/
duoPdf.py
executable file
·278 lines (239 loc) · 10.5 KB
/
duoPdf.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
275
276
__author__ = 'vin@misday.com'
import sys, os, traceback
from PyPDF2 import PdfFileReader, PdfFileWriter, PdfFileMerger
from pyvin.core import Log
from pdfrw import PdfReader, PdfWriter
if sys.platform == 'win32':
pass
elif sys.platform == 'linux2':
pass
class DuoPdf:
def __init__(self, scr = None):
self.TAG = DuoPdf.__name__
pass
@staticmethod
def crop(dest, src, left, top, bottom, right):
Log.i(DuoPdf.__name__, 'cropping file [%s]' % (src, ))
margin = (left, top, bottom, right)
srcFile = file(src, 'rb')
srcPdf = PdfFileReader(srcFile)
destPdf = PdfFileWriter()
for page in srcPdf.pages:
box = page.mediaBox
# print '%d %d %d %d' % (box.getLowerLeft_x(), box.getLowerLeft_y(), box.getUpperRight_x(), box.getUpperRight_y())
box.upperRight = (box.getUpperRight_x() - margin[2], box.getUpperRight_y() - margin[3])
box.lowerLeft = (box.getLowerLeft_x() + margin[0], box.getLowerLeft_y() + margin[1])
destPdf.addPage(page)
Log.i(DuoPdf.__name__, 'saving to file [%s]...' % (dest, ))
destFile = file(dest, 'wb')
destPdf.write(destFile)
destFile.close()
srcFile.close()
Log.i(DuoPdf.__name__, 'done')
@staticmethod
def crop2(dest, src, margin1, margin2):
Log.i(DuoPdf.__name__, 'cropping file [%s]' % (src, ))
srcFile = file(src, 'rb')
srcPdf = PdfFileReader(srcFile)
destPdf = PdfFileWriter()
index = 1
for page in srcPdf.pages:
box = page.mediaBox
if index != 1:
if index % 2 == 1: #odd
margin = margin1
else: #even
margin = margin2
# print '%d %d %d %d' % (box.getLowerLeft_x(), box.getLowerLeft_y(), box.getUpperRight_x(), box.getUpperRight_y())
box.upperRight = (box.getUpperRight_x() - margin[2], box.getUpperRight_y() - margin[3])
box.lowerLeft = (box.getLowerLeft_x() + margin[0], box.getLowerLeft_y() + margin[1])
destPdf.addPage(page)
index += 1
Log.i(DuoPdf.__name__, 'saving to file [%s]...' % (dest, ))
destFile = file(dest, 'wb')
destPdf.write(destFile)
destFile.close()
srcFile.close()
Log.i(DuoPdf.__name__, 'done')
@staticmethod
def cropWH(dest, src, destWidth, destHeight):
Log.i(DuoPdf.__name__, 'cropping file [%s]' % (src, ))
srcFile = file(src, 'rb')
srcPdf = PdfFileReader(srcFile)
destPdf = PdfFileWriter()
for page in srcPdf.pages:
box = page.mediaBox
width = box.getUpperRight_x() - box.getUpperRight_x()
height = box.getUpperRight_y() - box.getLowerLeft_y()
box.upperRight = (destWidth, box.getUpperRight_y() - (height - destHeight) / 2)
box.lowerLeft = (0, (height - destHeight) / 2)
destPdf.addPage(page)
Log.i(DuoPdf.__name__, 'saving to file [%s]...' % (dest, ))
destFile = file(dest, 'wb')
destPdf.write(destFile)
destFile.close()
srcFile.close()
Log.i(DuoPdf.__name__, 'done')
@staticmethod
def merge(dest, srcDir):
'''merge pdf files in srcDir'''
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
if len(files) > 0:
merger = PdfFileMerger()
for i,f in enumerate(files):
Log.i(DuoPdf.__name__, 'merge file [%s]' % (f, ))
filePath = os.path.join(srcDir, f)
if (os.path.isfile(filePath)):
try:
srcFileHdl = open(filePath, 'rb')
merger.merge(position=i, fileobj=srcFileHdl)
except:
Log.w(DuoPdf.__name__, 'merge [%s] failed' % (filePath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (filePath,))
Log.i(DuoPdf.__name__, 'save to file [%s]...' % (dest, ))
destFileStream = file(dest, 'wb')
merger.write(destFileStream)
destFileStream.close()
Log.i(DuoPdf.__name__, 'done')
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to merge' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
@staticmethod
def clean(srcDir):
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
if len(files) > 0:
for i,f in enumerate(files):
filePath = os.path.join(srcDir, f)
if (os.path.isfile(filePath)):
try:
DuoPdf.cleanPdf(filePath, filePath)
except:
Log.w(DuoPdf.__name__, 'clean [%s] failed' % (filePath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (filePath,))
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to clean' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
@staticmethod
def cleanPdf(srcPath, destPath=''):
if os.path.exists(srcPath):
if len(destPath) < 1:
f, e = os.path.splitext(srcPath)
destPath = f+'.cln.pdf'
x = PdfReader(srcPath)
for i, page in enumerate(x.pages):
print 'page %05d: ' % i,
xobjs = page.Resources.XObject
for okey in xobjs.keys():
xobj = xobjs[okey]
if DuoPdf.isDel(xobj):
# xobj.pop('/SMask')
xobjs.pop(okey)
# print xobj
# print xobj.SMask
print '.',
else:
print '[%sx%s#%s]' % (xobj.Width, xobj.Height, xobj.Length),
print 'done'
print '[%s] -> [%s]' % (srcPath, destPath)
PdfWriter().write(destPath, x)
@staticmethod
def isDel(xobj):
# quickly return
if not xobj:
return False
# print xobj.Filter
# print type(xobj.Filter)
# print xobj.ColorSpace
# print type(xobj.ColorSpace)
# print xobj.Type
# print type(xobj.Type)
# print xobj.Subtype
# print type(xobj.Subtype)
# if xobj.Filter != '/DCTDecode': return False
# if xobj.ColorSpace != '/DeviceRGB': return False
# if xobj.Type != '/XObject': return False
if xobj.BitsPerComponent != '8': return False
# if xobj.Subtype != '/Image': return False
# special xobject
# print xobj.Length
# print xobj.Height
# print xobj.Width
if xobj.Length == '1027' and xobj.Height == '160' and xobj.Width == '160': return True
if xobj.Length == '1027' and xobj.Height == '160' and xobj.Width == '160': return True
if xobj.Length == '667' and xobj.Height == '160' and xobj.Width == '1' : return True
if xobj.Length == '1027' and xobj.Height == '160' and xobj.Width == '160': return True
if xobj.Length == '667' and xobj.Height == '1' and xobj.Width == '160': return True
if xobj.Length == '667' and xobj.Height == '160' and xobj.Width == '1' : return True
if xobj.Length == '667' and xobj.Height == '1' and xobj.Width == '160': return True
if xobj.Length == '1027' and xobj.Height == '160' and xobj.Width == '160': return True
if xobj.Length == '7491' and xobj.Height == '188' and xobj.Width == '168': return True
if xobj.Length == '1226' and xobj.Height == '16' and xobj.Width == '45': return True
# fall down
return False
class ReduceSize():
def __init__(self):
pass
def cleanAllInPath(self, srcDir):
if os.path.exists(srcDir) and os.path.isdir(srcDir):
files = os.listdir(srcDir)
num = len(files)
if num > 0:
for i, f in enumerate(files):
print '%d/%d: %s' % (i, num, f)
fileName = self.getCleanedFileName(f)
srcPath = os.path.join(srcDir, f)
destPath = os.path.join(srcDir, fileName)
if (os.path.isfile(srcPath)):
if self.isCleanedFile(srcPath):
print 'skip [%s]' % srcPath
elif self.hasCleaned(srcPath):
print 'skip [%s]' % srcPath
else:
try:
DuoPdf.cleanPdf(srcPath, destPath)
# print '%s -> ' % srcPath
# print destPath
except:
Log.w(DuoPdf.__name__, 'clean [%s] failed' % (srcPath))
traceback.print_exc()
else:
Log.i(DuoPdf.__name__, 'skip file [%s]' % (srcPath,))
else:
Log.w(DuoPdf.__name__, 'no file in [%s] to clean' % (srcDir))
else:
Log.w(DuoPdf.__name__, 'dir [%s] not exist.' % (srcDir,))
def isCleanedFile(self, file):
fileName, extName = os.path.splitext(file)
fileName, extName = os.path.splitext(fileName)
if len(extName) < 1:
return False
if extName == '.cln':
return True
return False
def hasCleaned(self, file):
fileName = self.getCleanedFileName(file)
if os.path.exists(fileName) and os.path.isfile(fileName):
return True
return False
def getCleanedFileName(self, file):
fileName, extName = os.path.splitext(file)
return '%s.cln.pdf' % fileName
if __name__ == '__main__':
src = sys.argv[1]
# dest = sys.argv[2]
# dest = src[:-4] + '.cropped.pdf'
# duoPdf = DuoPdf(src)
# duoPdf.cropWH(dest, 500, 666)
# DuoPdf.duoMerge(src)
# DuoPdf.duoCrop(src)
# DuoPdf.duoCropForPrint(src)
# DuoPdf.cleanPdf(src)
DuoPdf.cleanAllInPath(src)