Python PDFDocument.get_pages方法代码示例

# 需要导入模块: from pdfminer.pdfdocument import PDFDocument [as 别名]
# 或者: from pdfminer.pdfdocument.PDFDocument import get_pages [as 别名]
    def __init__(self, *args, **kwargs):
        super(AccountRIB, self).__init__(*args, **kwargs)

        self.parsed_text = b''

        try:
            try:
                from pdfminer.pdfdocument import PDFDocument
                from pdfminer.pdfpage import PDFPage
                newapi = True
            except ImportError:
                from pdfminer.pdfparser import PDFDocument
                newapi = False
            from pdfminer.pdfparser import PDFParser, PDFSyntaxError
            from pdfminer.converter import TextConverter
            from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
        except ImportError:
            self.logger.warning('Please install python-pdfminer to get IBANs')
        else:
            parser = PDFParser(BytesIO(self.doc))
            try:
                if newapi:
                    doc = PDFDocument(parser)
                else:
                    doc = PDFDocument()
                    parser.set_document(doc)
                    doc.set_parser(parser)
            except PDFSyntaxError:
                return

            rsrcmgr = PDFResourceManager()
            out = BytesIO()
            device = TextConverter(rsrcmgr, out)
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            if newapi:
                pages = PDFPage.create_pages(doc)
            else:
                doc.initialize()
                pages = doc.get_pages()
            for page in pages:
                interpreter.process_page(page)

            self.parsed_text = out.getvalue()

# 需要导入模块: from pdfminer.pdfdocument import PDFDocument [as 别名]
# 或者: from pdfminer.pdfdocument.PDFDocument import get_pages [as 别名]
def extract_text(data):
    try:
        try:
            from pdfminer.pdfdocument import PDFDocument
            from pdfminer.pdfpage import PDFPage
            newapi = True
        except ImportError:
            from pdfminer.pdfparser import PDFDocument
            newapi = False
        from pdfminer.pdfparser import PDFParser, PDFSyntaxError
        from pdfminer.converter import TextConverter
        from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
    except ImportError:
        raise ImportError('Please install python-pdfminer to parse PDF')
    else:
        parser = PDFParser(BytesIO(data))
        try:
            if newapi:
                doc = PDFDocument(parser)
            else:
                doc = PDFDocument()
                parser.set_document(doc)
                doc.set_parser(parser)
        except PDFSyntaxError:
            return

        rsrcmgr = PDFResourceManager()
        out = BytesIO()
        device = TextConverter(rsrcmgr, out)
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        if newapi:
            pages = PDFPage.create_pages(doc)
        else:
            doc.initialize()
            pages = doc.get_pages()
        for page in pages:
            interpreter.process_page(page)

        return out.getvalue()

# 需要导入模块: from pdfminer.pdfdocument import PDFDocument [as 别名]
# 或者: from pdfminer.pdfdocument.PDFDocument import get_pages [as 别名]
#coding=utf-8
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.pdfdevice import PDFDevice
import LAParams
import PDFPageAggregator
fp = open('/home/zzq/learngit/pdf_document/php.pdf')#打开文件
parser=PDFParser(fp)#解析器
doc =PDFDocument()#文档
doc.set_parser(parser)#设置解析器
doc.initialize("")#初始化
resource=PDFResourceManager()#资源管理器
laparams=LAParams()#参数分析期
#聚合器
device=PDFPageAggregator()
#页面解析器
interpreter=PDFPageInterpreter(resource,device)

for page in doc.get_pages():
	interpreter.process_page(page)
	layout=device.get_result()
	for out in layout:
		print out.get_text()

# 需要导入模块: from pdfminer.pdfdocument import PDFDocument [as 别名]
# 或者: from pdfminer.pdfdocument.PDFDocument import get_pages [as 别名]
def pdf2csv(fp):
    # Create a PDF parser object associated with the file object.
    parser = PDFParser(fp)
    # Create a PDF document object that stores the document structure.
    doc = PDFDocument(parser)
    print doc
    # Connect the parser and document objects.
    # parser.set_document(doc)
    # doc.set_parser(parser)
    # Supply the password for initialization.
    # (If no password is set, give an empty string.)
    doc.initialize('')
    # Check if the document allows text extraction. If not, abort.
    # if not doc.is_extractable:
    #     raise PDFTextExtractionNotAllowed
    # Create a PDF resource manager object that stores shared resources.
    rsrcmgr = PDFResourceManager()
    # Set parameters for analysis.
    laparams = LAParams()
    # Create a PDF page aggregator object.
    device = PDFPageAggregator(rsrcmgr, laparams=laparams)
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    layout = device.get_result()
    
  
    for pageno, page in enumerate(doc.get_pages()):
        interpreter.process_page(page)
        # receive the LTPage object for the page.
        layout = device.get_result()
        #import code; code.interact(local=locals());
        hlines=[]
        vlines=[]
        for i in layout:
            if not type(i) in (LTRect, LTLine): continue
            hlines.append(int(i.x0))
            hlines.append(int(i.x1))
            vlines.append(int(layout.height - i.y0))
            vlines.append(int(layout.height - i.y1))
        hlines=filterclose(sorted(set(hlines)))
        vlines=filterclose(sorted(set(vlines)))
        print hlines
        print vlines
        print (layout.width, layout.height)
        i=0
        im = Image.new('1', (int(layout.width), int(layout.height)))
        draw = ImageDraw.Draw(im)
        while(i<len(vlines)-1):
            if not vlines[i+1]-vlines[i]>5:
                i=i+1
                continue
            j=0
            while(j<len(hlines)-1):
                if not hlines[j+1]-hlines[j]>5:
                    j=j+1
                    continue
                draw.rectangle([(int(hlines[j]),int(vlines[i])),(int(hlines[j+1]),int(vlines[i+1]))], outline=1)
                j=j+1
            i=i+1
        del draw
        fp=open("out%s.png" % pageno,'wb')
        im.save(fp,"PNG")
        fp.close()

# 需要导入模块: from pdfminer.pdfdocument import PDFDocument [as 别名]
# 或者: from pdfminer.pdfdocument.PDFDocument import get_pages [as 别名]
def get_pdf_rows(data, miner_layout=True):
    """
    Takes PDF file content as string and yield table row data for each page.

    For each page in the PDF, the function yields a list of rows.
    Each row is a list of cells. Each cell is a list of strings present in the cell.
    Note that the rows may belong to different tables.

    There are no logic tables in PDF format, so this parses PDF drawing instructions
    and tries to find rectangles and arrange them in rows, then arrange text in
    the rectangles.

    External dependencies:
    PDFMiner (http://www.unixuser.org/~euske/python/pdfminer/index.html).
    """

    try:
        from pdfminer.pdfparser import PDFParser, PDFSyntaxError
    except ImportError:
        raise ImportError('Please install python-pdfminer')

    try:
        from pdfminer.pdfdocument import PDFDocument
        from pdfminer.pdfpage import PDFPage
        newapi = True
    except ImportError:
        from pdfminer.pdfparser import PDFDocument
        newapi = False
    from pdfminer.converter import PDFPageAggregator
    from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
    from pdfminer.layout import LAParams, LTRect, LTTextBox, LTTextLine, LTLine, LTChar, LTCurve

    parser = PDFParser(BytesIO(data))
    try:
        if newapi:
            doc = PDFDocument(parser)
        else:
            doc = PDFDocument()
            parser.set_document(doc)
            doc.set_parser(parser)
    except PDFSyntaxError:
        return

    rsrcmgr = PDFResourceManager()
    if miner_layout:
        device = PDFPageAggregator(rsrcmgr, laparams=LAParams())
    else:
        device = PDFPageAggregator(rsrcmgr)

    interpreter = PDFPageInterpreter(rsrcmgr, device)
    if newapi:
        pages = PDFPage.get_pages(BytesIO(data), check_extractable=True)
    else:
        doc.initialize()
        pages = doc.get_pages()

    if LOGGER.isEnabledFor(DEBUGFILES):
        import tempfile
        import PIL.Image as Image
        import PIL.ImageDraw as ImageDraw
        import random

        path = tempfile.mkdtemp(prefix='pdf')

    for npage, page in enumerate(pages):
        LOGGER.debug('processing page %s', npage)
        interpreter.process_page(page)
        page_layout = device.get_result()

        texts = sum([list(lttext_to_multilines(obj, page_layout)) for obj in page_layout._objs if isinstance(obj, (LTTextBox, LTTextLine, LTChar))], [])
        LOGGER.debug('found %d text objects', len(texts))
        if LOGGER.isEnabledFor(DEBUGFILES):
            img = Image.new('RGB', (int(page.mediabox[2]), int(page.mediabox[3])), (255, 255, 255))
            draw = ImageDraw.Draw(img)
            for t in texts:
                color = (random.randint(127, 255), random.randint(127, 255), random.randint(127, 255))
                draw.rectangle((t.x0, t.y0, t.x1, t.y1), outline=color)
                draw.text((t.x0, t.y0), t.text.encode('utf-8'), color)
            fpath = '%s/1text-%03d.png' % (path, npage)
            img.save(fpath)
            LOGGER.log(DEBUGFILES, 'saved %r', fpath)

        if not miner_layout:
            texts.sort(key=lambda t: (t.y0, t.x0))

        # TODO filter ltcurves that are not lines?
        # TODO convert rects to 4 lines?
        lines = [lt_to_coords(obj, page_layout) for obj in page_layout._objs if isinstance(obj, (LTRect, LTLine, LTCurve))]
        LOGGER.debug('found %d lines', len(lines))
        if LOGGER.isEnabledFor(DEBUGFILES):
            img = Image.new('RGB', (int(page.mediabox[2]), int(page.mediabox[3])), (255, 255, 255))
            draw = ImageDraw.Draw(img)
            for l in lines:
                color = (random.randint(127, 255), random.randint(127, 255), random.randint(127, 255))
                draw.rectangle((l.x0, l.y0, l.x1, l.y1), outline=color)
            fpath = '%s/2lines-%03d.png' % (path, npage)
            img.save(fpath)
            LOGGER.log(DEBUGFILES, 'saved %r', fpath)

        lines = list(uniq_lines(lines))
#.........这里部分代码省略.........