質問編集履歴
9
set,py追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -32,6 +32,190 @@
|
|
|
32
32
|
|
|
33
33
|
|
|
34
34
|
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
pdfminer.sixのset.py↓
|
|
38
|
+
|
|
39
|
+
```ここに言語を入力
|
|
40
|
+
|
|
41
|
+
from setuptools import setup
|
|
42
|
+
|
|
43
|
+
from os import path
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
import pdfminer as package
|
|
48
|
+
|
|
49
|
+
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
|
|
53
|
+
with open(path.join(path.abspath(path.dirname(__file__)), 'README.md')) as f:
|
|
54
|
+
|
|
55
|
+
readme = f.read()
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
setup(
|
|
60
|
+
|
|
61
|
+
name='pdfminer.six',
|
|
62
|
+
|
|
63
|
+
version=package.__version__,
|
|
64
|
+
|
|
65
|
+
packages=['pdfminer'],
|
|
66
|
+
|
|
67
|
+
package_data={'pdfminer': ['cmap/*.pickle.gz']},
|
|
68
|
+
|
|
69
|
+
install_requires=[
|
|
70
|
+
|
|
71
|
+
'chardet ; python_version > "3.0"',
|
|
72
|
+
|
|
73
|
+
'pycryptodome',
|
|
74
|
+
|
|
75
|
+
'sortedcontainers',
|
|
76
|
+
|
|
77
|
+
],
|
|
78
|
+
|
|
79
|
+
extras_require={
|
|
80
|
+
|
|
81
|
+
"dev": ["nose", "tox"],
|
|
82
|
+
|
|
83
|
+
"docs": ["sphinx", "sphinx-argparse"],
|
|
84
|
+
|
|
85
|
+
},
|
|
86
|
+
|
|
87
|
+
description='PDF parser and analyzer',
|
|
88
|
+
|
|
89
|
+
long_description=readme,
|
|
90
|
+
|
|
91
|
+
long_description_content_type='text/markdown',
|
|
92
|
+
|
|
93
|
+
license='MIT/X',
|
|
94
|
+
|
|
95
|
+
author='Yusuke Shinyama + Philippe Guglielmetti',
|
|
96
|
+
|
|
97
|
+
author_email='pdfminer@goulu.net',
|
|
98
|
+
|
|
99
|
+
url='https://github.com/pdfminer/pdfminer.six',
|
|
100
|
+
|
|
101
|
+
scripts=[
|
|
102
|
+
|
|
103
|
+
'tools/pdf2txt.py',
|
|
104
|
+
|
|
105
|
+
'tools/dumppdf.py',
|
|
106
|
+
|
|
107
|
+
],
|
|
108
|
+
|
|
109
|
+
keywords=[
|
|
110
|
+
|
|
111
|
+
'pdf parser',
|
|
112
|
+
|
|
113
|
+
'pdf converter',
|
|
114
|
+
|
|
115
|
+
'layout analysis',
|
|
116
|
+
|
|
117
|
+
'text mining',
|
|
118
|
+
|
|
119
|
+
],
|
|
120
|
+
|
|
121
|
+
python_requires='>=3.4',
|
|
122
|
+
|
|
123
|
+
classifiers=[
|
|
124
|
+
|
|
125
|
+
'Programming Language :: Python',
|
|
126
|
+
|
|
127
|
+
'Programming Language :: Python :: 3.4',
|
|
128
|
+
|
|
129
|
+
'Programming Language :: Python :: 3.5',
|
|
130
|
+
|
|
131
|
+
'Programming Language :: Python :: 3.6',
|
|
132
|
+
|
|
133
|
+
'Programming Language :: Python :: 3 :: Only',
|
|
134
|
+
|
|
135
|
+
'Development Status :: 5 - Production/Stable',
|
|
136
|
+
|
|
137
|
+
'Environment :: Console',
|
|
138
|
+
|
|
139
|
+
'Intended Audience :: Developers',
|
|
140
|
+
|
|
141
|
+
'Intended Audience :: Science/Research',
|
|
142
|
+
|
|
143
|
+
'License :: OSI Approved :: MIT License',
|
|
144
|
+
|
|
145
|
+
'Topic :: Text Processing',
|
|
146
|
+
|
|
147
|
+
],
|
|
148
|
+
|
|
149
|
+
)
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
```
|
|
154
|
+
|
|
155
|
+
|
|
156
|
+
|
|
157
|
+
pdfminer3kminerのset.py↓
|
|
158
|
+
|
|
159
|
+
```
|
|
160
|
+
|
|
161
|
+
import setuptools
|
|
162
|
+
|
|
163
|
+
|
|
164
|
+
|
|
165
|
+
with open("README.md", "r") as fh:
|
|
166
|
+
|
|
167
|
+
long_description = fh.read()
|
|
168
|
+
|
|
169
|
+
|
|
170
|
+
|
|
171
|
+
setuptools.setup(
|
|
172
|
+
|
|
173
|
+
name="pdfminer3k",
|
|
174
|
+
|
|
175
|
+
version="1.3.4",
|
|
176
|
+
|
|
177
|
+
author="Serhat Can",
|
|
178
|
+
|
|
179
|
+
author_email="author@example.com",
|
|
180
|
+
|
|
181
|
+
description="Forked from original pdfminer",
|
|
182
|
+
|
|
183
|
+
long_description=long_description,
|
|
184
|
+
|
|
185
|
+
long_description_content_type="text/markdown",
|
|
186
|
+
|
|
187
|
+
url="https://github.com/canserhat77/pdfminer3k",
|
|
188
|
+
|
|
189
|
+
download_url="https://github.com/canserhat77/pdfminer3k/archive/v1.3.4.tar.gz",
|
|
190
|
+
|
|
191
|
+
packages=setuptools.find_packages(),
|
|
192
|
+
|
|
193
|
+
classifiers=[
|
|
194
|
+
|
|
195
|
+
"Programming Language :: Python :: 3",
|
|
196
|
+
|
|
197
|
+
"License :: OSI Approved :: MIT License",
|
|
198
|
+
|
|
199
|
+
"Operating System :: OS Independent",
|
|
200
|
+
|
|
201
|
+
],
|
|
202
|
+
|
|
203
|
+
install_requires=[
|
|
204
|
+
|
|
205
|
+
'ply',
|
|
206
|
+
|
|
207
|
+
],
|
|
208
|
+
|
|
209
|
+
python_requires='>=3.6',
|
|
210
|
+
|
|
211
|
+
)
|
|
212
|
+
|
|
213
|
+
```
|
|
214
|
+
|
|
215
|
+
|
|
216
|
+
|
|
217
|
+
|
|
218
|
+
|
|
35
219
|
|
|
36
220
|
|
|
37
221
|
Downloads配下↓
|
8
pip listコマンド実行後の画像追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -22,13 +22,9 @@
|
|
|
22
22
|
|
|
23
23
|
|
|
24
24
|
|
|
25
|
+
pip listコマンド実行後
|
|
25
26
|
|
|
26
|
-
|
|
27
|
+
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
28
|
|
|
33
29
|
|
|
34
30
|
|
7
説明文追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -1,3 +1,9 @@
|
|
|
1
|
+
プログラミング初心者です。
|
|
2
|
+
|
|
3
|
+
大変基礎的な内容かもしれませんが、質問させてください。
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
|
|
1
7
|
あるツールのDownloads配下のフォルダでインストールを実行(pip3 install package)しました。
|
|
2
8
|
|
|
3
9
|
Downloads配下のフォルダへのインストール後、usr/local/bin配下にも同じ名前のファイルが自動的にインストールされることを確認し、
|
6
文章編集
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -32,17 +32,17 @@
|
|
|
32
32
|
|
|
33
33
|
|
|
34
34
|
|
|
35
|
-
Downloads配下
|
|
35
|
+
Downloads配下↓
|
|
36
36
|
|
|
37
37
|
|
|
38
38
|
|
|
39
|
-
usr/local/bin配下
|
|
39
|
+
usr/local/bin配下↓
|
|
40
40
|
|
|
41
41
|
|
|
42
42
|
|
|
43
43
|
|
|
44
44
|
|
|
45
|
-
Downloads配下
|
|
45
|
+
Downloads配下↓
|
|
46
46
|
|
|
47
47
|
```
|
|
48
48
|
|
|
@@ -106,7 +106,7 @@
|
|
|
106
106
|
|
|
107
107
|
|
|
108
108
|
|
|
109
|
-
usr/local/bin配下
|
|
109
|
+
usr/local/bin配下↓
|
|
110
110
|
|
|
111
111
|
```
|
|
112
112
|
|
5
フォルダ構成に関する画像の追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -31,6 +31,14 @@
|
|
|
31
31
|
|
|
32
32
|
|
|
33
33
|
|
|
34
|
+
|
|
35
|
+
Downloads配下
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
usr/local/bin配下
|
|
40
|
+
|
|
41
|
+
|
|
34
42
|
|
|
35
43
|
|
|
36
44
|
|
4
説明文編集
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
あるツールの
|
|
1
|
+
あるツールのDownloads配下のフォルダでインストールを実行(pip3 install package)しました。
|
|
2
2
|
|
|
3
|
-
インストール後、usr/local/bin配下に自動的にインストールされることを確認し、
|
|
3
|
+
Downloads配下のフォルダへのインストール後、usr/local/bin配下にも同じ名前のファイルが自動的にインストールされることを確認し、
|
|
4
4
|
|
|
5
|
-
下記のように、インストール場所が異なる同じファイル名のdumppdf.pyのファイル中身を確認した
|
|
5
|
+
下記のように、インストール場所が異なる同じファイル名のdumppdf.pyのファイル中身を確認しましたが、両ファイルの中身が違いました。
|
|
6
6
|
|
|
7
7
|
なぜ、同じファイル名にもかかわらず中身が異なるのでしょうか？
|
|
8
8
|
|
3
コード追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -30,6 +30,134 @@
|
|
|
30
30
|
|
|
31
31
|
|
|
32
32
|
|
|
33
|
+
|
|
33
34
|
|
|
34
35
|
|
|
36
|
+
|
|
37
|
+
Downloads配下
|
|
38
|
+
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
#!/usr/bin/env python3
|
|
42
|
+
|
|
43
|
+
"""Extract pdf structure in XML format"""
|
|
44
|
+
|
|
45
|
+
import logging
|
|
46
|
+
|
|
47
|
+
import os.path
|
|
48
|
+
|
|
49
|
+
import re
|
|
50
|
+
|
|
51
|
+
import sys
|
|
52
|
+
|
|
53
|
+
import warnings
|
|
54
|
+
|
|
55
|
+
from argparse import ArgumentParser
|
|
56
|
+
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
import pdfminer
|
|
60
|
+
|
|
61
|
+
from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines, PDFXRefFallback, \
|
|
62
|
+
|
|
63
|
+
PDFNoValidXRefWarning
|
|
64
|
+
|
|
65
|
+
from pdfminer.pdfpage import PDFPage
|
|
66
|
+
|
|
67
|
+
from pdfminer.pdfparser import PDFParser
|
|
68
|
+
|
|
69
|
+
from pdfminer.pdftypes import PDFObjectNotFound, PDFValueError
|
|
70
|
+
|
|
71
|
+
from pdfminer.pdftypes import PDFStream, PDFObjRef, resolve1, stream_value
|
|
72
|
+
|
|
73
|
+
from pdfminer.psparser import PSKeyword, PSLiteral, LIT
|
|
74
|
+
|
|
75
|
+
from pdfminer.utils import isnumber
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
logging.basicConfig()
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
ESC_PAT = re.compile(r'[\000-\037&<>()"\042\047\134\177-\377]')
|
|
84
|
+
|
|
85
|
+
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
def e(s):
|
|
90
|
+
|
|
91
|
+
if isinstance(s, bytes):
|
|
92
|
+
|
|
93
|
+
s = str(s, 'latin-1')
|
|
94
|
+
|
|
95
|
+
return ESC_PAT.sub(lambda m: '&#%d;' % ord(m.group(0)), s)
|
|
96
|
+
|
|
97
|
+
```
|
|
98
|
+
|
|
99
|
+
|
|
100
|
+
|
|
101
|
+
usr/local/bin配下
|
|
102
|
+
|
|
103
|
+
```
|
|
104
|
+
|
|
105
|
+
#!/usr/local/opt/python/bin/python3.7
|
|
106
|
+
|
|
107
|
+
#
|
|
108
|
+
|
|
35
|
-
|
|
109
|
+
# dumppdf.py - dump pdf contents in XML format.
|
|
110
|
+
|
|
111
|
+
#
|
|
112
|
+
|
|
113
|
+
# usage: dumppdf.py [options] [files ...]
|
|
114
|
+
|
|
115
|
+
# options:
|
|
116
|
+
|
|
117
|
+
# -i objid : object id
|
|
118
|
+
|
|
119
|
+
#
|
|
120
|
+
|
|
121
|
+
import sys, os.path, re
|
|
122
|
+
|
|
123
|
+
from io import StringIO
|
|
124
|
+
|
|
125
|
+
from pdfminer.psparser import PSKeyword, PSLiteral, LIT
|
|
126
|
+
|
|
127
|
+
from pdfminer.pdfparser import PDFParser
|
|
128
|
+
|
|
129
|
+
from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines
|
|
130
|
+
|
|
131
|
+
from pdfminer.pdftypes import PDFObjectNotFound, PDFValueError
|
|
132
|
+
|
|
133
|
+
from pdfminer.pdftypes import PDFStream, PDFObjRef, resolve1, stream_value
|
|
134
|
+
|
|
135
|
+
from pdfminer.pdfpage import PDFPage
|
|
136
|
+
|
|
137
|
+
from pdfminer.utils import isnumber, q
|
|
138
|
+
|
|
139
|
+
|
|
140
|
+
|
|
141
|
+
|
|
142
|
+
|
|
143
|
+
ESCAPE = set(map(ord, '&<>"'))
|
|
144
|
+
|
|
145
|
+
def encode(data):
|
|
146
|
+
|
|
147
|
+
buf = StringIO()
|
|
148
|
+
|
|
149
|
+
for b in data:
|
|
150
|
+
|
|
151
|
+
if b < 32 or 127 <= b or b in ESCAPE:
|
|
152
|
+
|
|
153
|
+
buf.write(f'&#{b};')
|
|
154
|
+
|
|
155
|
+
else:
|
|
156
|
+
|
|
157
|
+
buf.write(chr(b))
|
|
158
|
+
|
|
159
|
+
return buf.getvalue()
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
|
|
163
|
+
```
|
2
画像追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -32,4 +32,4 @@
|
|
|
32
32
|
|
|
33
33
|
|
|
34
34
|
|
|
35
|
-
|
1
タグ追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
File without changes
|