Python LAParams.boxes_flow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 boxes_flow [as 别名]
def GetScript(filename):
    global scriptName
    ResetGlobals()
    scriptName = filename
    password = ""
    # Open a PDF file.
    fp = open(filename, 'rb')
    # Create a PDF parser object associated with the file object.
    parser = PDFParser(fp)
    # Create a PDF document object that stores the document structure.
    # Supply the password for initialization.
    document = PDFDocument(parser, password)
    # Check if the document allows text extraction. If not, abort.
    if not document.is_extractable:
        print "---Not translatable---"
        return
        #raise PDFTextExtractionNotAllowed
    # Create a PDF resource manager object that stores shared resources.
    rsrcmgr = PDFResourceManager()
    # Create a PDF device object.
    device = PDFDevice(rsrcmgr)
    # Create a PDF interpreter object.
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    # Process each page contained in the document.
    for page in PDFPage.create_pages(document):
        interpreter.process_page(page)
    
    # Set parameters for analysis.
    laparams = LAParams()
    laparams.boxes_flow = 2
    # Create a PDF page aggregator object.
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    for pgnum,page in enumerate(PDFPage.create_pages(document)):
        if pgnum == 0:
            continue
        interpreter.process_page(page)
        # receive the LTPage object for the page.
        layout = device.get_result()
        text = []
        for page in layout:
            try:
                if page.get_text().strip():
                    text.append(TextBlock(page.x0,page.y1,page.get_text().strip()))
            except:
                temp=5  
            print ".",
        text.sort(key = lambda row:(-row.y))
        # Parse all of the "line" objects in each page
        for line in text:
            ParseLine(line.text, line.x)

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [as 别名]
def from_pdf(pdfFile):
    try:
        pagenos = set()
        strfp = StringIO()
        codec = 'utf-8'
        
        laparams = LAParams()
        #laparams.char_margin = 10
        laparams.line_margin = 20
        #laparams.word_margin = 10
        laparams.boxes_flow = -1
        
        rsrcmgr = PDFResourceManager()
        device = TextConverter(rsrcmgr, strfp, codec=codec, laparams=laparams)
        
        fp = file(pdfFile, 'rb')
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        for page in PDFPage.get_pages(fp, pagenos, check_extractable=True):
            interpreter.process_page(page)
    except Exception, e:
        print e
        traceback.print_exc()
        pass

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [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] [-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

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [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.........

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [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 boxes_flow [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 boxes_flow [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 boxes_flow [as 别名]
def convert_pdf_To_Txt(path,opts={}):
    """
    this ALGO form pdfinterp modul  documentation


    """

        # debug option
    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = 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': imagewriter = ImageWriter(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
    retstr = StringIO()
    if outtype == 'text':
        device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams,
                               imagewriter=imagewriter)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    for page in PDFPage.get_pages(fp, pagenos,
                                      maxpages=maxpages, password=password,
                                      caching=caching, check_extractable=True):
        interpreter.process_page(page)
    #print retstr.getvalue()
    txt2Pdf=retstr.getvalue()
    #print type(txt2Pdf)

    #fp.close()
    #device.close()
    #outfp.close()
    return txt2Pdf

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [as 别名]
def main(fname, k, v):

    # debug option
    debug = 0
    # input option
    password = ''
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = None
    rotation = 0
    stripcontrol = False
    layoutmode = 'normal'
    codec = 'utf-8'
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()

    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 == '-S':
        stripcontrol = True
    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
    PDFPageInterpreter.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,
                              stripcontrol=stripcontrol)
    elif outtype == 'html':
        device = HTMLConverter(rsrcmgr, outfp, codec=codec, scale=scale,
                               layoutmode=layoutmode, laparams=laparams,
                               imagewriter=imagewriter, debug=debug)
    elif outtype == 'tag':
        device = TagExtractor(rsrcmgr, outfp, codec=codec)
    else:
        return usage()
 
    fp = file(fname, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
#.........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 boxes_flow [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] [-R rotation] [-S]"
            " [-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:St:c:s:")
    except getopt.GetoptError:
        return usage()
    if not args:
        return usage()
    # input option
    password = b""
    pagenos = set()
    maxpages = 0
    # output option
    outfile = None
    outtype = None
    imagewriter = None
    rotation = 0
    stripcontrol = False
    layoutmode = "normal"
    codec = "utf-8"
    pageno = 1
    scale = 1
    caching = True
    showpageno = True
    laparams = LAParams()
    for (k, v) in opts:
        if k == "-d":
            logging.getLogger().setLevel(logging.DEBUG)
        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 == "-S":
            stripcontrol = True
        elif k == "-t":
            outtype = v
        elif k == "-c":
            codec = v
        elif k == "-s":
            scale = float(v)
    #
    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 = open(outfile, "wb")
    else:
        outfp = sys.stdout
        if outfp.encoding is not None:
            codec = None
    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, stripcontrol=stripcontrol
        )
#.........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 boxes_flow [as 别名]
def readPDF2HTML(pdfFile, opts={}):
    # open a PDF file
    fp = StringIO(pdfFile.read())
    retstr = StringIO()
    # create a PDF parser object associated with the file object
    parser = PDFParser(fp)
    # create a PDF document allows text extraction
    document = PDFDocument(parser) # password if needed
    # check if document allows text extraction without password
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    # create a PDF resource manager object that sotres shared resources
    rsrcmgr = PDFResourceManager()
    # create a PDF device object
    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 == '-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)
    codec = 'utf-8'
    device = HTMLConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    # create a PDF interpreter object
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    pagenos = set()
    # process each page contained in the document
    for page in PDFPage.get_pages(fp, pagenos):
        interpreter.process_page(page)
    # close streams and return text content
    fp.close()
    content = retstr.getvalue()
    device.close()
    retstr.close()
    return content

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [as 别名]

#.........这里部分代码省略.........

    parser.add_argument('-n', '--no-layout', dest='layout', action='store_false',
                       default=True,
                       help='Suppress layout analysis.')

    parser.add_argument('--show-pageno', dest='show_pageno', action='store_true',
                       default=False,
                       help='Show page numbers.')


    parser.add_argument('-A', '--analyze-all', dest='all_texts', action='store_true',
                       default=False,
                       help='Forces to perform layout analysis for all the text strings, including text contained in figures.')

    parser.add_argument('-V', '--detect-vertical', dest='detect_vertical', action='store_true',
                       default=False,
                       help='Allows vertical writing detection.')

    parser.add_argument('-M', dest='char_margin', action='store',
                       type=float,
                       default=2.0,
                       help='Two text chunks whose distance is closer than the char_margin (shown as M) is considered continuous and get grouped into one.')

    parser.add_argument('-L', dest='line_margin', action='store',
                       type=float,
                       default=0.5,
                       help='Two lines whose distance is closer than the line_margin (L) is grouped as a text box, which is a rectangular area that contains a "cluster" of text portions.')

    parser.add_argument('-W', dest='word_margin', action='store',
                       type=float,
                       default=0.1,
                       help='It may be required to insert blank characters (spaces) as necessary if the distance between two words is greater than the word_margin (W), as a blank between words might not be represented as a space, but indicated by the positioning of each word.')

    parser.add_argument('-F', dest='boxes_flow', action='store',
                       type=float,
                       default=0.5,
                       help='Specifies how much a horizontal and vertical position of a text matters when determining a text order. The value should be within the range of -1.0 (only horizontal position matters) to +1.0 (only vertical position matters).')

    parser.add_argument('-Y', '--layout-mode', dest='layoutmode', action='store',
                       type=str,
                       default='normal',
                       choices = ['exact', 'normal', 'loose'],
                       help='Specifies how the page layout should be preserved. (Currently only applies to HTML format.) One of: exact, normal, loose.')

    parser.add_argument('-O', '--image-writer', dest='imagewriter', action='store',
                       type=str,
                       default=None,
                       help='imagewriter')

    parser.add_argument('-R', '--rotation', dest='rotation', action='store',
                       type=int,
                       default=0,
                       help='rotation')

    parser.add_argument('-S', '--strip-control', dest='stripcontrol', action='store_true',
                       default=False,
                       help='stripcontrol')

    parser.add_argument('-s', dest='scale', action='store',
                       type=float,
                       default=1,
                       help='Specifies the output scale. Can be used in HTML format only.')

    parser.add_argument('--draw-lines', dest='draw_lines', action='store_true',
                       help="Draw crude page representation, coloured TextLines (= short pieces of text). Valid only for the `shape' output.")

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import boxes_flow [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 boxes_flow [as 别名]
def pdfminerr(argv):
    global pdfminerr, install
    import getopt
  
    def usage():
        print ("usage: just put the path to the pdf file in pdf.txt, and make sure you create a seprate folder and put nothing there except for this repository.")
        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
    imagewriter = 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': imagewriter = ImageWriter(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')
        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 boxes_flow [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