pdf2pacs/pdf2txt3.py at master · ysdede/pdf2pacs · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
# -*- coding: utf-8 -*-
import sys
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter


# main
def extTxt(fname, outfile):
    # 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
    # '-d': debug += 1
    laparams = LAParams()
    laparams.line_margin = float(30)
    laparams.word_margin = float(0.1)
    # '-n': laparams = None
    # '-A': laparams.all_texts = True
    # '-V': laparams.detect_vertical = True
    # '-M': laparams.char_margin = float(v)
    # '-F': laparams.boxes_flow = float(v)
    # '-Y': layoutmode = v
    #
    PDFDocument.debug = debug
    PDFParser.debug = debug
    CMapDB.debug = debug
    PDFResourceManager.debug = debug
    PDFPageInterpreter.debug = debug
    PDFDevice.debug = debug
    #
    rsrcmgr = PDFResourceManager(caching=caching)

    outtype = 'text'
    # outfile = 'SAMPLE/Output.tmp'

    outfp = file(outfile, 'w') if outfile else sys.stdout
    outLns = ''
    device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
                           imagewriter=imagewriter)
    # fname = 'SAMPLE/sample.pdf'

    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

# if __name__ == '__main__': sys.exit(main(sys.argv))