python读取pdf里的文字、图片以及图片里的文字_python 读pdf中图片

import pdfplumber
import fitz
from PIL import Image
from aip import AipOcr
import re
import threading
import xlwt
import numpy as np
import pandas as pd

# ##提取pdf文档的文字写入运动报告.txt中

pdf_name=r'C:\Users\Pert\Desktop\公司文档\食物\中国食物成分表 标准版 第6版 第1册_14452917_.pdf'

# f=open('运动报告.txt','w',encoding="utf-8")
# pdf=pdfplumber.open(pdf_name)

# page_count = len(pdf.pages)
# print(page_count)  # 得到页数

# for page in pdf.pages:
#     # print('---------- 第[%d]页 ----------' % page.page_number)
#     # # 获取当前页面的全部文本信息，包括表格中的文字
#     # print(page.extract_text())
#     f.write(str(page.extract_text()))
  
# f.close()
# pdf.close()




class Acqire:
	def __init__(self):
		self.APP_ID = '24414511'
		self.API_KEY = 'OUogI3CydVfG54yeK4NwnYQt'
		self.SECRET_KEY = 'swhZn760fvuTAvppUHbCC3CAkRK7Xngw'

	### 改变图片尺寸
	def ResizeImage(self,path2):
	    filein = path2
	    fileout = path2
	    width = 1600
	    height = 2000
	    img = Image.open(filein)
	    out = img.resize((width, height),Image.ANTIALIAS)
	    out.save(fileout)
	    img.close()

	def get_file_content(self,filepath,num):
		def printI():
		    self.ResizeImage(filepath)
		    client = AipOcr(self.APP_ID,self.API_KEY,self.SECRET_KEY)
		    with open(filepath, 'rb') as fp:
		        image = fp.read()
		    fp.close()
		     # 定义参数变量
		    options = {
		        # 定义图像方向
		        'detect-direction': 'true',
		        'language-type': 'CHN_ENG'
		    }
		    result = client.general(image, options)
		    fp=open('txt/{}.txt'.format(num),'w')
		    try:
		    	for word in result['words_result']:
			    	fp.write(word['words'])
			    	fp.write('\n')
		    except:
		    	print(num)
		    fp.close()
		return printI

	def func(self,doc,i):
		imglist = doc.getPageImageList(i)
		for j, img in enumerate(imglist):
			xref = img[0]
			pix = fitz.Pixmap(doc, xref)   # make pixmap from image
			if pix.n - pix.alpha < 4:      # can be saved as PNG
				pix.writePNG("image/p%s-%s.png" % (i+1, j+1))
			else:
				pix0 = fitz.Pixmap(fitz.csRGB, pix)
				pix0.writePNG("image/p%s-%s.png" % (i+1, j+1))
				pix0 = None                # free Pixmap resources
			pix = None                     # free Pixmap resources


######提取pdf里面的图片
doc=fitz.open(pdf_name)
print(len(doc))
for i in range(len(doc)):
	locals()['thread_'+str(i)]=threading.Thread(target = Acqire().func(doc,i))
	locals()['thread_'+str(i)].start()

######识别图片里的文字
x=6
filepath='img/p{}-1.png'.format(x)
locals()['thread_'+str(x)]=threading.Thread(target = Acqire().get_file_content(filepath,x))
locals()['thread_'+str(x)].start()
locals()['thread_'+str(x)].join()
doc.close()
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