pdfmine

  • 环境：python2.7 + windows调试成功。
  • 测试文件test.pdf下载。

test.pdf

  1. import sys
  2. from pdfminer.pdfdocument import PDFDocument
  3. from pdfminer.pdfparser import PDFParser
  4. from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
  5. from pdfminer.pdfdevice import PDFDevice, TagExtractor
  6. from pdfminer.pdfpage import PDFPage
  7. from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
  8. from pdfminer.cmapdb import CMapDB
  9. from pdfminer.layout import LAParams
  10. from pdfminer.image import ImageWriter
  14. """
  15.         print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
  16.                ' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
  17.                ' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation] [-S]'
  18.                ' [-t text|html|xml|tag] [-c codec] [-s scale]'
  19.                ' file ...' % argv[0])
  20. """
  21. # main
  22. def extract_text(filename, password_param, output_file):
  24.     # debug option
  25.     debug = 0
  26.     # input option
  27.     password = ''
  28.     pagenos = set()
  29.     maxpages = 0
  30.     # output option
  31.     outfile = None
  32.     outtype = None
  33.     imagewriter = None
  34.     rotation = 0
  35.     stripcontrol = False
  36.     layoutmode = 'normal'
  37.     codec = 'utf-8'
  38.     pageno = 1
  39.     scale = 1
  40.     caching = True
  41.     showpageno = True
  42.     laparams = LAParams()
  44.     if filename.strip()[-4:] != '.pdf':
  45.         print 'file type is not pdf!'
  46.         return
  47.     elif output_file is not None:
  48.         outfile = output_file
  49.     else:
  50.         outfile = filename.strip()[:-4] + '.txt'
  51.         print 'output file path: %s' % outfile
  52.     if password_param is not None:
  53.         password = password_param
  55.     PDFDocument.debug = debug
  56.     PDFParser.debug = debug
  57.     CMapDB.debug = debug
  58.     PDFPageInterpreter.debug = debug
  59.     #
  60.     rsrcmgr = PDFResourceManager(caching=caching)
  61.     if not outtype:
  62.         outtype = 'text'
  63.         if outfile:
  64.             if outfile.endswith('.htm') or outfile.endswith('.html'):
  65.                 outtype = 'html'
  66.             elif outfile.endswith('.xml'):
  67.                 outtype = 'xml'
  68.             elif outfile.endswith('.tag'):
  69.                 outtype = 'tag'
  70.     if outfile:
  71.         outfp = file(outfile, 'w')
  72.     else:
  73.         outfp = sys.stdout
  74.     if outtype == 'text':
  75.         device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
  76.                                imagewriter=imagewriter)
  77.     elif outtype == 'xml':
  78.         device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
  79.                               imagewriter=imagewriter,
  80.                               stripcontrol=stripcontrol)
  81.     elif outtype == 'html':
  82.         device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
  83.                                layoutmode=layoutmode, laparams=laparams,
  84.                                imagewriter=imagewriter, debug=debug)
  85.     elif outtype == 'tag':
  86.         device = TagExtractor(rsrcmgr, outfp, codec=codec)
  87.     else:
  88.         return
  89.     fname = filename
  90.     fp = file(fname, 'rb')
  91.     interpreter = PDFPageInterpreter(rsrcmgr, device)
  92.     print 'extracting text in pdf ... ...'
  93.     page_cnt = 1
  94.     for page in PDFPage.get_pages(fp, pagenos,
  95.                                 maxpages=maxpages, password=password,
  96.                                 caching=caching, check_extractable=True):
  97.         page.rotate = (page.rotate+rotation) % 360
  98.         print 'processing page %d ...' % page_cnt
  99.         interpreter.process_page(page)
  100.         page_cnt += 1
  101.     fp.close()
  102.     device.close()
  103.     outfp.close()
  104.     print 'text has been written into %s ' % outfile
  105.     return outfile
  108. def check_line_valid(line):# only line like '1 ' will be invalid
  109.     line = line[:-1]
  110.     if line == '':
  111.         return True
  112.     digits = '0123456789'
  113.     for c in line:
  114.         if c != ' ' and c not in digits:
  115.             return True
  116.     return False
  119. def process_line(line):
  120.     if line != '\n':  # single line with '\n' will be ignored
  121.         line = line[:-1]
  122.         if line[-1:] == '-':
  123.             line = line[:-1]
  124.         else:
  125.             line += ' '
  126.     else:
  127.         line += '\n'
  128.     return line
  130. """
  131. """
  132. def reformat_output_file(outfile):
  133.     text_reformated = ''
  134.     file_handler = open(outfile)
  135.     line = file_handler.readline()
  136.     recording = False
  137.     while line:
  138.         if line == 'Abstract\n':
  139.             recording = True
  140.         if recording is True:
  141.             if check_line_valid(line):
  142.                 line = process_line(line)
  143.                 text_reformated += line
  144.         line = file_handler.readline()
  145.     file_handler.close()
  146.     print '%s has been reformated.' % outfile
  147.     file_reformated_name = outfile[:-4] + '.reformated.txt'
  148.     file_handler = open(file_reformated_name, 'w')
  149.     file_handler.write(text_reformated)
  150.     return text_reformated
  152. of = extract_text('D:/pdfmine/test.pdf', '', None)
  153. tr = reformat_output_file(of)