a

Showing posts with label free python code. Show all posts
Showing posts with label free python code. Show all posts

Thursday, 7 July 2016

Python code to convert all pdf files to .txt files in a folder

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
 import os

from os import chdir, getcwd, listdir, path

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)

i=0

while i<=len(list):

    path=list[i]

    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 i in range(0, pdf.getNumPages()):

        # Extract text from page and add to content

        content += pdf.getPage(i).extractText() + "\n"

    print strftime("%H:%M:%S"), " pdf  -> txt "

    f=open(name,'w')

    f.write(content.encode("UTF-8"))

    f.close



Simple animation loop in python


Click here to download the python file



Build A Salesforce To Sell For Your Business With Monkey Business


  For Python version 3 users follow the code given below.
  for the code to work you have to install pypdf2
  by using  ---------->        pip install pypdf2
   
 For converting html files to text files  Click here 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
import os

from os import chdir, getcwd, listdir, path

import PyPDF2

from time import strftime


def check_path(prompt):

    ''' (str) -> str

    Verifies if the provided absolute path does exist.

    '''

    abs_path = input(prompt)

    while path.exists(abs_path) != True:

        print ("\nThe specified path does not exist.\n")

        abs_path = 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)




for item in list:
    path=item

    head,tail=os.path.split(path)

    var="\\"

   

    tail=tail.replace(".pdf",".txt")

    name=head+var+tail

    

   

   

    

    content = ""

    

    pdf = PyPDF2.PdfFileReader(path, "rb")

    

    for i in range(0, pdf.getNumPages()):

        

        content += pdf.getPage(i).extractText() + "\n"
        

    print (strftime("%H:%M:%S"), " pdf  -> txt ")

    with open(name,'a') as out:
        out.write(content
Posted by at 42 comments:
Labels: ,
Subscribe to: Posts (Atom)