Пример #1
0
def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos = set()

    for page in PDFPage.get_pages(fp,
                                  pagenos,
                                  maxpages=maxpages,
                                  password=password,
                                  caching=caching,
                                  check_extractable=True):
        interpreter.process_page(page)

    text = retstr.getvalue()

    fp.close()
    device.close()
    retstr.close()
    return text
Пример #2
0
def pdf2text(path):
    x = os.path.split(path)
    new_f_name = x[-1]
    if new_f_name.endswith('.pdf'):
        new_f_txt = new_f_name.replace('.pdf', '.txt')
    elif new_f_name.endswith('.PDF'):
        new_f_txt = new_f_name.replace('.PDF', '.txt')
    print(new_f_txt)
    os.chdir(output_path)
    f = open(new_f_txt, "a")
    try:
        rsrcmgr = PDFResourceManager()
        retstr = io.StringIO()
        codec = 'utf-8'
        laparams = LAParams()
        device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.get_pages(f):
            interpreter.process_page(page)
            path = retstr.getvalue()
        print(path)
    except:
        print('This pdf contains images. Starting OCR....')
        pages = convert_from_path(path, 500)
        image_counter = 1
        for page in pages:
            filename = "page_" + str(image_counter) + ".jpg"
            page.save(filename, 'JPEG')
            image_counter = image_counter + 1
        filelimit = image_counter - 1
        for i in range(1, filelimit + 1):
            filename = "page_" + str(i) + ".jpg"
            text = str(((pytesseract.image_to_string(Image.open(filename)))))
            text = text.replace('-\n', '')
            f.write(text)
        f.close()
        del_files = glob.glob(output_path + '*')
        for i in del_files:
            if i.endswith(".jpg") or i.endswith(".jpeg") or i.endswith(".JPG"):
                os.remove(i)
        print('OCRed file: %s is available' % (new_f_txt))
        print('Deleted all images to the above job')
Пример #3
0
def pdf2txt(outfp, rsrc, fname, pages, codec, password='', debug=0):
  device = TextConverter(rsrc, debug=debug)
  doc = PDFDocument(debug=debug)
  fp = file(fname, 'rb')
  parser = PDFParser(doc, fp, debug=debug)
  try:
    doc.initialize(password)
  except PDFPasswordIncorrect:
    raise TextExtractionNotAllowed('incorrect password')
  if not doc.is_extractable:
    raise TextExtractionNotAllowed('text extraction is not allowed: %r' % fname)
  interpreter = PDFPageInterpreter(rsrc, device, debug=debug)
  outfp.write('<document>\n')
  for (i,page) in enumerate(doc.get_pages(debug=debug)):
    if pages and (i not in pages): continue
    device.reset()
    interpreter.process_page(page)
    device.dump(outfp, codec)
  fp.close()
  device.close()
  outfp.write('</document>\n')
  return
Пример #4
0
def main(argv):
    import getopt

    def usage():
        #print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
        #       ' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
        #       ' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation]'
        #       ' [-t text|html|xml|tag] [-c codec] [-s scale]'
        #       ' file ...' % argv[0])
        return 100

    try:
        (opts, args) = getopt.getopt(argv[1:],
                                     'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    # debug option
    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = None
    rotation = 0
    layoutmode = 'normal'
    codec = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == '-d': debug += 1
        elif k == '-p': pagenos.update(int(x) - 1 for x in v.split(','))
        elif k == '-m': maxpages = int(v)
        elif k == '-P': password = v
        elif k == '-o': outfile = v
        elif k == '-C': caching = False
        elif k == '-n': laparams = None
        elif k == '-A': laparams.all_texts = True
        elif k == '-V': laparams.detect_vertical = True
        elif k == '-M': laparams.char_margin = float(v)
        elif k == '-L': laparams.line_margin = float(v)
        elif k == '-W': laparams.word_margin = float(v)
        elif k == '-F': laparams.boxes_flow = float(v)
        elif k == '-Y': layoutmode = v
        elif k == '-O': imagewriter = ImageWriter(v)
        elif k == '-R': rotation = int(v)
        elif k == '-t': outtype = v
        elif k == '-c': codec = v
        elif k == '-s': scale = float(v)
    #
    PDFDocument.debug = debug
    PDFParser.debug = debug
    CMapDB.debug = debug
    PDFResourceManager.debug = debug
    PDFPageInterpreter.debug = debug
    PDFDevice.debug = debug
    #
    rsrcmgr = PDFResourceManager(caching=caching)
    if not outtype:
        outtype = 'text'
        if outfile:
            if outfile.endswith('.htm') or outfile.endswith('.html'):
                outtype = 'html'
            elif outfile.endswith('.xml'):
                outtype = 'xml'
            elif outfile.endswith('.tag'):
                outtype = 'tag'
    if outfile:
        outfp = file(outfile, 'w')
    else:
        outfp = sys.stdout
    if outtype == 'text':
        device = TextConverter(rsrcmgr,
                               outfp,
                               codec=codec,
                               laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr,
                              outfp,
                              codec=codec,
                              laparams=laparams,
                              imagewriter=imagewriter)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr,
                               outfp,
                               codec=codec,
                               scale=scale,
                               layoutmode=layoutmode,
                               laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()
    for fname in args:
        fp = file(fname, 'rb')
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.get_pages(fp,
                                      pagenos,
                                      maxpages=maxpages,
                                      password=password,
                                      caching=caching,
                                      check_extractable=True):
            page.rotate = (page.rotate + rotation) % 360
            interpreter.process_page(page)
        fp.close()
    device.close()
    outfp.close()
    return
Пример #5
0
def main(argv):
    try:
        (opts, args) = getopt.getopt(argv[1:],
                                     'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    # debug option
    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = None
    rotation = 0
    layoutmode = 'normal'
    codec = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    PDFDocument.debug = debug
    PDFParser.debug = debug
    CMapDB.debug = debug
    PDFResourceManager.debug = debug
    PDFPageInterpreter.debug = debug
    PDFDevice.debug = debug
    #
    rsrcmgr = PDFResourceManager(caching=caching)
    if not outtype:
        outtype = 'text'
        if outfile:
            if outfile.endswith('.htm') or outfile.endswith('.html'):
                outtype = 'html'
            elif outfile.endswith('.xml'):
                outtype = 'xml'
            elif outfile.endswith('.tag'):
                outtype = 'tag'
    if outfile:
        outfp = file(outfile, 'w')
    else:
        outfp = sys.stdout
    if outtype == 'text':
        device = TextConverter(rsrcmgr,
                               outfp,
                               codec=codec,
                               laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr,
                              outfp,
                              codec=codec,
                              laparams=laparams,
                              imagewriter=imagewriter)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr,
                               outfp,
                               codec=codec,
                               scale=scale,
                               layoutmode=layoutmode,
                               laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()
    for fname in args:
        fp = file(fname, 'rb')
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.get_pages(fp,
                                      pagenos,
                                      maxpages=maxpages,
                                      password=password,
                                      caching=caching,
                                      check_extractable=True):
            page.rotate = (page.rotate + rotation) % 360
            interpreter.process_page(page)
        fp.close()
    device.close()
    outfp.close()
    return
Пример #6
0
def main(argv):
    import getopt
    def usage():
        #print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
        #       ' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
        #       ' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation]'
        #       ' [-t text|html|xml|tag] [-c codec] [-s scale]'
        #       ' file ...' % argv[0])
        return 100
    try:
        (opts, args) = getopt.getopt(argv[1:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    # debug option
    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = None
    rotation = 0
    layoutmode = 'normal'
    codec = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == '-d': debug += 1
        elif k == '-p': pagenos.update( int(x)-1 for x in v.split(',') )
        elif k == '-m': maxpages = int(v)
        elif k == '-P': password = v
        elif k == '-o': outfile = v
        elif k == '-C': caching = False
        elif k == '-n': laparams = None
        elif k == '-A': laparams.all_texts = True
        elif k == '-V': laparams.detect_vertical = True
        elif k == '-M': laparams.char_margin = float(v)
        elif k == '-L': laparams.line_margin = float(v)
        elif k == '-W': laparams.word_margin = float(v)
        elif k == '-F': laparams.boxes_flow = float(v)
        elif k == '-Y': layoutmode = v
        elif k == '-O': imagewriter = ImageWriter(v)
        elif k == '-R': rotation = int(v)
        elif k == '-t': outtype = v
        elif k == '-c': codec = v
        elif k == '-s': scale = float(v)
    #
    PDFDocument.debug = debug
    PDFParser.debug = debug
    CMapDB.debug = debug
    PDFResourceManager.debug = debug
    PDFPageInterpreter.debug = debug
    PDFDevice.debug = debug
    #
    rsrcmgr = PDFResourceManager(caching=caching)
    if not outtype:
        outtype = 'text'
        if outfile:
            if outfile.endswith('.htm') or outfile.endswith('.html'):
                outtype = 'html'
            elif outfile.endswith('.xml'):
                outtype = 'xml'
            elif outfile.endswith('.tag'):
                outtype = 'tag'
    if outfile:
        outfp = file(outfile, 'w')
    else:
        outfp = sys.stdout
    if outtype == 'text':
        device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
                              imagewriter=imagewriter)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
                               layoutmode=layoutmode, laparams=laparams,
                               imagewriter=imagewriter)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()
    for fname in args:
        fp = file(fname, 'rb')
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.get_pages(fp, pagenos,
                                      maxpages=maxpages, password=password,
                                      caching=caching, check_extractable=True):
            page.rotate = (page.rotate+rotation) % 360
            interpreter.process_page(page)
        fp.close()
    device.close()
    outfp.close()
    return