Last active
June 8, 2022 07:42
-
-
Save kvgc/704c9af2ab91be19905fb5b31dad551a to your computer and use it in GitHub Desktop.
This file contains 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
### pytho exportAnnotations.py test.pdf | |
### Outputs notes and highlights in the pdf as html | |
### Requires: markdown2, PyPDF2, pdfannots | |
from PyPDF2 import PdfFileReader | |
import subprocess | |
from pathlib import Path | |
import markdown2 | |
import sys | |
# filename = "downloads_firefox/2204.09332.pdf" | |
filename = str(sys.argv[1]) | |
reader = PdfFileReader(filename) | |
##print(reader.getPage(0).mediaBox) | |
finalNote = '<h2> Notes </h2><br>' | |
pageNum=0 | |
for page in reader.pages: | |
pageNum+=1 | |
# print(pageNum) | |
if "/Annots" in page: | |
for annot in page["/Annots"]: | |
subtype = annot.get_object()["/Subtype"] | |
if subtype == "/Text": | |
# print(annot.get_object()["/Contents"]) | |
# print('''<a href="''' + filename + '''#page=''' + str(pageNum) + '''"></a>''') | |
finalNote+='''Page:'''+ str(pageNum)+''' <a href="''' + filename + '''#page=''' + str(pageNum) + '''">''' + annot.get_object()["/Contents"] +'''</a><br>''' | |
if subtype == "/FreeText": | |
finalNote+='''Page:'''+ str(pageNum)+''' <a href="''' + filename + '''#page=''' + str(pageNum) + '''">''' + annot.get_object()["/Contents"] +'''</a><br>''' | |
## use pdfannots to extract the highlights | |
subprocess.call(['pdfannots', filename, '-s','highlights', '-o', 'pdfAnnots_foo.txt']) | |
txt = Path('pdfAnnots_foo.txt').read_text() | |
# print(txt) | |
## replace all the page 1, page 3 , etc from output to be urls instead. Assume maximum of 1000 pages | |
## Has to be reversed otherwise Page 100 might be mistaken for Page 10 or Page 1 | |
for i in reversed(range(1000)): | |
string = "Page %d"%(i+1) | |
string_updated =''' <a href="''' + filename + '''#page=''' + '''%d">Page-%d'''%(i+1,i+1) + '''</a><br>''' | |
txt = txt.replace(string, string_updated) | |
# print( markdown2.markdown(txt)) | |
finalNote += "<br>"+markdown2.markdown(txt) | |
print(finalNote) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment