-
Notifications
You must be signed in to change notification settings - Fork 0
/
p2i.py
196 lines (129 loc) · 5.53 KB
/
p2i.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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Sep 6 22:33:23 2019
@author:Naveen Kumar Vasudevan,
Doctoral Student,
The Xi Research Group,
McMaster University,
Hamilton,
Canada.
naveenovan@gmail.com
https://naveenovan.wixsite.com/kuroonai
"""
'''
################################### pdf2image convertor ######################################
https://pypi.org/project/pdf2image/
Using conda
conda install -c conda-forge poppler
pip install pdf2image
pip install pillow
for large files to track progress use tqdm:
conda install -c conda-forge tqdm
make sure pip is from conda using "which pip" in commandline
usage :
1) python p2i.py </location/to/folder/with/pdf/files/for/conversion>
output : converts all .pdf file from location into .jpg file
2) python p2i.py </location/to/folder/with/pdf/file/with/itsname.pdf> <page number>
output : converts specified page of the pdf file in path
3) python p2i.py <location_with_filename> <page number range eg: <start> <stop> >
output : converts the range of pages from specified pdf file
'''
'''
add alias in linux or unix for easy access
use following commands:
cd
open .bashrc file (vi .bashrc) and type the below line
alias p2i = "python /location to p2i.py"
now code can be used from command line as follows
p2i /location/of/pdf/files(/test.pdf) pagenumber or <start> <stop>
'''
'''
examples:
python p2i.py /home/user/Desktop/
python p2i.py /home/user/Desktop/test.pdf 2
python p2i.py /home/user/Desktop/test.pdf 2 19
'''
from pdf2image import convert_from_path
import os
import sys
from tqdm import tqdm
loc = sys.argv[1]
if len(sys.argv) < 2: raise SyntaxError("Syntax: p2i.py <location of pdf files>")
elif len(sys.argv) == 2 and len(loc.split('/')[-1].split('.')) == 2 :
if loc.split('/')[-1].split('.')[1] != 'pdf': raise SyntaxError("Syntax: p2i.py <./pdf file> need, directed file is not a pdf file")
if os.name == 'posix':
location = loc.split('/')[:-1]
s = '/'
elif os.name == 'nt':
location = loc.split('\\')[:-1]
s = '\\'
newlocation = s.join(location)
path = sys.argv[1]
pageno = 1
pagename = loc.split('/')[-1].split('.')[0]
images = convert_from_path(path,dpi=300,output_folder=None,first_page=pageno,last_page=pageno)
print(('\n\nconverting page number %d of "%s"\n'%(pageno,path.split('/')[-1])))
#for page in tqdm(range(len(images))):
if os.name == 'posix':
images[0].save(newlocation+'/'+'%s'%(pagename)+'.jpg')
elif os.name =='nt':
images[0].save(newlocation+'\\'+'%s'%(pagename)+'.jpg')
elif len(sys.argv) == 2:
#loc = '/media/sf_dive/Research_work/afinalpaperrun/analysis/OPT/bmark/splits/results'
os.chdir(loc)
source = os.listdir(loc)
print('\n')
for file in source:
if file.endswith('.pdf'):
filename = file.split('.')
if os.name == 'posix':
images = convert_from_path(loc+'/'+file,dpi=300)
elif os.name =='nt':
images = convert_from_path(loc+'\\'+file,dpi=300)
print(('\n\nconverting "%s" with %d page(s)\n'%(str(file),len(images))))
for page in tqdm(list(range(len(images)))):
if os.name == 'posix':
if page > 0: images[page].save(loc+'/'+'.'.join(filename[:-1])+'_%d'%(page+1)+'.jpg')
else: images[page].save(loc+'/'+'.'.join(filename[:-1])+'.jpg')
elif os.name == 'nt':
if page > 0: images[page].save(loc+'\\'+'.'.join(filename[:-1])+'_%d'%(page+1)+'.jpg')
else: images[page].save(loc+'\\'+'.'.join(filename[:-1])+'.jpg')
elif len(sys.argv) == 3:
if os.name == 'posix':
location = loc.split('/')[:-1]
s = '/'
elif os.name == 'nt':
location = loc.split('\\')[:-1]
s = '\\'
newlocation = s.join(location)
path = sys.argv[1]
pageno = int(sys.argv[2])
images = convert_from_path(path,dpi=300,output_folder=None,first_page=pageno,last_page=pageno)
print(('\n\nconverting page number %d of "%s"\n'%(pageno,path.split('/')[-1])))
#for page in tqdm(range(len(images))):
if os.name == 'posix':
images[0].save(newlocation+'/'+'pagenumer_%d'%(pageno)+'.jpg')
elif os.name =='nt':
images[0].save(newlocation+'\\'+'pagenumer_%d'%(pageno)+'.jpg')
elif len(sys.argv) == 4:
if os.name == 'posix':
location = loc.split('/')[:-1]
s = '/'
elif os.name == 'nt':
location = loc.split('\\')[:-1]
s = '\\'
newlocation = s.join(location)
path = sys.argv[1]
start = int(sys.argv[2])
stop = int(sys.argv[3])
print(('\n\nconverting page numbers %d to %d of "%s"\n'%(start,stop,path.split('/')[-1])))
images = convert_from_path(path,dpi=300,output_folder=None,first_page=start, last_page=stop)
pagenumbers = list(range(start,stop+1))
for pages in tqdm(list(range(len(images)))):
if os.name == 'posix':
images[pages].save(newlocation+'/'+'pagenumer_%d'%(pagenumbers[pages])+'.jpg')
elif os.name == 'nt':
images[pages].save(newlocation+'\\'+'pagenumer_%d'%(pagenumbers[pages])+'.jpg')
elif len(sys.argv) != 4 or len(sys.argv) > 4:
raise SyntaxError("Syntax: p2i.py <location_with_filename> <page number range eg: <start> <stop> >")