Created
November 17, 2016 22:50
-
-
Save agentcooper/4c55133f5d95866acdee5017cd318558 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from PyPDF2 import PdfFileWriter, PdfFileReader | |
from PyPDF2Highlight import createHighlight, addHighlightToPage | |
pdfInput = PdfFileReader(open("input.pdf", "rb")) | |
pdfOutput = PdfFileWriter() | |
page1 = pdfInput.getPage(0) | |
highlight = createHighlight(100, 400, 400, 500, { | |
"author": "", | |
"contents": "Bla-bla-bla" | |
}) | |
addHighlightToPage(highlight, page1, pdfOutput) | |
pdfOutput.addPage(page1) | |
outputStream = open("output.pdf", "wb") | |
pdfOutput.write(outputStream) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from PyPDF2.generic import ( | |
DictionaryObject, | |
NumberObject, | |
FloatObject, | |
NameObject, | |
TextStringObject, | |
ArrayObject | |
) | |
# x1, y1 starts in bottom left corner | |
def createHighlight(x1, y1, x2, y2, meta, color = [1, 0, 0]): | |
newHighlight = DictionaryObject() | |
newHighlight.update({ | |
NameObject("/F"): NumberObject(4), | |
NameObject("/Type"): NameObject("/Annot"), | |
NameObject("/Subtype"): NameObject("/Highlight"), | |
NameObject("/T"): TextStringObject(meta["author"]), | |
NameObject("/Contents"): TextStringObject(meta["contents"]), | |
NameObject("/C"): ArrayObject([FloatObject(c) for c in color]), | |
NameObject("/Rect"): ArrayObject([ | |
FloatObject(x1), | |
FloatObject(y1), | |
FloatObject(x2), | |
FloatObject(y2) | |
]), | |
NameObject("/QuadPoints"): ArrayObject([ | |
FloatObject(x1), | |
FloatObject(y2), | |
FloatObject(x2), | |
FloatObject(y2), | |
FloatObject(x1), | |
FloatObject(y1), | |
FloatObject(x2), | |
FloatObject(y1) | |
]), | |
}) | |
return newHighlight | |
def addHighlightToPage(highlight, page, output): | |
highlight_ref = output._addObject(highlight); | |
if "/Annots" in page: | |
page[NameObject("/Annots")].append(highlight_ref) | |
else: | |
page[NameObject("/Annots")] = ArrayObject([highlight_ref]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
@rbehal You should no longer use PyPDF2 as it's deprecated. Use pypdf. It supports highlights out of the box: https://pypdf.readthedocs.io/en/latest/user/adding-pdf-annotations.html#highlighting