Python的PDFMIner - PDF到CSV

Question

我希望能够以PDF文件转换成CSV文件，并发现了一些有用的脚本，但是，作为新的Python，我有一个问题：

你在哪里指定的文件路径PDF和您想要打印的CSV？

我使用Python 2.7.11和PDFMiner 20140328.

import sys 
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter 
from pdfminer.pdfpage import PDFPage 
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter 
from pdfminer.layout import LAParams 
from cStringIO import StringIO 

def pdfparser(data): 

    fp = file(data, 'rb') 
    rsrcmgr = PDFResourceManager() 
    retstr = StringIO() 
    codec = 'utf-8' 
    laparams = LAParams() 
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams) 
    interpreter = PDFPageInterpreter(rsrcmgr, device) 


    for page in PDFPage.get_pages(fp): 
    interpreter.process_page(page) 
    data = retstr.getvalue() 

    print data 

if __name__ == '__main__': 
pdfparser(sys.argv[1]) 

Answer 1

下面是一些this修改后的代码SO回答tgray写：

def pdf_to_csv(filename, separator, threshold): 
    from cStringIO import StringIO 
    from pdfminer.converter import LTChar, TextConverter 
    from pdfminer.layout import LAParams 
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter 
    from pdfminer.pdfpage import PDFPage 

    class CsvConverter(TextConverter): 
     def __init__(self, *args, **kwargs): 
      TextConverter.__init__(self, *args, **kwargs) 
      self.separator = separator 
      self.threshold = threshold 

     def end_page(self, i): 
      from collections import defaultdict 
      lines = defaultdict(lambda: {}) 
      for child in self.cur_item._objs: # <-- changed 
       if isinstance(child, LTChar): 
        (_, _, x, y) = child.bbox 
        line = lines[int(-y)] 
        line[x] = child._text.encode(self.codec) # <-- changed 
      for y in sorted(lines.keys()): 
       line = lines[y] 
       self.line_creator(line) 
       self.outfp.write(self.line_creator(line)) 
       self.outfp.write("\n") 

     def line_creator(self, line): 
      keys = sorted(line.keys()) 
      # calculate the average distange between each character on this row 
      average_distance = sum([keys[i] - keys[i - 1] for i in range(1, len(keys))])/len(keys) 
      # append the first character to the result 
      result = [line[keys[0]]] 
      for i in range(1, len(keys)): 
       # if the distance between this character and the last character is greater than the average*threshold 
       if (keys[i] - keys[i - 1]) > average_distance * self.threshold: 
        # append the separator into that position 
        result.append(self.separator) 
       # append the character 
       result.append(line[keys[i]]) 
      printable_line = ''.join(result) 
      return printable_line 

    # ... the following part of the code is a remix of the 
    # convert() function in the pdfminer/tools/pdf2text module 
    rsrc = PDFResourceManager() 
    outfp = StringIO() 
    device = CsvConverter(rsrc, outfp, codec="utf-8", laparams=LAParams()) 
    # becuase my test documents are utf-8 (note: utf-8 is the default codec) 

    fp = open(filename, 'rb') 

    interpreter = PDFPageInterpreter(rsrc, device) 
    for i, page in enumerate(PDFPage.get_pages(fp)): 
     outfp.write("START PAGE %d\n" % i) 
     if page is not None: 
      print 'none' 
      interpreter.process_page(page) 
     outfp.write("END PAGE %d\n" % i) 

    device.close() 
    fp.close() 

    return outfp.getvalue() 


if __name__ == '__main__': 
    # the separator to use with the CSV 
    separator = ';' 
    # the distance multiplier after which a character is considered part of a new word/column/block. Usually 1.5 works quite well 
    threshold = 1.5 
    print pdf_to_csv('myLovelyFile.pdf', separator, threshold) 

的答案之间的主要区别链接和这一个是line_creator方法，它试图从PDF中提取一些结构。

应与PDFminer工作20140328.