def mailmerge( ifile, ofile, fn_updatetmpl, content_list ):
with open( ifile, "rb" ) as f:
pdf = PdfFileReader( f )
out = PdfFileWriter( )
# Get and update template page
pg = pdf.getPage( 0 )
if fn_updatetmpl:
fn_updatetmpl( pg )
# Use one copy of template contents and page resources dictionary
tmpl = out._addObject( pg.getContents() )
res = out._addObject( pg['/Resources'] )
# Generate page for each content element
for cdata in content_list:
if isinstance( cdata, StreamObject ):
c = cdata
else:
d = { '/Length' : len(cdata), '__streamdata__' : cdata }
c = StreamObject.initializeFromDictionary( d )
p = DictionaryObject( pg.items() )
p[NameObject('/Contents')] = ArrayObject( [tmpl,c] )
p[NameObject('/Resources')] = res
out.addPage( p )
# Write complete output file
with open( ofile, "wb" ) as g:
out.write( g )
def add_outlines(toc, filename, output):
build_outlines_btree(toc)
pdf_out = PdfFileWriter()
inputFile = open(filename, 'rb')
pdf_in = PdfFileReader(inputFile)
for p in pdf_in.pages:
pdf_out.addPage(p)
toc_num = len(toc)
if (toc_num == 0): # Just copy if toc empty
outputFile = open(output, "wb")
pdf_out.write(outputFile)
inputFile.close()
outputFile.close()
return
idoix = len(pdf_out._objects) + 1
idorefs = [PDF.IndirectObject(x + idoix, 0, pdf_out)
for x in range(toc_num + 1)]
ol = PDF.DictionaryObject()
ol.update({
PDF.NameObject("/Type"): PDF.NameObject("/Outlines"),
PDF.NameObject("/First"): idorefs[1],
PDF.NameObject("/Last"): idorefs[-1],
PDF.NameObject("/Count"): PDF.NumberObject(toc_num)
})
olitems = []
for t in toc:
oli = PDF.DictionaryObject()
oli.update({
PDF.NameObject("/Title"): PDF.TextStringObject(t["title"].decode("utf-8")),
PDF.NameObject("/Dest"): make_dest(pdf_out, t["page"])
})
opt_keys = {"real_parent": "/Parent", "prev": "/Prev",
"next": "/Next", "first": "/First", "last": "/Last"}
for k, v in opt_keys.items():
n = getattr(t["node"], k)()
if n is not None:
oli.update({
PDF.NameObject(v): idorefs[n.index]
})
olitems.append(oli)
pdf_out._addObject(ol)
for i in olitems:
pdf_out._addObject(i)
pdf_out._root_object.update({
PDF.NameObject("/Outlines"): idorefs[0]
})
outputFile = open(output, "wb")
pdf_out.write(outputFile)
inputFile.close()
outputFile.close()
def add_outlines(toc, filename, output):
build_outlines_btree(toc)
pdf_out = PdfFileWriter()
inputFile = open(filename, 'rb')
pdf_in = PdfFileReader(inputFile)
for p in pdf_in.pages:
pdf_out.addPage(p)
toc_num = len(toc)
idoix = len(pdf_out._objects) + 1
idorefs = [PDF.IndirectObject(x + idoix, 0, pdf_out)
for x in range(toc_num + 1)]
ol = PDF.DictionaryObject()
ol.update({
PDF.NameObject("/Type"): PDF.NameObject("/Outlines"),
PDF.NameObject("/First"): idorefs[1],
PDF.NameObject("/Last"): idorefs[-1],
PDF.NameObject("/Count"): PDF.NumberObject(toc_num)
})
olitems = []
for t in toc:
oli = PDF.DictionaryObject()
oli.update({
PDF.NameObject("/Title"): PDF.TextStringObject(t["title"].decode("utf-8")),
PDF.NameObject("/Dest"): make_dest(pdf_out, t["page"])
})
opt_keys = {"real_parent": "/Parent", "prev": "/Prev",
"next": "/Next", "first": "/First", "last": "/Last"}
for k, v in opt_keys.items():
n = getattr(t["node"], k)()
if n is not None:
oli.update({
PDF.NameObject(v): idorefs[n.index]
})
olitems.append(oli)
pdf_out._addObject(ol)
for i in olitems:
pdf_out._addObject(i)
pdf_out._root_object.update({
PDF.NameObject("/Outlines"): idorefs[0]
})
outputFile = open(output, "wb")
pdf_out.write(outputFile)
inputFile.close()
outputFile.close()
class Document():
def __init__(self, source):
if 'redactor/' not in source:
source = 'redactor/' + source
try:
im = Image.open(source)
except Exception as e:
raise Exception('Failed to open image source ' + source)
source = source.replace('/in/', '/temp/')
self.page_size = 1240, int(1240.0 * im.size[1] / im.size[0])
im = im.resize(self.page_size, Image.ANTIALIAS)
im.save(source)
document = BytesIO()
canvas = Canvas(document, pagesize=(self.page_size))
canvas.setFillColorRGB(1, 1, 1)
canvas.drawImage(source, 0, 0, mask=(1, 1, 1, 1, 1, 1))
canvas.save()
self.pdf = PdfFileWriter()
self.pdf.addPage(
PdfFileReader(BytesIO(document.getvalue())).getPage(0))
def add_line(self, x0, y0, x1, y1, color):
document = BytesIO()
canvas = Canvas(document, pagesize=self.page_size)
canvas.setLineWidth(25)
canvas.setStrokeColorRGB(*color)
canvas.line(x0, y0, x1, y1)
canvas.save()
self.pdf.getPage(0).mergePage(
PdfFileReader(BytesIO(document.getvalue())).getPage(0))
def add_rect(self, x0, y0, x1, y1, color=[0, 0, 0, 0]):
document = BytesIO()
canvas = Canvas(document, pagesize=self.page_size)
canvas.setFillColorRGB(*color)
canvas.rect(x0, y0, x1 - x0, y1 - y0, 0, 1)
canvas.save()
self.pdf.getPage(0).mergePage(
PdfFileReader(BytesIO(document.getvalue())).getPage(0))
def add_note(self, src, x0, y0, comment='', author=''):
self._add_image(src, x0, y0)
self._add_highlight(x0, y0, 71, 39, comment, author)
def export(self, fn, objects):
funcs = {
'LINE': self.add_line,
'RECT': self.add_rect,
'COMM': self.add_note,
}
for obj in objects['objects']:
if funcs.get(obj['mode'], None):
funcs[obj['mode']](**obj['attributes'])
self.pdf.write(open(fn, 'wb'))
def _add_image(self, source, x, y):
if 'redactor/' not in source:
source = 'redactor/' + source
document = BytesIO()
canvas = Canvas(document, pagesize=self.page_size)
canvas.setFillColorRGB(1, 1, 1)
canvas.drawImage(source, x, y, mask='auto')
canvas.save()
self.pdf.getPage(0).mergePage(
PdfFileReader(BytesIO(document.getvalue())).getPage(0))
def _create_highlight(self,
x0,
y0,
width,
height,
comment,
author='',
color=[0, 0, 0, 0]):
self.add_rect(x0, y0, width, height)
highlight = DictionaryObject()
highlight.update({
NameObject("/F"):
NumberObject(4),
NameObject("/Type"):
NameObject("/Annot"),
NameObject("/Subtype"):
NameObject("/Highlight"),
NameObject("/T"):
TextStringObject(author),
NameObject("/Contents"):
TextStringObject(comment),
NameObject("/C"):
ArrayObject([FloatObject(c) for c in color]),
NameObject("/Rect"):
ArrayObject([
FloatObject(x0),
FloatObject(y0),
FloatObject(x0 + width),
FloatObject(y0 + width)
]),
NameObject("/QuadPoints"):
ArrayObject([
FloatObject(x0),
FloatObject(y0 + width),
FloatObject(x0 + width),
FloatObject(y0 + width),
FloatObject(x0),
FloatObject(y0),
FloatObject(x0 + width),
FloatObject(y0)
]),
})
return highlight
def _add_highlight(self,
x0,
y0,
width,
height,
comment,
author='',
color=[0, 0, 0, 0]):
highlight = self._create_highlight(x0, y0, width, height, comment,
author, color)
highlight_ref = self.pdf._addObject(highlight)
if "/Annots" in self.pdf.getPage(0):
self.pdf.getPage(0)[NameObject("/Annots")].append(highlight_ref)
else:
self.pdf.getPage(0)[NameObject("/Annots")] = ArrayObject(
[highlight_ref])
def anotate_pdf(file_path, sht, query_dict):
# preparing the output file name
path = pathlib.Path(file_path).parent
extension = pathlib.Path(file_path).suffix
name = pathlib.Path(file_path).name[:-len(extension)]
result_file = str(path) + '\\' + name + '_highlighted' + extension
#=========================================================
# create a parser object associated with the file object
parser = PDFParser(open(file_path, 'rb'))
# create a PDFDocument object that stores the document structure
doc = PDFDocument(parser)
# Layout Analysis
# Set parameters for analysis.
laparams = LAParams()
# Create a PDF page aggregator object.
rsrcmgr = PDFResourceManager()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
# create pdf layout - this is list with layout of every page
layout = []
for page in PDFPage.create_pages(doc):
interpreter.process_page(page)
# receive the LTPage object for the page.
layout.append(device.get_result())
# add tooltip info not sure how to use this option in the most usefull way
m_meta = {"author": "AK", "contents": "HL text1"}
outputStream = open(result_file, "wb")
pdfInput = PdfFileReader(open(file_path, 'rb'), strict=True)
pdfOutput = PdfFileWriter()
npage = pdfInput.numPages
for pgn in range(0, npage):
for query in query_dict:
all_coor = []
for page in layout:
result = get_page_coordinates(page, query)
all_coor.append(result)
page_hl = pdfInput.getPage(pgn)
for item in all_coor[pgn]:
highlight = create_highlight(item[0],
item[1],
item[2],
item[3],
m_meta,
color=query_dict[query])
highlight_ref = pdfOutput._addObject(highlight)
if "/Annots" in page_hl:
page_hl[NameObject("/Annots")].append(highlight_ref)
else:
page_hl[NameObject("/Annots")] = ArrayObject(
[highlight_ref])
pdfOutput.addPage(page_hl)
# save HL to new file
pdfOutput.write(outputStream)
outputStream.close()
sht.range('B2').value = f'File {name+extension} completed'
