Python LAParams.line_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 line_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 line_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 line_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 line_margin [as 别名]
def extractrefs(infile, outfile):
    pagenos = set()
    caching = True
    infp = open(infile, 'rb')
    outfp = open(outfile, 'w')

    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    laparams.line_margin = 1.4
    device = RefsExtractor(rsrcmgr, outfp, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    for page in PDFPage.get_pages(infp, pagenos,
                                  caching=caching,
                                  check_extractable=True):
        interpreter.process_page(page)

    infp.close()
    outfp.close()

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import line_margin [as 别名]
def output_pdf_to_table(path):

    fp = open(path, "rb")
    rsrcmgr = PDFResourceManager()
    laparams = LAParams()
    laparams.line_margin = line_margin_threshold
    codec = 'utf-8'
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)

    password=""
    maxpages=pages_to_view
    caching=True
    pagenos=set()

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

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import line_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 line_margin [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 line_margin [as 别名]
#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 line_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 line_margin [as 别名]
    ##ATTEMPT 1
    # Create a PDF parser object associated with the file object.
    #parser = PDFParser(open_file)
    # Create a PDF document object that stores the document structure.
    #doc = PDFDocument(parser)
    # Connect the parser and document objects.
    #print parser.nextline()
    #print parser.nextline()
    #print parser.nextline()


    ##ATTEMPT 2
    #Code from pdf2txt.py
    laparams = LAParams()
    laparams.char_margin = 2.0
    laparams.line_margin=0.5
    laparams.word_margin=0.1
    laparams.all_texts=False

    rsrcmgr = PDFResourceManager()
    device = TextConverter(rsrcmgr, fp_out, codec='utf-8', laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    pdf_pages = PDFPage.get_pages(fp_in, set())
    pagenum = 0
    pagelim = 3
    for page in pdf_pages:
        pagenum += 1
        if pagenum > pagelim:
            continue
        print "Transcribing page " + str(pagenum) + " from PDF to text"
        interpreter.process_page(page)

# 需要导入模块: from pdfminer.layout import LAParams [as 别名]
# 或者: from pdfminer.layout.LAParams import line_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 line_margin [as 别名]
        if m is None:
            continue
        if gname is not None:
            logging.warn('skip %s: 2 groups in one doc: %s [%s] and %s [%s]' % (pdf_file, gname, gtype, m.groups()[2], m.groups()[0]))
            return
        gname = m.groups()[2].strip()
        gtype = m.groups()[0].strip()
        if u'五十音順' in gname:
            # HACK: some docs are really borked..
            return
        logging.info(u'%s is a doc for %s' % (pdf_file, gname))
    return gname


LAPARAMS = LAParams()
LAPARAMS.line_margin = 10.0


def extract_pdf_text(fname):
    rsrcmgr = PDFResourceManager(caching=True)
    codec = 'utf-8'
    outfp = StringIO()
    device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=LAPARAMS,
                           imagewriter=None)
    fp = file(fname, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    for page in PDFPage.get_pages(fp, set(), maxpages=1,
                                  caching=True, check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()

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