We Keep Coding

While obtaining hash files, some folders and files from the directory are not showing up

My code was working just fine before adding the hash function. I was getting the list of all folders and files in my directory in the Pretty Table. Once I added the hash function, I got maybe 5 of the files in that directory with hashes in the table. I am not sure where I have gone wrong. Please forgive me, I am new to this. We are not learning to code from scratch, but have to modify existing codes to function the way we need it to.
# Python Standard Libaries
import os #file system methode
import hashlib #hashing function
import sys #system methods
import time #time conversions
# Python 3rd Party Libraries
from prettytable import PrettyTable # pip install prettytable
# Local Functions
def GetFileMetaData(fileName):
#obtain file system metadata
try:
metaData = os.stat(fileName) # Use the stat method to obtain meta data
fileSize = metaData.st_size # Extract fileSize and MAC Times
timeLastAccess = metaData.st_atime
timeLastModified = metaData.st_mtime
timeCreated = metaData.st_ctime
macTimeList = [timeLastModified, timeCreated, timeLastAccess] # Group the MAC Times in a List
return True, None, fileSize, macTimeList
except Exception as err:
return False, str(err), None, None
# Psuedo Constants
# Start of the Script
tbl = PrettyTable(['FilePath','FileSize','UTC-Modified', 'UTC-Accessed', 'UTC-Created', 'SHA-256 HASH'])
#file check
while True:
targetFolder = input("Enter Target Folder: ")
if os.path.isdir(targetFolder):
break
else:
print("\nInvalid Folder ... Please Try Again")
print("Walking: ", targetFolder, "\n")
print()
for currentRoot, dirList, fileList in os.walk(targetFolder):
for nextFile in fileList:
fullPath = os.path.join(currentRoot, nextFile)
absPath = os.path.abspath(fullPath)
fileSize = os.path.getsize(absPath)
success, errInfo, fileSize, macList = GetFileMetaData(absPath)
if success:
#convert to readable Greenich Time
modTime = time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(macList[0]))
accTime = time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(macList[1]))
creTime = time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(macList[2]))
#hashing function
with open(absPath, 'rb') as target:
fileContents = target.read()
sha256Obj = hashlib.sha256()
sha256Obj.update(fileContents)
hexDigest = sha256Obj.hexdigest()
tbl.add_row( [ absPath, fileSize,modTime, accTime, creTime, hexDigest] )
tbl.align = "l" # align the columns left justified
# display the table
print (tbl.get_string(sortby="FileSize", reversesort=True))
print("\nScript-End\n")

how can i know the path of a file created by os.makedirs() and store it in a variable for later use?

i want to build a function that convert names from csv to a document in word by docx library and i want to create an empty file with os.makedirs(), the file is created but i cant get its path to later join path with word document to save the document in that file
here is my code:
import docx
import pandas as pd
from datetime import datetime
import os
from docx2pdf import convert
from pathlib import Path
def auto_fill(x,y):
database=pd.read_csv(x)
df=pd.DataFrame(database)
df=df.dropna(axis=0)
targeted_doc=docx.Document(y)
date = datetime.date(datetime.now())
strdate = date.strftime("%m-%d-%Y")
path = strdate
newfile = os.makedirs(path)
newfile_path = path(newfile)
for i in range(len(df.Name)+1):
for n in range (len(targeted_doc.paragraphs)+1):
if targeted_doc.paragraphs[n].text=="Name of trainee":
name=targeted_doc.paragraphs[n].runs[0].text=df.at[i,'Name']
for m in range(len(targeted_doc.paragraphs) + 1):
if targeted_doc.paragraphs[m].text == "tissue date":
date = targeted_doc.paragraphs[n].runs[0].text = strdate
for l in range(len(targeted_doc.paragraphs) + 1):
if targeted_doc.paragraphs[n].text == "tserial number":
sr_num = targeted_doc.paragraphs[l].runs[0].text = df.at[i, 'serial number']
name_of_file = (f"{df.at[i, 'Name']}.docx")
outputdoc=targeted_doc.save(name_of_file)
path_of_document=path(outputdoc)
completesave = os.path.join(path_of_document, name_of_file)
convert(path_of_document,newfile_path+f"{name_of_file}.pdf")
auto_fill("database.csv","01.docx")

If I'm understanding what you're trying to accomplish, then just use the path variable you made earlier. Since you used os.makedirs(path), then the path to that would just be the path object.

If you don't change the location, you can use the same path. If you change the location, you can get the path from your script using os.getcwd() and join it wiht the path using os.path.join()
You can store the result of os.path.join(os.getcwd(), path) to a variable and use it later. You can compose that absolute path before creating the file, so you'll have the entire path

Python: How do I add files to a new directory with a time-stamp?

Im new to python. I am trying to create a script that will add imported files to a new directory with a timestamp, as a daily backup. How do I point to the new directory as it changes name every day? Here is my script:
gis = GIS("https://arcgis.com", "xxx", "xxx")
items = gis.content.search(query="type:Feature Service, owner:xxx", max_items=5000,)
import datetime
import shutil
import os
now = datetime.datetime.today()
nTime = now.strftime("%d-%m-%Y")
source = r"C:\Users\Bruger\xxx\xxx\xxx\Backup\Backup"
dest = os.path.join(source+nTime)
if not os.path.exists(dest):
os.makedirs(dest) #creat dest dir
source_files = os.listdir(source)
for f in source_files:
source_file = os.path.join(source,f)
if os.path.isfile(source_file): #check if source file is a file not dir
shutil.move(source_file,dest) #move all only files (not include dir) to dest dir
for item in items:
service_title = item.title
if service_title == "Bøjninger_09_06":
try:
service_title = item.title
version = "1"
fgdb_title = service_title+version
result = item.export(fgdb_title, "File Geodatabase")
result.download(r"C:\Users\Bruger\xxx\xxx\xxx\Backup\?????) **what shal I write here in order to point to the new folder?**
result.delete()
except:
print("An error occurred downloading"+" "+service_title)```

You could try an f-string instead of a regular string, like this:
rf"C:\Users\Bruger\xxx\xxx\xxx\Backup\{dest}"

You can use something like that:
result.download("C:\Users\Bruger\xxx\xxx\xxx\Backup\{}".format(dest))

Opening xlxs workbook in Python, automating file name

I'm a heavy R user but very new to Python. I'm trying to edit a Python script that is part of a larger workflow. The script starts off by opening an .xlsx document. This document is produced in an earlier part of the workflow and the naming convention is always YYYYMMDD_location (ex: 20191101_Potomac). I would like to set up the Python script so that it automatically pastes today's date and that location variable into the path.
In R, to not have to manually update the path name each time I run the script, I would do something like:
#R
library(openxlsx)
dir_name <- 'C:/path/to/file/'
location_selection <- 'Potomac'
date <- (paste(format(Sys.Date(),"%Y%m%d"))
open.xlsx(paste0(dir_name, date, "_", location_selection, ".xlsx")
I've looked up how to set up something similar in Python (ex: Build the full path filename in Python), but not making much progress in producing something that works.
# Python
import datetime
dir_name = 'C:\path\to\file'
location_selection = todays_date.strftime('%Y%m%d')+'_Potomac'
suffix = '.xlsx'
file = os.path.join(dir_name, location_selection + suffix)
book = xlrd.open_workbook(file)

No need to use os module as you provide the full directory path.
from datetime import date
dir_name = r'C:\path\to\file'
location_selection = f"{date.today().strftime('%Y%m%d')}_Potomac"
suffix = '.xlsx'
file_name = f'{dir_name}\{location_selection}{suffix}'
book = xlrd.open_workbook(file_name)
We can add more variables as well :
from datetime import date
dir_name = r'C:\path\to\file'
today = date.today().strftime('%Y%m%d')
location = "Potomac"
suffix = '.xlsx'
file_name = f'{dir_name}\{today}_{location}{suffix}'
book = xlrd.open_workbook(file_name)
Finaly we can create a function that could be reused :
from datetime import date
def get_filename(location, dir_name=r'C:\path\to\file', suffix=".xlsx", date_format = '%Y%m%d'):
today = date.today().strftime(date_format)
return f'{dir_name}\{today}_{location}{suffix}'
book = xlrd.open_workbook(get_filename("Potomac"))
book2 = xlrd.open_workbook(get_filename("Montreal"))
book3 = xlrd.open_workbook(get_filename("NewYork"))

python zip extract with timestamp under Windows [duplicate]

I'm trying to extract files from a zip file using Python 2.7.1 (on Windows, fyi) and each of my attempts shows extracted files with Modified Date = time of extraction (which is incorrect).
import os,zipfile
outDirectory = 'C:\\_TEMP\\'
inFile = 'test.zip'
fh = open(os.path.join(outDirectory,inFile),'rb')
z = zipfile.ZipFile(fh)
for name in z.namelist():
z.extract(name,outDirectory)
fh.close()
I also tried using the .extractall method, with the same results.
import os,zipfile
outDirectory = 'C:\\_TEMP\\'
inFile = 'test.zip'
zFile = zipfile.ZipFile(os.path.join(outDirectory,inFile))
zFile.extractall(outDirectory)
Can anyone tell me what I'm doing wrong?
I'd like to think this is possible without having to post-correct the modified time per How do I change the file creation date of a Windows file?.

Well, it does take a little post-processing, but it's not that bad:
import os
import zipfile
import time
outDirectory = 'C:\\TEMP\\'
inFile = 'test.zip'
fh = open(os.path.join(outDirectory,inFile),'rb')
z = zipfile.ZipFile(fh)
for f in z.infolist():
name, date_time = f.filename, f.date_time
name = os.path.join(outDirectory, name)
with open(name, 'wb') as outFile:
outFile.write(z.open(f).read())
date_time = time.mktime(date_time + (0, 0, -1))
os.utime(name, (date_time, date_time))
Okay, maybe it is that bad.

Based on Jia103's answer, I have developed a function (using Python 2.7.14) which preserves directory and file dates AFTER everything has been extracted. This isolates any ugliness in the function, and you can also use zipfile.Zipfile.extractAll() or whatever zip extract method you want:
import time
import zipfile
import os
# Restores the timestamps of zipfile contents.
def RestoreTimestampsOfZipContents(zipname, extract_dir):
for f in zipfile.ZipFile(zipname, 'r').infolist():
# path to this extracted f-item
fullpath = os.path.join(extract_dir, f.filename)
# still need to adjust the dt o/w item will have the current dt
date_time = time.mktime(f.date_time + (0, 0, -1))
# update dt
os.utime(fullpath, (date_time, date_time))
To preserve dates, just call this function after your extract is done.
Here's an example, from a script I wrote to zip/unzip game save directories:
z = zipfile.ZipFile(zipname, 'r')
print 'I have opened zipfile %s, ready to extract into %s' \
% (zipname, gamedir)
try: os.makedirs(gamedir)
except: pass # Most of the time dir already exists
z.extractall(gamedir)
RestoreTimestampsOfZipContents(zipname, gamedir) #<-- USED
print '%s zip extract done' % GameName[game]
Thanks everyone for your previous answers!

Based on Ethan Fuman's answer, I have developed this version (using Python 2.6.6) which is a little more consise:
zf = ZipFile('archive.zip', 'r')
for zi in zf.infolist():
zf.extract(zi)
date_time = time.mktime(zi.date_time + (0, 0, -1))
os.utime(zi.filename, (date_time, date_time))
zf.close()
This extracts to the current working directory and uses the ZipFile.extract() method to write the data instead of creating the file itself.

Based on Ber's answer, I have developed this version (using Python 2.7.11), which also accounts for directory mod dates.
from os import path, utime
from sys import exit
from time import mktime
from zipfile import ZipFile
def unzip(zipfile, outDirectory):
dirs = {}
with ZipFile(zipfile, 'r') as z:
for f in z.infolist():
name, date_time = f.filename, f.date_time
name = path.join(outDirectory, name)
z.extract(f, outDirectory)
# still need to adjust the dt o/w item will have the current dt
date_time = mktime(f.date_time + (0, 0, -1))
if (path.isdir(name)):
# changes to dir dt will have no effect right now since files are
# being created inside of it; hold the dt and apply it later
dirs[name] = date_time
else:
utime(name, (date_time, date_time))
# done creating files, now update dir dt
for name in dirs:
date_time = dirs[name]
utime(name, (date_time, date_time))
if __name__ == "__main__":
unzip('archive.zip', 'out')
exit(0)
Since directories are being modified as the extracted files are being created inside them, there appears to be no point in setting their dates with os.utime until after the extraction has completed, so this version caches the directory names and their timestamps till the very end.