/Python/Arabic text recognition from pdf using python

Arabic text recognition from pdf using python

import os
from os import chdir, getcwd, listdir, path
import codecs
import pyPdf
from time import strftime

def check_path(prompt):
    ''' (str) -> str
    Verifies if the provided absolute path does exist.
    '''
    abs_path = raw_input(prompt)
    while path.exists(abs_path) != True:
        print "\nThe specified path does not exist.\n"
        abs_path = raw_input(prompt)
    return abs_path    

print "\n"

folder = check_path("Provide absolute path for the folder: ")

list=[]
directory=folder
for root,dirs,files in os.walk(directory):
    for filename in files:
        if filename.endswith('.pdf'):
            t=os.path.join(directory,filename)

            list.append(t)

m=len(list)
print (m)
i=0
while i<=m-1:

    path=list[i]
    print(path)
    head,tail=os.path.split(path)
    var="\\"

    tail=tail.replace(".pdf",".txt")
    name=head+var+tail

    content = ""
    # Load PDF into pyPDF
    pdf = pyPdf.PdfFileReader(file(path, "rb"))
            # Iterate pages
    for j in range(0, pdf.getNumPages()):
        # Extract text from page and add to content
        content += pdf.getPage(j).extractText() + "\n"
    print strftime("%H:%M:%S"), " pdf  -> txt "
    f=open(name,'w')
    content.encode('utf-8')
    f.write(content)
    f.close
    i=i+1

Source: stackoverflow.com

Similar codes

0 vote152 views1 answer
Python - Cara Bermain Mp3 File
Python
0 vote141 views10 answers
Logistic Regression with a Neural Network mindset python example
Python
3 votes184 views1 answer
Tf 1 compatible colab
Python
1 vote147 views1 answer
Check if value is in series pandas
Python
12 votes142 views3 answers
Convert pandas dataframe to dict with a column as key
Python
0 vote145 views2 answers
Remove empty lines from file python
Python
16 votes151 views2 answers
Access row of dataframe
Python
0 vote142 views1 answer
Fetch last record from django model
Python
2 votes386 views1 answer
Minimal flask application import
Python Flask
4 votes155 views4 answers
Recursion python examples
Python