token, 可登陆 Earthdata 网站后在 profile 中得到
headers['Authorization'] = 'Bearer ' + token
try:
import ssl
CTX = ssl.SSLContext(ssl.PROTOCOL_TLSv1_2)
from urllib.request import urlopen, Request, URLError, HTTPError
try:
response = urlopen(Request(url, headers=headers), context=CTX)
if out is None:
return response.read().decode('utf-8')
else:
start = time.time()
# 将连接中的下载文件写入临时文件 并返回文件写入进度
chunk_read(response, out, report_hook=chunk_report)
elapsed = max(time.time() - start,1.0)
# 平均下载速度
rate = (get_total_size(response) / 1024 ** 2) / elapsed
print("Downloaded {0}b in {1:.2f}secs, Average Rate: {2:.2f}MB/sec".format(get_total_size(response), elapsed, rate))
# shutil.copyfileobj(response, out)
except HTTPError as e:
print('HTTP GET error code: %d' % e.code(), file=sys.stderr)
print('HTTP GET error message: %s' % e.message, file=sys.stderr)
except URLError as e:
print('Failed to make request: %s' % e.reason, file=sys.stderr)
return None
except AttributeError:
# OS X Python 2 and 3 don't support tlsv1.1+ therefore... curl
import subprocess
try:
args = ['curl', '--fail', '-sS', '-L', '--get', url]
for (k,v) in headers.items():
args.extend(['-H', ': '.join([k, v])])
if out is None:
# python3's subprocess.check_output returns stdout as a byte string
result = subprocess.check_output(args)
return result.decode('utf-8') if isinstance(result, bytes) else result
else:
subprocess.call(args, stdout=out)
except subprocess.CalledProcessError as e:
print('curl GET error message: %' + (e.message if hasattr(e, 'message') else e.output), file=sys.stderr)
return None
# chunk_read modified from
def chunk_read( response, local_file, chunk_size=10240, report_hook=None):
# 完整文件大小
file_size = get_total_size(response)
# 下载文件大小
bytes_so_far = 0
# 文件写入本地
while 1:
try:
# 从地址中读取固定大小文件对象
chunk = response.read(chunk_size)
except:
sys.stdout.write("\n > There was an error reading data. \n")
break
try:
# 将读取出的文件对象写入本地文件
local_file.write(chunk)
except TypeError:
local_file.write(chunk.decode(local_file.encoding))
# 写入完成即更新已下载文件大小
bytes_so_far += len(chunk)
if not chunk:
break
if report_hook:
# 获取下载进度
report_hook(bytes_so_far, file_size)
return bytes_so_far
def chunk_report( bytes_so_far, file_size):
if file_size is not None:
# 计算下载进度百分比
percent = float(bytes_so_far) / file_size
percent = round(percent * 100, 2)
sys.stdout.write(" > Downloaded %d of %d bytes (%0.2f%%)\r" %
(bytes_so_far, file_size, percent))
else:
# We couldn't figure out the size.
sys.stdout.write(" > Downloaded %d of unknown Size\r" % (bytes_so_far))
def get_total_size(response):
try:
file_size = response.info().getheader('Content-Length').strip()
except AttributeError:
try:
file_size = response.getheader('Content-Length').strip()
except AttributeError:
print ("> Problem getting size")
return None
return int(file_size)
if __name__ == "__main__":
# 定义要下载数据的信息
ProductID = 'MOD021KM--61/' # 产品号 #sys.argv[1]#
# 设置数据的起始和截至时间。其实就是根据需要构造一个简单的字符串
StartTime = '2020-06-01' # 开始时间 #sys.argv[2]#
EndTime = '2020-06-03' # 截至日期 #sys.argv[3]#
search_file = r'E:\***\ 北京市 .shp' # 查询范围 #sys.argv[4]#
# 构建查询地址
url = GetURL(ProductID,StartTime,EndTime,search_file)
# 获取数据列表
csvdir = SearchFileList(url)
# 根据列表下载数据
MODISDown(csvdir)
