Esempio n. 1
0
    def work(self, filename, inpath, outpath):
        password = ""
        pagenos = set()
        maxpages = 0
        caching = True

        debug = 0
        PDFDocument.debug = debug
        PDFParser.debug = debug
        CMapDB.debug = debug
        PDFResourceManager.debug = debug
        PDFPageInterpreter.debug = debug
        PDFDevice.debug = debug
        infile = inpath + filename + ".pdf"
        outfile = outpath + filename + ".txt"

        rsrcmgr = PDFResourceManager(caching=caching)
        outfp = file(outfile, "w")
        codec = "utf-8"
        laparams = LAParams()
        imagewriter = None

        device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, imagewriter=imagewriter)

        fp = file(infile, "rb")

        process_pdf(
            rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password, caching=caching, check_extractable=True
        )

        fp.close()
        device.close()
        outfp.close()
        return
Esempio n. 2
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
Esempio n. 3
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
Esempio n. 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