Python LAParams.char_margin方法代码示例

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def get_result_from_file(filename):
    from pdfminer.pdfparser import PDFParser
    from pdfminer.pdfdocument import PDFDocument
    from pdfminer.pdfpage import PDFPage
    from pdfminer.pdfpage import PDFTextExtractionNotAllowed
    from pdfminer.pdfinterp import PDFResourceManager
    from pdfminer.pdfinterp import PDFPageInterpreter
    from pdfminer.converter import PDFPageAggregator
    from pdfminer.layout import LAParams

    result = {"filename": filename, "pages": []}
    fp = open(filename, "rb")
    parser = PDFParser(fp)
    document = PDFDocument(parser)
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    laparams.char_margin = 2.0
    laparams.detect_vertical = True
    laparams.line_margin = 1.0
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    page_index = 0
    for page in PDFPage.create_pages(document):
        interpreter.process_page(page)
        layout = device.get_result()
        bounding_box = get_bounding_box(layout)
        labels = get_text_labels(layout)
        result["pages"].append({"index": page_index, "bounding_box": bounding_box, "labels": labels})
        page_index += 1
    fp.close()
    return result

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def pdf2xml(infile):
    '''
    Return a string of XML representation for given PDF file handle.
    Uses pdfminer to do the conversion and does some final post-processing.
    '''

    outfile = StringIO()

    # Empirically determined...
    laparams = LAParams()
    laparams.char_margin = 0.4

    # See pdf2txt.py
    rsrcmgr = PDFResourceManager(caching=False)
    device = XMLConverter(rsrcmgr, outfile, codec='utf-8', laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    if page_api:
        for page in PDFPage.get_pages(infile, set()):
            interpreter.process_page(page)
    else:
        process_pdf(rsrcmgr, device, infile, set())

    infile.close()
    return outfile.getvalue().replace("\n", "")

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
    def parse(self, path):
		out = StringIO.StringIO()
		fp = None
        # Directory
		if os.path.isdir(path):
			raise NotImplementedError()
        # File
	       	else:
			fp = file(path)		
		rsrc = PDFResourceManager()
		codec = 'utf-8'
		laparams = LAParams()
		laparams.char_margin = 2.0
		laparams.line_margin = 2.0
		laparams.word_margin = 0.0
		device = TextConverter(rsrc, out, codec=codec, laparams=laparams)
		doc = PDFDocument()
		parser = PDFParser(fp)
		parser.set_document(doc)
		doc.set_parser(parser)
		doc.initialize()
		interpreter = PDFPageInterpreter(rsrc, device)
		for page in doc.get_pages():
			interpreter.process_page(page)
		device.close()
		sample = Sample(path, None, out.getvalue())
		out.close()
		return sample

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
    def parse_pdf(self, test_parse=False):
        """
            Parse a PDF and return text contents as an array
        """

        dtpo_log("debug", "parsePDF sourceFile -> '%s'", self.source_file)

        # input options
        pagenos = set()
        maxpages = 0
        # output option
        codec = "utf-8"
        caching = True
        laparams = LAParams()
        laparams.char_margin = 8.0
        laparams.word_margin = 2.0

        rsrcmgr = PDFResourceManager(caching=caching)

        try:
            outfp = file(self.text_file, "w")
        except IOError as io_error:
            raise DTPOFileError(self.text_file, 0, str(io_error))

        try:
            fp = file(self.source_file, "rb")
        except IOError as io_error:
            raise DTPOFileError(self.source_file, 0, str(io_error))

        try:
            device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams)
            process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, caching=caching, check_extractable=True)

        except PDFException as pdf_error:
            message = "Failed to parse file {0} -> {1}".format(self.source_file, str(pdf_error))
            raise DTPOFileError(self.source_file, 0, message)
        except Exception as exception:
            message = "Failed to parse PDF file Unknown exception {0} - > {1}".format(type(exception), str(exception))
            raise DTPOFileError(self.source_file, 0, message)

        fp.close()
        device.close()
        outfp.close()

        #   Got the PDF converted = now get it into an array
        self.file_array = []
        for line in open(self.text_file):
            self.file_array.append(line)

        #   Remove the last entry - it's always '\x0c'
        if len(self.file_array) > 0:
            del self.file_array[-1]

        #   Remove the outfile
        if not test_parse:
            os.remove(self.text_file)

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def convert_to_text_file(filename_in, filename_out, rewrite=False):
    """
        Parse file according to BORME PDF format

        filename:
        filenameOut:
    """

    if os.path.isdir(filename_out):
        filename_out = os.path.join(filename_out, os.path.basename(filename_in))

    if os.path.exists(filename_out) and not rewrite:
        logging.info('Skipping file %s already exists and rewriting is disabled!' % filename_out)
        return False

    # conf
    codec = 'utf-8'
    laparams = LAParams()
    imagewriter = None
    pagenos = set()
    maxpages = 0
    password = ''
    rotation = 0

    # <LAParams: char_margin=2.0, line_margin=0.5, word_margin=0.1 all_texts=False>
    laparams.detect_vertical = True
    laparams.all_texts = False
    laparams.char_margin = 2.0
    laparams.line_margin = 0.5
    laparams.word_margin = 0.1

    caching = True
    rsrcmgr = PDFResourceManager(caching=caching)
    outfp = open(filename_out, 'w')
    device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, imagewriter=imagewriter)
    fp = open(filename_in, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    # https://github.com/euske/pdfminer/issues/72
    #page = PDFPage()
    #PDFPage.cropbox =

    # y esto?
    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 True

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def readpdf(pdfFile):
    fp = open(pdfFile, 'rb')
    parser = PDFParser(fp)
    doc = PDFDocument(parser)
    #doc.initialize('password') # leave empty for no password

    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    laparams.char_margin = float('1.1') #too small and it splits the description, too big and Quantity-Unit-Part number are not separated: 1.1 seems to work
    laparams.line_margin = float('0.8')
    device = PDFPageDetailedAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    for page in PDFPage.create_pages(doc):
        interpreter.process_page(page)
        # receive the LTPage object for this page
        device.get_result()

    #print(device.rows)
    df = pd.DataFrame(device.rows, columns=['Page', 'x', 'y', 'c1','c2','String'])
    return df

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
    def read_file(self):
        with open(self.path, 'rb') as f:
            parser = PDFParser(f)
        doc = PDFDocument()
        parser.set_document(doc)
        doc.set_parser(parser)
        doc.initialize('')
        rsrcmgr = PDFResourceManager()
        laparams = LAParams()
        laparams.char_margin = 0.1
        laparams.word_margin = 1.0
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        extracted_text = []

        for page in doc.get_pages():
            interpreter.process_page(page)
            layout = device.get_result()
            for lt_obj in layout:
                if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
                    extracted_text.append(lt_obj.get_text())
        self.content = ' '.join(extracted_text)

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def main(argv=None):
    parser = argparse.ArgumentParser(description='Convert PDF into text.')
    parser.add_argument('file', nargs='*', type=argparse.FileType('rb'), default=sys.stdin, help='file(s) to convert')
    parser.add_argument('-C', '--nocache', dest='cache', action='store_false', help='prevent object caching (slower)')
    parser.add_argument('-l', metavar='level', default='warn', help='logging level (warn, info, debug)')
    parser.add_argument('-p', metavar='page', nargs='+', default=[], type=int, help='page number(s) (space separated)')
    parser.add_argument('-m', metavar='maxpages', default=0, type=int, help='maximum number of pages to extract')
    parser.add_argument('-P', metavar='password', default='', help='pdf password')
    parser.add_argument('-o', metavar='outfile', type=argparse.FileType('w'), default=sys.stdout,
                        help='output file name (default: stdout)')
    parser.add_argument('-O', metavar='directory', type=ImageWriter, help='extract images and save to directory')
    parser.add_argument('-t', metavar='outtype', help='output type (text, html, xml, tag)')
    parser.add_argument('-c', metavar='codec', default='utf-8', help='output text encoding (default: %(default)s)')
    lagroup = parser.add_argument_group(title='layout analysis')
    lagroup.add_argument('-n', action='store_true', help='disable layout analysis')
    lagroup.add_argument('-A', action='store_true', help='force layout analysis on all text')
    lagroup.add_argument('-V', action='store_true', help='detect vertical text')
    lagroup.add_argument('-M', metavar='char_margin', type=float, help='custom character margin')
    lagroup.add_argument('-L', metavar='line_margin', type=float, help='custom line margin')
    lagroup.add_argument('-W', metavar='word_margin', type=float, help='custom word margin')
    lagroup.add_argument('-F', metavar='boxes_flow', type=float, help='custom boxes flow')
    lagroup.add_argument('-Y', metavar='layout_mode', default='normal', help='layout mode for HTML (normal, exact, loose)')
    lagroup.add_argument('-s', metavar='scale', default=1, type=float, help='output scaling for HTML')
    args = parser.parse_args(argv)

    logging.basicConfig()
    logging.getLogger('pdfminer').setLevel(args.l.upper())

    laparams = LAParams()
    if args.n:
        laparams = None
    else:
        laparams.all_texts = args.A
        laparams.detect_vertical = args.V
        if args.M:
            laparams.char_margin = args.M
        if args.L:
            laparams.line_margin = args.L
        if args.W:
            laparams.word_margin = args.W
        if args.F:
            laparams.boxes_flow = args.F

    rsrcmgr = PDFResourceManager(caching=args.cache)
    outtype = args.t
    if not outtype:
        if args.o:
            if args.o.name.endswith('.htm') or args.o.name.endswith('.html'):
                outtype = 'html'
            elif args.o.name.endswith('.xml'):
                outtype = 'xml'
            elif args.o.name.endswith('.tag'):
                outtype = 'tag'
    if outtype == 'xml':
        device = XMLConverter(rsrcmgr, args.o, codec=args.c, laparams=laparams, imagewriter=args.O)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, args.o, codec=args.c, scale=args.s, layoutmode=args.Y,
                               laparams=laparams, imagewriter=args.O)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, args.o, codec=args.c)
    else:
        device = TextConverter(rsrcmgr, args.o, codec=args.c, laparams=laparams, imagewriter=args.O)
    for fp in args.file:
        process_pdf(rsrcmgr, device, fp, [i-1 for i in args.p], maxpages=args.m, password=args.P,
                    caching=args.cache, check_extractable=True)
        fp.close()
    device.close()
    if args.o is not sys.stdout:
        args.o.close()

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def main(argv):
    import getopt			#getopt 模块，它的功能是 获取执行命令行时附带的参数，关于getopt模块详细可参照http://www.16kan.com/post/207647.html
    def usage(): 			#usage() 函数，用于在用户输入错误命令或者命令输入不规范时，输出py文件的使用范例。当参数不足或错误时，usage()被调用
        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] [-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:t:c:s:')
		'''
		getopt函数的格式是getopt.getopt ( [命令行参数列表], "短选项", [长选项列表] )
		短选项名后的冒号(:)表示该选项必须有附加的参数。p,m,P,o,M,L,W,F,Y,O,t,c,s均为必须参数
		长选项名后的等号(=)表示该选项必须有附加的参数。
		返回opts和args。
		'''
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    # debug option
    debug = 0
    # input option
    password = ''			#参数P
    pagenos = set()			#参数p
    maxpages = 0			#参数m
    # output option
    outfile = None			#参数o output
    outtype = None			#参数t out type
    outdir = None			#参数O output directory
    layoutmode = 'normal'	#参数Y
    codec = 'utf-8'			#参数c
    pageno = 1				
    scale = 1				#参数s,暂缺M,L,F,Y四个参数
    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': outdir = 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:				#确认输出文件格式
        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)  #TextConverter貌似不能指定outdir参数
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, outdir=outdir)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
                               layoutmode=layoutmode, laparams=laparams, outdir=outdir)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()
    for fname in args:
        fp = file(fname, 'rb')
        process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
                    caching=caching, check_extractable=True)
        fp.close()
    device.close()
    outfp.close()
    return

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
#fp = open(r'C:/Users/ashmaro1/Documents/GitHub/Text-Analysis/PDFnOCR/data/POxca-000078-AN168846.pdf', 'rb')
#fp = open(r'C:/Users/ashmaro1/Documents/GitHub/Text-Analysis/PDFnOCR/data/POxca-000078-AN168968.pdf', 'rb')
#fp = open(r'C:/Users/ashmaro1/Documents/GitHub/Text-Analysis/PDFnOCR/data/POxca-000510-BX425914.pdf', 'rb')
#fp = open(r'C:/Users/ashmaro1/Documents/GitHub/Text-Analysis/PDFnOCR/data/POxca-000078-AN168907.pdf', 'rb')
#fp = open(r'C:/Users/ashmaro1/Documents/GitHub/Text-Analysis/PDFnOCR/data/POxca-000078-AN168907.pdf', 'rb')

#fp = open(r'S:/Bhavani/Aaron/POxca-000052-R201631.pdf', 'rb')
fp = open(r'C:/Users/ashmaro1/Documents/_Projects/Glencore/POxca-000052-R201631.pdf','rb')

parser = PDFParser(fp)
doc = PDFDocument(parser)
#doc.initialize('password') # leave empty for no password

rsrcmgr = PDFResourceManager()
laparams = LAParams()
laparams.char_margin = float('1.1') #too small and it splits the description, too big and Quantity-Unit-Part number are not separated: 1.4 seems to work
laparams.line_margin = float('0.8')
device = PDFPageDetailedAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)

for page in PDFPage.create_pages(doc):
    interpreter.process_page(page)
    # receive the LTPage object for this page
    device.get_result()

print(device.rows)
df = pd.DataFrame(device.rows, columns=['Page', 'x', 'y', 'c1','c2','String'])



# create text rows from 'y' coordinate data

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def main(argv):
    import getopt
    def usage():
        print ('usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output] '
               '[-n] [-A] [-D writing_mode] [-M char_margin] [-L line_margin] [-W word_margin] '
               '[-O output_dir] [-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:nAD:M:L:W:O: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
    outdir = None
    codec = 'utf-8'
    pageno = 1
    scale = 1
    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 == '-n': laparams = None
        elif k == '-A': laparams.all_texts = True
        elif k == '-D': laparams.writing_mode = v
        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 == '-O': outdir = v
        elif k == '-t': outtype = v
        elif k == '-c': codec = v
        elif k == '-s': scale = float(v)
    #
    CMapDB.debug = debug
    PDFResourceManager.debug = debug
    PDFDocument.debug = debug
    PDFParser.debug = debug
    PDFPageInterpreter.debug = debug
    PDFDevice.debug = debug
    #
    rsrc = PDFResourceManager()
    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(rsrc, outfp, codec=codec, laparams=laparams)
    elif outtype == 'xml':
        device = XMLConverter(rsrc, outfp, codec=codec, laparams=laparams, outdir=outdir)
    elif outtype == 'html':
        device = HTMLConverter(rsrc, outfp, codec=codec, scale=scale, laparams=laparams, outdir=outdir)
    elif outtype == 'tag':
        device = TagExtractor(rsrc, outfp, codec=codec)
    else:
        return usage()
    for fname in args:
        fp = file(fname, 'rb')
        process_pdf(rsrc, device, fp, pagenos, maxpages=maxpages, password=password)
        fp.close()
    device.close()
    outfp.close()
    return

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def main(argv):
    import getopt
    def usage():
        print 'Syntax:\npdf2htm.exe SourcePDF\n where the parameter is either a file name or\na wildcard spec like\n*.pdf\nEnclose it with quotes if it contains a space\n\nAdditional options are supported with named command line parameters as follows:'
        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 = 'tag'
    imagewriter = None
    rotation = 0
    layoutmode = 'normal'
    codec = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = False
    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 = 'tag'
        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

    for fname in args:
        l = glob.glob(fname)
        count = len(l)
        print 'Converting ' + str(count) + ' from ' + fname + ' to ' + outtype + ' format'
        for pdf in l:
#             print pdf
            d = {'html' : 'htm', 'tag' : 'tag', 'text' : 'txt', 'xml' : 'xml'}
            ext = '.' + d[outtype]
            outfile = pdf[0:-4] + ext
            print outfile
            outfp = file(outfile, 'wb')
            if outtype == 'text':
                device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
                                       imagewriter=imagewriter)
                device.showpageno = False
            elif outtype == 'xml':
                device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
                                      imagewriter=imagewriter)
                device.showpageno = False
            elif outtype == 'html':
                device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
                                       layoutmode=layoutmode, laparams=laparams,
                                       imagewriter=imagewriter)
                device.showpageno = False
#.........这里部分代码省略.........

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def main(argv):
    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] [-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:t:c:s:')
    except getopt.GetoptError:
        return usage()
    if not args: return usage()
    debug = False
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    outdir = None
    layoutmode = 'normal'
    codec = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == '-d': debug = True
        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': outdir = v
        elif k == '-t': outtype = v
        elif k == '-c': codec = v
        elif k == '-s': scale = float(v)
    
    if debug:
        set_debug_logging()
    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 = io.open(outfile, 'wt', encoding=codec, errors='ignore')
        close_outfp = True
    else:
        outfp = sys.stdout
        close_outfp = False
    if outtype == 'text':
        device = TextConverter(rsrcmgr, outfp, laparams=laparams)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr, outfp, laparams=laparams, outdir=outdir)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, scale=scale, layoutmode=layoutmode,
            laparams=laparams, outdir=outdir, debug=debug)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp)
    else:
        return usage()
    for fname in args:
        fp = io.open(fname, 'rb')
        process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
                    caching=caching, check_extractable=True)
        fp.close()
    device.close()
    if close_outfp:
        outfp.close()

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
def pdf2txt(argv):
    import getopt
    (opts, args) = getopt.getopt(argv[0:], 'dp:m:P:o:CnAVM:L:W:F:Y:O:t:c:s:')
    # debug option
    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    outdir = None
    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': outdir = 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)
    elif outtype == 'xml':
        device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, outdir=outdir)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
                               layoutmode=layoutmode, laparams=laparams, outdir=outdir)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()
    for fname in args:
        fp = file(fname, 'rb')
        process_pdf(rsrcmgr, device, fp, pagenos, maxpages=maxpages, password=password,
                    caching=caching, check_extractable=True)
        fp.close()
    device.close()
    outfp.close()
    return

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import char_margin [as 别名]
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] [-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: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
    outdir = None
    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":
            outdir = 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)
    elif outtype == "xml":
        device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams, outdir=outdir)
    elif outtype == "html":
        device = HTMLConverter(
            rsrcmgr, outfp, codec=codec, scale=scale, layoutmode=layoutmode, laparams=laparams, outdir=outdir
#.........这里部分代码省略.........