python Requsets Download code for open source Web site of with indexed data
- 2021-10-25 07:31:14
- OfStack
Environmental construction
python 3.x
requests packet
re packet
gooey package (for visualization)
Code
import requests
import re
import os
from gooey import Gooey, GooeyParser
import time
s = requests.Session()
def judgeTypeOfPath(name):
'''
Determine whether the path is a file or a folder
:param name: Path name
:return:True-> Documents ;False-> Folder
'''
if name[-1] == '/':
return False
else:
return True
def makeDirOfPath(path):
'''
Create a folder
:param path: Folder name and path
:return: True-> Successful creation ;False-> Failed to create
'''
if not os.path.isdir(path):
os.mkdir(path)
if not os.path.isdir(path):
return False
return True
def getPath(url):
'''
Get a list of page paths
:param url: Current Page Path
:return: Path list
'''
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):
'''
Recursively find directories and paths , And download the file
:param listOfPath: List of files and folders in the current directory
:param nowPath: Path on which you are now
: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' Start downloading {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]} Download complete \t\t Time {t2-t1}')
@Gooey(
program_name='isric Data downloader ',
encoding="utf-8", )
def main():
parser = GooeyParser(description="isric Data downloader ")
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)
### If visualization is not required, no gooey You can replace the above section with the following
#@Gooey(
# program_name='isric Data downloader ',
# encoding="utf-8", )
# Above 3 You can delete the row
###main Function with the following section:
# def main():
# url=r'https://files.isric.org/soilgrids/latest/data/'# Modify the address link here
# nowPath = r'F:/isricData/'# Modify the file save address here
# u = getPath(url)
# rfSearch(u, url,nowPath)
if __name__ == "__main__":
main()