/
ocr_on_terminal.py
274 lines (195 loc) · 5.39 KB
/
ocr_on_terminal.py
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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
@author: vysh
"""
#Make sure this script is in the same folder as the file from which text is to be extracted
from wand.image import Image as wi
from autocorrect import spell
from PIL import Image
import pytesseract
import os
import io
def imgOcrEng(file_name):
im = Image.open(file_name)
text = pytesseract.image_to_string(im, lang='eng')
fin = open('temp-extracted.txt','w')
fin.write(text)
fin.close()
fhand = open('temp-extracted.txt')
fout = open('extracted.txt','w')
for line in fhand:
line.rstrip()
words=line.split()
for word in words:
word=spell(word)+' '
fout.write(word)
fout.write('\n')
fout.close()
f = open("extracted.txt", "r")
text = f.read()
f.close()
os.remove("temp-extracted.txt")
#os.remove("extracted.txt")
return text
def pdfOcrEng(file_name):
pdf = wi(filename = file_name, resolution = 300)
pdfImage = pdf.convert('jpeg')
imageBlobs = []
for img in pdfImage.sequence:
imgPage = wi(image = img)
imageBlobs.append(imgPage.make_blob('jpeg'))
extracted_text = []
for imgBlob in imageBlobs:
im = Image.open(io.BytesIO(imgBlob))
text = pytesseract.image_to_string(im, lang = 'eng')
extracted_text.append(text)
fin = open('temp-extracted.txt','w')
fin.writelines(["%s\n" % item for item in extracted_text])
fin.close()
fhand = open('temp-extracted.txt')
fout = open('extracted.txt','w')
for line in fhand:
line.rstrip()
words=line.split()
for word in words:
word=spell(word)+' '
fout.write(word)
fout.write('\n')
fout.close()
f = open("extracted.txt", "r")
text = f.read()
f.close()
os.remove("temp-extracted.txt")
#os.remove("extracted.txt")
return text
def imgOcrKan(file_name):
im = Image.open(file_name)
text = pytesseract.image_to_string(im, lang='kan')
fout = open('extracted.txt','w')
fout.write(text)
fout.close()
return text
def pdfOcrKan(file_name):
pdf = wi(filename = file_name, resolution = 300)
pdfImage = pdf.convert('jpeg')
imageBlobs = []
for img in pdfImage.sequence:
imgPage = wi(image = img)
imageBlobs.append(imgPage.make_blob('jpeg'))
extracted_text = []
for imgBlob in imageBlobs:
im = Image.open(io.BytesIO(imgBlob))
text = pytesseract.image_to_string(im, lang = 'eng')
extracted_text.append(text)
fin = open('extracted.txt','w')
fin.writelines(["%s\n" % item for item in extracted_text])
fin.close()
f = open('extracted.txt','r')
text = f.read()
f.close()
return text
def imgOcrTam(file_name):
im = Image.open(file_name)
text = pytesseract.image_to_string(im, lang='tam')
fout = open('extracted.txt','w')
fout.write(text)
fout.close()
return text
def pdfOcrTam(file_name):
pdf = wi(filename = file_name, resolution = 300)
pdfImage = pdf.convert('jpeg')
imageBlobs = []
for img in pdfImage.sequence:
imgPage = wi(image = img)
imageBlobs.append(imgPage.make_blob('jpeg'))
extracted_text = []
for imgBlob in imageBlobs:
im = Image.open(io.BytesIO(imgBlob))
text = pytesseract.image_to_string(im, lang = 'tam')
extracted_text.append(text)
fin = open('extracted.txt','w')
fin.writelines(["%s\n" % item for item in extracted_text])
fin.close()
f = open('extracted.txt','r')
text = f.read()
f.close()
return text
def imgOcrTel(file_name):
im = Image.open(file_name)
text = pytesseract.image_to_string(im, lang='tel')
fout = open('extracted.txt','w')
fout.write(text)
fout.close()
return text
def pdfOcrTel(file_name):
pdf = wi(filename = file_name, resolution = 300)
pdfImage = pdf.convert('jpeg')
imageBlobs = []
for img in pdfImage.sequence:
imgPage = wi(image = img)
imageBlobs.append(imgPage.make_blob('jpeg'))
extracted_text = []
for imgBlob in imageBlobs:
im = Image.open(io.BytesIO(imgBlob))
text = pytesseract.image_to_string(im, lang = 'tel')
extracted_text.append(text)
fin = open('extracted.txt','w')
fin.writelines(["%s\n" % item for item in extracted_text])
fin.close()
f = open('extracted.txt','r')
text = f.read()
f.close()
return text
def main():
print("Optical Character Recognition.\n")
lang_choice = int(input("Select Language:\n\n1.English\n2.Kannada\n3.Tamil\n4.Telegu\n"))
file_type = int(input("\nSelect the file type:\n1.Image\n2.pdf\n"))
file_name = input("\nEnter the file name: ")
if lang_choice == 1:
if file_type == 1:
text = imgOcrEng(file_name)
print(text)
elif file_type == 2:
text = pdfOcrEng(file_name)
print(text)
else:
print("Invalid Choice.")
return
elif lang_choice == 2:
if file_type == 1:
text = imgOcrKan(file_name)
print(text)
elif file_type == 2:
text = pdfOcrKan(file_name)
print(text)
else:
print("Invalid Choice.")
return
elif lang_choice == 3:
if file_type == 1:
text = imgOcrTam(file_name)
print(text)
elif file_type == 2:
text = pdfOcrTam(file_name)
print(text)
else:
print("Invalid choice.")
return
elif lang_choice == 4:
if file_type == 1:
text = imgOcrTel(file_name)
print(text)
elif file_type == 2:
text = pdfOcrTel(file_name)
print(text)
else:
print("Invalid Choice.")
return
else:
print("Invalid choice.")
return
print("\n\nExtracted text can also be found in the same folder in a file- 'extracted.txt'\n")
return
if __name__== "__main__":
main()