/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 vote250 views1 answer
Python mayusculas
Python
0 vote266 views2 answers
Read_json
Python
1 vote262 views1 answer
Python csv update row
Python
0 vote285 views1 answer
How to dynamically search for a class variable in python
Python
4 votes270 views1 answer
Python extract all numbers from string re
Python
1 vote261 views1 answer
Not null constraint failed django
Python
0 vote245 views1 answer
Read list stored as a string with pandas read csv
Python
5 votes281 views1 answer
Date time module date diference
Python
0 vote260 views1 answer
Array search with regex python
Python
1 vote256 views1 answer
UnicodeEncodeError: 'latin-1' codec can't encode character '\u2013' in position 83: ordinal not in range(256)
Python