python Requsets下載開源網(wǎng)站的代碼(帶索引 數(shù)據(jù))

import requests
import re
import os
from gooey import Gooey, GooeyParser
import time

s = requests.Session()

def judgeTypeOfPath(name):
    '''
    判斷該路徑是文件還是文件夾
      :param name: 路徑名稱
      :return:True->文件;False->文件夾
    '''
    if name[-1] == '/':
        return False
    else:
        return True


def makeDirOfPath(path):
    '''
    創(chuàng)建文件夾
    :param path: 文件夾名稱以及路徑
    :return: True->創(chuàng)建成功;False->創(chuàng)建失敗
    '''
    if not os.path.isdir(path):
        os.mkdir(path)
    if not os.path.isdir(path):
        return False
    return True

def getPath(url):
    '''
    獲取網(wǎng)頁路徑列表
    :param url: 當(dāng)前網(wǎng)頁路徑
    :return: 路徑列表
    '''
    baseResponse = s.get(url=url, stream=True,verify=False).text
    listOfDirOrFilesTemp = re.findall(r'li>a href=".*?" rel="external nofollow" >', baseResponse)
    listOfDirOrFiles = []
    for i in range(len(listOfDirOrFilesTemp)):
        listOfDirOrFiles.append(listOfDirOrFilesTemp[i].split("\"")[1])
    return listOfDirOrFiles[1:len(listOfDirOrFiles) + 1]

def rfSearch(listOfPath,url, nowPath):
    '''
    遞歸尋找目錄、路徑,并下載文件
    :param listOfPath: 當(dāng)前目錄下文件以及文件夾目錄列表
    :param nowPath: 現(xiàn)在所在路徑
    :return:
    '''
    newList = listOfPath[:]
    if not newList:
        return
    for i in range(len(newList)):
        if not judgeTypeOfPath(newList[i]):
            u = nowPath + newList[i][0:len(newList[i])]
            makeDirOfPath(u)
            tempPath=nowPath + newList[i][0:len(newList[i])+1]
            tempUrl=url+newList[i][0:len(newList[i])+1]
            u=getPath(tempUrl)
            rfSearch(u,tempUrl,tempPath)
        else:
            print(f'開始下載{newList[i]}...')
            t1=time.time()
            u = nowPath + newList[i]
            m=url+newList[i]
            if not os.path.exists(u):
                r = s.get(m, stream=True,verify=False)
                f = open(u, "wb")
                for chunk in r.iter_content(chunk_size=10240):
                    if chunk:
                        f.write(chunk)
                f.close()
            t2=time.time()
            print(f'{newList[i]}下載完成\t\t用時  {t2-t1}')

@Gooey(
    program_name='isric數(shù)據(jù)下載器',
    encoding="utf-8", )
def main():
    parser = GooeyParser(description="isric數(shù)據(jù)下載器")
    parser.add_argument('--url',default=r'https://files.isric.org/soilgrids/latest/data/')
    parser.add_argument('--path', widget="DirChooser", default=r'F:/isricData/')
    args = parser.parse_args()
    url=args.url
    nowPath = args.path
    u = getPath(url)
    rfSearch(u, url,nowPath)
###如果不需要可視化，則不用gooey，可以將上面部分替換如下
#@Gooey(
#    program_name='isric數(shù)據(jù)下載器',
#   encoding="utf-8", )
#上面三行刪除即可
###main函數(shù)替換成下面部分：
# def main():
#     url=r'https://files.isric.org/soilgrids/latest/data/'#在此處修改地址鏈接
#     nowPath = r'F:/isricData/'#在此處修改文件保存地址
#     u = getPath(url)
#     rfSearch(u, url,nowPath)

if __name__ == "__main__":
    main()