बैच प्रोसेसर - एकाधिक पाता है और पायथन के साथ प्रतिस्थापित करें

 
 
 rel="context" href="www.peepee.com" spree="one"> 
 spree="one" rel="context" href="www.peepee.com"> 
 href="www.peepee.com" rel="context" spree="one"> 
 
 
 
 
 

---- आउटपुट होगा: ---

 
 
empty row 
empty row 
empty row 
 
 
 
 
 

import re
import os

# 0. Construim o functie care primeste ca argument un fisier si aplica niste expresii regulate
def aplica_expresii_regulate(cale_fisier): 
    with open(cale_fisier,'r') as f:
        text_citit_din_fisier = f.read() 

# Regex1  FIND: 
text_citit_din_fisier=re.sub(r', r', text_citit_din_fisier)
print ("Primul Regex:", text_citit_din_fisier)

# Regex2  FIND: spree.*>  REPLACE BY: bebe
text_citit_din_fisier=re.sub(r'spree.*>', r'bebe', text_citit_din_fisier)
print ("Second Regex:", text_citit_din_fisier)

# Regex3  FIND: (^.*)bebe  REPLACE BY: empty row/x20
text_citit_din_fisier=re.sub(r'.*bebe', r'empty row', text_citit_din_fisier)
print ("Third Regex:", text_citit_din_fisier)   
    

    print(text_citit_din_fisier)
   
    with open(cale_fisier, "w") as h:
        h.write(text_citit_din_fisier)


# 1. Construim o functie care primeste ca argument un director, iar pentru fiecare fisier din director facem o anumita operatie
def parcurge_director(cale_director):
    for nume_fisier in os.listdir(cale_director):
        if nume_fisier.endswith(".txt") or nume_fisier.endswith(".png"): #daca incepe cu txt
            cale_completa_fisier = os.path.join(cale_director, nume_fisier)
            aplica_expresii_regulate(cale_completa_fisier)
        else:
            continue


directory = r'd:\Downloads'
parcurge_director(directory)

>>> t1 = re.sub(r"^.*?>(.+?)(?= \|).*?$", r"\1.html")
>>> t2 = re.sub(r"\s", r"-", t1)