Last active
May 5, 2020 23:04
-
-
Save PedroBern/2378b33bc7a66c1379d8865e7b1ab6c0 to your computer and use it in GitHub Desktop.
Jupyter Notebook html2pdf
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
import sys | |
import re | |
import pdfkit | |
infile_name = sys.argv[1] | |
if len(sys.argv) > 2: | |
outfile_name = sys.argv[2] | |
else: | |
outfile_name = infile_name + "_2" | |
re_remove = [ | |
"#notebook\-container\s+{.+(-webkit-box-shadow:[^;]+;)", | |
"#notebook\-container\s+{.+(box-shadow:[^;]+;)" | |
] | |
re_sub = [ | |
("\/\* This needs to be wide enough for 3 digit prompt numbers: In\[100\]: \*\/", | |
"visibility: hidden;") | |
] | |
with open(outfile_name + ".html", 'w') as outfile: | |
with open(infile_name + ".html") as infile: | |
f = infile.read() | |
for r in re_remove: | |
f = re.sub(r, '', f, flags=re.DOTALL) | |
for r in re_sub: | |
f = re.sub(r[0], r[1], f, flags=re.DOTALL) | |
outfile.write(f) | |
pdfkit.from_file(outfile_name + ".html", outfile_name + ".pdf") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment