/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

5 votes161 views1 answer
Surface = pygame.surface module not callable
Python
12 votes135 views4 answers
How to print a list without the brackets in python
Python
0 vote133 views2 answers
Input numpy array
Python
5 votes122 views3 answers
Click a button using selenium python
Python
0 vote121 views1 answer
Python send sms
Python
0 vote138 views1 answer
Load a Dictionary from File in Python Using the Load Function of the pickle Module
Python
13 votes137 views4 answers
Even in python
Python
0 vote125 views2 answers
Round to nearest multiple of 5 python from both end
Python
1 vote140 views1 answer
Df.select_dtypes
Python
0 vote129 views1 answer
How to sort values in numpy by one column
Python