Python使用PDFMiner解析PDF代码实例

# make cmap

python tools/conv_cmap.py pdfminer/cmap Adobe-CNS1 cmaprsrc/cid2code_Adobe_CNS1.txtreading 'cmaprsrc/cid2code_Adobe_CNS1.txt'...writing 'CNS1_H.py'......(this may take several minutes) 

# python setup.py install 

#!/usr/bin/python

import sys
import os
from binascii import b2a_hex

###
### pdf-miner requirements
###

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox, LTTextLine, LTFigure, LTImage, LTChar

def with_pdf (pdf_doc, fn, pdf_pwd, *args):
 """Open the pdf document, and apply the function, returning the results"""
 result = None
 try:
  # open the pdf file
  fp = open(pdf_doc, 'rb')
  # create a parser object associated with the file object
  parser = PDFParser(fp)
  # create a PDFDocument object that stores the document structure
  doc = PDFDocument(parser, pdf_pwd)
  # connect the parser and document objects
  parser.set_document(doc)
  # supply the password for initialization

  if doc.is_extractable:
   # apply the function and return the result
   result = fn(doc, *args)

  # close the pdf file
  fp.close()
 except IOError:
  # the file doesn't exist or similar problem
  pass
 return result


### 
### Table of Contents
### 

def _parse_toc (doc):
 """With an open PDFDocument object, get the table of contents (toc) data
 [this is a higher-order function to be passed to with_pdf()]"""
 toc = []
 try:
  outlines = doc.get_outlines()
  for (level,title,dest,a,se) in outlines:
   toc.append( (level, title) )
 except PDFNoOutlines:
  pass
 return toc

def get_toc (pdf_doc, pdf_pwd=''):
 """Return the table of contents (toc), if any, for this pdf file"""
 return with_pdf(pdf_doc, _parse_toc, pdf_pwd)


###
### Extracting Images
###

def write_file (folder, filename, filedata, flags='w'):
 """Write the file data to the folder and filename combination
 (flags: 'w' for write text, 'wb' for write binary, use 'a' instead of 'w' for append)"""
 result = False
 if os.path.isdir(folder):
  try:
   file_obj = open(os.path.join(folder, filename), flags)
   file_obj.write(filedata)
   file_obj.close()
   result = True
  except IOError:
   pass
 return result

def determine_image_type (stream_first_4_bytes):
 """Find out the image file type based on the magic number comparison of the first 4 (or 2) bytes"""
 file_type = None
 bytes_as_hex = b2a_hex(stream_first_4_bytes)
 if bytes_as_hex.startswith('ffd8'):
  file_type = '.jpeg'
 elif bytes_as_hex == '89504e47':
  file_type = '.png'
 elif bytes_as_hex == '47494638':
  file_type = '.gif'
 elif bytes_as_hex.startswith('424d'):
  file_type = '.bmp'
 return file_type

def save_image (lt_image, page_number, images_folder):
 """Try to save the image data from this LTImage object, and return the file name, if successful"""
 result = None
 if lt_image.stream:
  file_stream = lt_image.stream.get_rawdata()
  if file_stream:
   file_ext = determine_image_type(file_stream[0:4])
   if file_ext:
    file_name = ''.join([str(page_number), '_', lt_image.name, file_ext])
    if write_file(images_folder, file_name, file_stream, flags='wb'):
     result = file_name
 return result


###
### Extracting Text
###

def to_bytestring (s, enc='utf-8'):
 """Convert the given unicode string to a bytestring, using the standard encoding,
 unless it's already a bytestring"""
 if s:
  if isinstance(s, str):
   return s
  else:
   return s.encode(enc)

def update_page_text_hash (h, lt_obj, pct=0.2):
 """Use the bbox x0,x1 values within pct% to produce lists of associated text within the hash"""

 x0 = lt_obj.bbox[0]
 x1 = lt_obj.bbox[2]

 key_found = False
 for k, v in h.items():
  hash_x0 = k[0]
  if x0 >= (hash_x0 * (1.0-pct)) and (hash_x0 * (1.0+pct)) >= x0:
   hash_x1 = k[1]
   if x1 >= (hash_x1 * (1.0-pct)) and (hash_x1 * (1.0+pct)) >= x1:
    # the text inside this LT* object was positioned at the same
    # width as a prior series of text, so it belongs together
    key_found = True
    v.append(to_bytestring(lt_obj.get_text()))
    h[k] = v
 if not key_found:
  # the text, based on width, is a new series,
  # so it gets its own series (entry in the hash)
  h[(x0,x1)] = [to_bytestring(lt_obj.get_text())]

 return h

def parse_lt_objs (lt_objs, page_number, images_folder, text=[]):
 """Iterate through the list of LT* objects and capture the text or image data contained in each"""
 text_content = [] 

 page_text = {} # k=(x0, x1) of the bbox, v=list of text strings within that bbox width (physical column)
 for lt_obj in lt_objs:
  if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
   # text, so arrange is logically based on its column width
   page_text = update_page_text_hash(page_text, lt_obj)
  elif isinstance(lt_obj, LTImage):
   # an image, so save it to the designated folder, and note its place in the text 
   saved_file = save_image(lt_obj, page_number, images_folder)
   if saved_file:
    # use html style <img /> tag to mark the position of the image within the text
    text_content.append('<img src="/UploadFiles/2021-04-08/'+os.path.join(images_folder, saved_file)+'">

这段代码重点在于第１２８行，可以看到PDFMiner是一种基于坐标来解析的框架，PDF中能解析的组件全都包括上下左右边缘的坐标，如x0 = lt_obj.bbox[0]就是lt_obj元素的左边缘的坐标，同理x1则为右边缘。以上代码的意思就是把所有x0且x1的坐标相差在２０％以内的元素分成一组，这样就实现了从PDF文件中定向抽取内容。
－－－－－－－－－－－－－－－－补充－－－－－－－－－－－－－－－－－－－－
有一个需要注意的地方，在解析有些PDF的时候会报这样的异常：pdfminer.pdfdocument.PDFEncryptionError: Unknown algorithm: param={'CF': {'StdCF': {'Length': 16, 'CFM': /AESV2, 'AuthEvent': /DocOpen}}, 'O': '\xe4\xe74\xb86/\xa8)\xa6x\xe6\xa3/U\xdf\x0fWR\x9cPh\xac\xae\x88B\x06_\xb0\x93@\x9f\x8d', 'Filter': /Standard, 'P': -1340, 'Length': 128, 'R': 4, 'U': '|UTX#f\xc9V\x18\x87z\x10\xcb\xf5{\xa7\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00', 'V': 4, 'StmF': /StdCF, 'StrF': /StdCF}
从字面意思来看是因为这个PDF是一个加密的PDF，所以无法解析 ，但是如果直接打开PDF却是可以的并没有要求输密码什么的，原因是这个PDF虽然是加过密的，但密码是空，所以就出现了这样的问题。
解决这个的问题的办法是通过qpdf命令来解密文件（要确保已经安装了qpdf），要想在python中调用该命令只需使用call即可：


 from subprocess import call
call('qpdf --password=%s --decrypt %s %s' %('', file_path, new_file_path), shell=True)


其中参数file_path是要解密的PDF的路径，new_file_path是解密后的PDF文件路径，然后使用解密后的文件去做解析就OK了
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。