python - SameFileError because of overwriting location

Question

I have created an script that looks for words in pdf in one folder, then if it finds it moves the pdf to another folder.

from pathlib import Path
import PyPDF2
import re
import os
import shutil

pattern = input("Enter string pattern to search: ")

basepath = Path('hrdinhalDataDesktopAnalizeSearch engine')

src = basepath / 'Folder 1'
dst = basepath / 'Folder 2'


for file_name in os.scandir(src):
    file = PyPDF2.PdfFileReader(str(src / file_name), 'rb')
    numPages = file.getNumPages()

    for i in range(0, numPages):
        pageObj = file.getPage(i)
        text = pageObj.extractText()
        
        for match in re.findall(pattern, text, re.IGNORECASE):
            shutil.copyfile(str(src / file_name), str(dst / file_name))

When I run it I get error:

SameFileError: '\hrdinhal\Data\Desktop\Analize\Search engine\Folder 1\Daily Production Summary 1.pdf' and '\hrdinhal\Data\Desktop\Analize\Search engine\Folder 1\Daily Production Summary 1.pdf' are the same file

For some reason it takes dst and replaces it with src. Why? And how to fix it?

dst
Out[99]: WindowsPath('/hrdinhal/Data/Desktop/Analize/Search engine/Folder 2')

file_name
Out[100]: <DirEntry 'Daily Production Summary 1.pdf'>

dst/file_name
Out[101]: WindowsPath('/hrdinhal/Data/Desktop/Analize/Search engine/Folder 1/Daily Production Summary 1.pdf')

It changes Folder 2 to Folder 1!

question from:https://stackoverflow.com/questions/65920604/samefileerror-because-of-overwriting-location

Answer 1

I find out that file_name keeps full path to file and this path replaces src, dst in

src / file_name 
dst / file_name

You have to get only name file_name.name

src / file_name.name
dst / file_name.name

---

BTW:

Full path

print( file_name.path )

only filename

print( file_name.name )

---

BTW: You copy the same file after every match but you could do it only once

Using variable found and copy after for i-loop

from pathlib import Path
import PyPDF2
import re
import os
import shutil

pattern = input("Enter string pattern to search: ")

basepath = Path('hrdinhalDataDesktopAnalizeSearch engine')

src = basepath / 'Folder 1'
dst = basepath / 'Folder 2'

#print('[DEBUG] (before for file_name) src:', src)

for file_name in os.scandir(src):

    file = PyPDF2.PdfFileReader(str(src / file_name.name), 'rb')
    numPages = file.getNumPages()

    found = False

    # ---

    #print('[DEBUG] (before for i) src:', src)
    
    for i in range(0, numPages):
        pageObj = file.getPage(i)
        text = pageObj.extractText()

        #print('[DEBUG] (before if re) src:', src)

        if re.findall(pattern, text, re.IGNORECASE):
            found = True
            
    # ----

    #print('[DEBUG] (before for found) src:', src)
    
    if found:
        #print('[DEBUG] (before copy) src:', src)
        shutil.copyfile(str(src / file_name.name), str(dst / file_name.name))
        
    

or using break to skip for i-loop after first copy

from pathlib import Path
import PyPDF2
import re
import os
import shutil

pattern = input("Enter string pattern to search: ")

basepath = Path('hrdinhalDataDesktopAnalizeSearch engine')

src = basepath / 'Folder 1'
dst = basepath / 'Folder 2'

#print('[DEBUG] (before for file_name) src:', src)

for file_name in os.scandir(src):

    #print('[DEBUG] (before pyPDF2) file_name:', file_name)

    file = PyPDF2.PdfFileReader(str(src / file_name.name), 'rb')
    numPages = file.getNumPages()

    # ---

    #print('[DEBUG] (before for i) src:', src)
    
    for i in range(0, numPages):
        pageObj = file.getPage(i)
        text = pageObj.extractText()

        #print('[DEBUG] (before if re) src:', src)

        if re.findall(pattern, text, re.IGNORECASE):
            #print('[DEBUG] (before copy) src:', src)
            shutil.copyfile(str(src / file_name.name), str(dst / file_name.name))
            break # there is no need to check rest of PDF