Python pdfrw.PdfReader方法代碼示例

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def __init__(self, file_or_reader, scale=None, compress=True):
        """Draw annotations directly on PDFs. Annotations are always drawn on
        as if you're drawing them in a viewer, i.e. they take into account page
        rotation and weird, translated coordinate spaces.

        :param str|PdfReader file_or_reader: filename of PDF or pdfrw.PdfReader
        :param number|tuple|None scale: number by which to scale coordinates
            to get to default user space. Use this if, for example, your points
            in the coordinate space of the PDF viewed at a dpi. In this case,
            scale would be 72/dpi. Can also specify a 2-tuple of x and y scale.
        :param bool compress: whether to output flate-compressed PDFs
        """
        if isinstance(file_or_reader, str):
            file_or_reader = PdfReader(file_or_reader)
        self._pdf = PDF(file_or_reader)
        self._scale = self._expand_scale(scale)
        self._dimensions = {}
        self._compress = compress 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def get_issuer_address(pdf_file):
    pdf = PdfReader(pdf_file)
    try:
        version = pdf.Info.version
        if(version == '1'):
            issuer = json.loads( pdf.Info.issuer.decode() )
            return issuer['identity']['address']
        else:
            issuer_address = pdf.Info.issuer_address
            if issuer_address:
                return issuer_address.decode()
            else:
                metadata_object = json.loads( pdf.Info.metadata_object.decode() )
                return metadata_object['issuer_address']
    except AttributeError:
        raise ValueError("Could not find issuer address in pdf") 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def __init__(self, filename_or_object, width=None, height=None, kind='direct'):
        if hasattr(filename_or_object, 'read'):
            filename_or_object.seek(0)
        page = PdfReader(filename_or_object, decompress=False).pages[0]
        self.xobj = pagexobj(page)
        self.dynamic = 0
        # Actual image size
        x1, y1, x2, y2 = self.xobj.BBox
        imgw, imgh = x2 - x1, y2 - y1
        self._imgw, self._imgh = imgw, imgh
        if kind in ['direct', 'absolute']:
            self.drawWidth = width or imgw
            self.drawHeight = height or imgh
        elif kind in ['percentage', '%']:
            self.drawWidth = imgw * width * 0.01
            self.drawHeight = imgh * height * 0.01
        elif kind in ['bound', 'proportional']:
            w, h = width or imgw, height or imgh
            factor = min(float(w) / imgw, float(h) / imgh)
            self.drawWidth = imgw * factor
            self.drawHeight = imgh * factor
        elif kind in ['dynamic']:
            self.dynamic = 1 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def set_pagelabel(self,count,style="arabic"):
        if self.isPDF:
            from pdfrw import PdfReader, PdfWriter
            from pagelabels import PageLabels, PageLabelScheme
            reader = PdfReader(self.filename)
            labels = PageLabels.from_pdf(reader)
            newlabels = PageLabels()
            for label in labels:
                if label.startpage != self.page:
                    newlabels.append(label)

            newlabel = PageLabelScheme(startpage=self.page, 
                                       style=style,
                                       prefix="",
                                       firstpagenum=count) 
            newlabels.append(newlabel) 
            newlabels.write(reader)

            writer = PdfWriter()
            writer.trailer = reader
            logging.debug("writing new pagelabels...")
            writer.write(self.filename)

    # unused; using pdfrw instead 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def merge(overlay, basename):
    '''
    Merge the overlay with the original form, and return the result.
    '''

    input_pdf_path = os.path.join('templates', basename)

    template_pdf = pdfrw.PdfReader(input_pdf_path)
    overlay_pdf = pdfrw.PdfReader(overlay)
    for page, data in zip(template_pdf.pages, overlay_pdf.pages):
        overlay = pdfrw.PageMerge().add(data)[0]
        pdfrw.PageMerge(page).add(overlay).render()
    form = io.BytesIO()
    pdfrw.PdfWriter().write(form, template_pdf)
    form.seek(0)
    return form 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def test_init_with_reader(self):
        a = PdfAnnotator(PdfReader(files.SIMPLE))
        assert a._pdf is not None 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def test_write_with_compress_off_smoke_test(self):
        a = PdfAnnotator(PdfReader(files.SIMPLE), compress=False)
        with write_to_temp(a) as t:
            assert load_annotations_from_pdf(t) is None 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def load_annotations_from_pdf(filename, page=0):
    reader = PdfReader(filename)
    return reader.pages[page].Annots 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def _check_num_annotations(self, output_file):
        f = pdfrw.PdfReader(output_file)
        assert len(f.pages[0].Annots) == self.EXPECTED_ANNOTATIONS 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def get_issuer_verification(pdf_file):
    pdf = PdfReader(pdf_file)
    try:
        version = pdf.Info.version
        if(version == '1'):
            issuer = json.loads( pdf.Info.issuer.decode() )
            return issuer['identity']['verification']
    except AttributeError:
        raise ValueError("Could not find issuer address verification in pdf") 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def get_and_remove_chainpoint_proof(pdf_file):
    pdf = PdfReader(pdf_file)
    try:
        proof = json.loads( pdf.Info.chainpoint_proof.decode() )
    except AttributeError:
        return None
    metadata = PdfDict(chainpoint_proof='')
    pdf.Info.update(metadata)
    PdfWriter().write(pdf_file, pdf)
    return proof 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def insert_proof_to_certificates(conf, cp, txid, cert_files, interactive=False):
    if interactive:
        print('')
    for ind, val in enumerate(cert_files):
        proof = json.dumps( cp.get_receipt(ind, txid) )
        metadata = PdfDict(chainpoint_proof=proof)
        pdf = PdfReader(val)
        pdf.Info.update(metadata)
        PdfWriter().write(val, pdf)

        if interactive:
            # print progress
            print('.', end="", flush=True) 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def insert_proof_to_certificates(conf, cp, txid, cert_files, interactive=False):
    if interactive:
        print('')
    for ind, val in enumerate(cert_files):
        proof = json.dumps( cp.get_receipt(ind, txid) )
        metadata = PdfDict(chainpoint_proof=proof)
        pdf = PdfReader(val)
        pdf.Info.update(metadata)
        PdfWriter().write(val, pdf)
        if interactive:
            # print progress
            print('.', end="", flush=True) 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def parse_pagelabels(self):
        if self.isPDF:
            from pdfrw import PdfReader
            from pagelabels import PageLabels, PageLabelScheme
            try: 
                reader = PdfReader(self.filename)
                labels = PageLabels.from_pdf(reader)
                labels = sorted(labels, key=attrgetter('startpage'))
            except:
                labels = []
        else:
            labels = []
        return labels 

# 需要導入模塊: import pdfrw [as 別名]
# 或者: from pdfrw import PdfReader [as 別名]
def form_xo_reader(imgdata):
    page, = PdfReader(imgdata).pages
    return pagexobj(page)