python读取PDF文件内容 

 1 import os
 2 from pdfminer.pdfparser import PDFParser
 3 from pdfminer.pdfdocument import PDFDocument
 4 from pdfminer.pdfpage import PDFPage
 5 from pdfminer.pdfpage import PDFTextExtractionNotAllowed
 6 from pdfminer.pdfinterp import PDFResourceManager
 7 from pdfminer.pdfinterp import PDFPageInterpreter
 8 from pdfminer.pdfdevice import PDFDevice
 9 from pdfminer.layout import *
10 from pdfminer.converter import PDFPageAggregator
11 
12 
13 import os
14 import pdb
15 
16 #inputFile = r'D:\用户目录\桌面\340xxxxxxxxxxxxxxxxxx0.pdf'
17 
18 
19 def decode_text(s):
20     """
21     Decodes a PDFDocEncoding string to Unicode.
22     Adds py3 compatability to pdfminer's version.
23     """
24     if type(s) == bytes and s.startswith(b'\xfe\xff'):
25         return six.text_type(s[2:], 'utf-16be', 'ignore')
26     else:
27         ords = (ord(c) if type(c) == str else c for c in s)
28         return ''.join(PDFDocEncoding[o] for o in ords)
29 
30 
31 
32 def get_msgs(inputFile):
33     msgs = []
34     fp = open(inputFile, 'rb')
35     #来创建一个pdf文档分析器
36     parser = PDFParser(fp)  
37     #创建一个PDF文档对象存储文档结构
38     document = PDFDocument(parser)
39     # 检查文件是否允许文本提取
40     if not document.is_extractable:
41         raise PDFTextExtractionNotAllowed
42     else:
43         # 创建一个PDF资源管理器对象来存储共赏资源
44         rsrcmgr=PDFResourceManager()
45         # 设定参数进行分析
46         laparams=LAParams()
47         # 创建一个PDF设备对象
48         # device=PDFDevice(rsrcmgr)
49         device=PDFPageAggregator(rsrcmgr,laparams=laparams)
50         # 创建一个PDF解释器对象
51         interpreter=PDFPageInterpreter(rsrcmgr,device)
52      
53         # 处理每一页
54         for page in PDFPage.create_pages(document):
55      
56             interpreter.process_page(page)
57      
58             # 接受该页面的LTPage对象
59             layout=device.get_result()
60      
61             for x in layout:
62                 
63                 if(isinstance(x,LTTextBoxHorizontal)):
64                     #print(x.get_text().strip())
65                     
66                     msgs.append(x.get_text().strip())
67                     
68         return msgs
69                    
70 
71 
72     #print(msgs[5][5:]+ '\t' + msgs[4][4:])
73     
74 
75 
76 if __name__ == "__main__":
77     names = os.listdir('.')
78     for i in names:
79         if os.path.splitext(i)[-1] == '.pdf':
80             #print(i)
81             msg = get_msgs(i)
82             #print(msg)
83             ms = msg[5][5:]+ '\t' + msg[4][4:]
84             with open('学生信息表.txt','a') as f:
85                 f.write(ms+'\n')
86

 

posted @ 2019-11-14 16:46  了解2号  阅读(1551)  评论(0)    收藏  举报