图片版pdf无法复制,转化成文字版的pdf后使用更方便.
我们需要用到python3.6,pypdf2,ghostscript,pythonmagick,百度文字识别服务和pdfkit.
安装
安装python3.6 略
安装ghostscript
https://ghostscript.com/download/gsdnld.html
安装wkhtmltopdf
https://wkhtmltopdf.org/downloads.html
pip安装pypdf2,ghostscript,baidu-aip,pdfkit
|
1
2
3
4
|
pip install pypdf2
pip install ghostscript
pip install baidu-aip
pip install pdfkit
|
pip安装pythonmagick
https://www.lfd.uci.edu/~gohlke/pythonlibs/
|
1
2
|
cd 下载目录
pip install pythonmagick‑0.9.13‑cp36‑cp36m‑win_amd64.whl
|
pypdf2用于拆分和合并pdf
示例代码如下:
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
#导入pdffilereader和pdffilewriter
from pypdf2 import pdffilereader, pdffilewriter
#获取一个pdf对象
pdf_input = pdffilereader(open(r'pdf路径', 'rb'))
#获取pdf页数
page_count = pdf_input.getnumpages()
#获取pdf第四页的内容
page = pdf_input.getpage(3)
page['/contents']
#获取一个pdfwriter对象
pdf_output = pdffilewriter()
# 将一个 pageobject 加入到 pdffilewriter 中
pdf_output.addpage(page)
#把新pdf保存
pdf_output.write(open(r'新pdf路径','wb'))
|
pythonmagick用于将单页pdf转化为jpg
百度云-文字识别-python sdk
每天有500次免费的识别
示例代码如下:
|
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
|
#导入baidu-aip
from aip import aipocr
#https://console.bce.baidu.com/#/index/overview
#产品服务->人工智能->文字识别->创建应用
#获取以下三个值
app_id = '??'
api_key = '??'
secret_key = '?? '
#新建一个aipocr
client = aipocr(app_id, api_key, secret_key)
#读取本地图片的函数
def get_file_content(filepath):
with open(filepath, 'rb') as fp:
return fp.read()
#读取本地图片
image = get_file_content('p1.jpg')
#可选参数
options = {}
options["language_type"] = "chn_eng"
options["detect_direction"] = "true"
options["detect_language"] = "true"
options["probability"] = "true"
#通用文字识别
client.basicgeneral(image, options)
#读取网络图片
url = "https://note.youdao.com/yws/public/resource/1577071c1ffa2b6bf4e238ef6dbcfbf5/xmlnote/e5a19bedfeba4879b217c5bbf53b0245/22138"
#可选参数
options = {}
options["language_type"] = "chn_eng"
options["detect_direction"] = "true"
options["detect_language"] = "true"
options["probability"] = "true"
#通用文字识别
client.basicgeneralurl(url, options)
#读取本地表格图片的函数
def get_file_content(filepath):
with open(filepath, 'rb') as fp:
return fp.read()
#读取本地表格图片
image = get_file_content('p2.jpg')
#可选参数
options = {}
options["language_type"] = "chn_eng"
options["detect_direction"] = "true"
options["detect_language"] = "true"
options["probability"] = "true"
#通用文字识别
client.basicgeneral(image, options)
#读取表格分割效果较差!
|
pdfkit用于利用字符串生成pdf
示例代码如下:
|
1
2
3
4
5
6
7
|
#pdfkit安装位置设置
path_wk = r'pdfkit安装位置设置'
pdfkit_config = pdfkit.configuration(wkhtmltopdf = path_wk)
#pdfkit参数
pdfkit_options = {'encoding': 'utf-8',}
#制作pdf
pdfkit.from_string(('string'),'d:\test.pdf',configuration=pdfkit_config,options=pdfkit_options)
|
完整代码如下
|
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
|
#导入所需包
#os,操作文件和路径
import os
#ghostscript,代码简化
import ghostscript
#pypdf2,拆分pdf
from pypdf2 import pdffilereader, pdffilewriter
#pythonmagick,单页pdf转图片
from pythonmagick import image
#baidu-aip,百度文字识别
from aip import aipocr
#pdfkit,字符串制作pdf
import pdfkit
#参数
path='??'
pdfname='??'
dpi='85'
#https://console.bce.baidu.com/#/index/overview
#产品服务->人工智能->文字识别->创建应用
#获取以下三个值
app_id = '??'
api_key = '??'
secret_key = '?? '
#pdfkit安装位置设置
path_wk = r'pdfkit安装位置设置'
pdfkit_config = pdfkit.configuration(wkhtmltopdf = path_wk)
#pdfkit参数
pdfkit_options = {'encoding': 'utf-8',}
#pdf转化为图片
os.chdir(path)
pdf_input = pdffilereader(open(pdfname, 'rb'))
#自动获取pdf页数
page_count = pdf_input.getnumpages()
page_range=range(page_count)
#也可以手工指定pdf需要转换的页数
#page_range=range(0,100)
#使用pypdf和ghostscript
#==超级好用,超级直观,超级短==
for page_num in page_range:
im = image()
im.density(dpi)
im.read(pdfname + '[' + str(page_num) +']')
im.write(str(page_num)+ '.jpg')
#图片转化为字符串
#新建一个aipocr
client = aipocr(app_id, api_key, secret_key)
#读取本地图片的函数
def get_file_content(filepath):
with open(filepath, 'rb') as fp:
return fp.read()
#可选参数
options = {}
options["language_type"] = "chn_eng"
options["detect_direction"] = "false"
options["detect_language"] = "false"
options["probability"] = "false"
allteststr=[]
for page_num in page_range:
#读取本地图片
image = get_file_content(r'%s\%s.jpg' % (path,page_num))
#通用文字识别,得到的是一个dict
testjson=client.basicgeneral(image, options)
teststr=''
for x in testjson['words_result']:
teststr=teststr+x['words']+'</br>'
allteststr.append(teststr)
#字符串写入pdf
for page_num in page_range:
pdfkit.from_string((allteststr[page_num]),'%s.pdf' % (str(page_num)),configuration=pdfkit_config,options=pdfkit_options)
#合并单页pdf
pdf_output = pdffilewriter()
for page_num in page_range:
os.chdir(path)
pdf_input = pdffilereader(open('%s.pdf' % (str(page_num)), 'rb'))
page = pdf_input.getpage(0)
pdf_output.addpage(page)
pdf_output.write(open('newpdf.pdf','wb'))
|
以上就是为大家介绍的如何使用python3.6,pypdf2,ghostscript,pythonmagick,百度文字识别服务和pdfkit
原文链接：https://blog.csdn.net/sqq513/article/details/79368243