Created
August 17, 2016 11:12
-
-
Save phreeza/d2d1f20ecff5d7768e119bf6ec17a966 to your computer and use it in GitHub Desktop.
Extract comments from a pdf file and dump them into a markdown file for pretty formatting.
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
# adapted from http://stackoverflow.com/a/12502560/379300 | |
# Output should be valid markdown, so it can be turned into a nice pdf with pandoc | |
import poppler | |
import sys | |
import urllib | |
import os | |
def main(): | |
input_filename = sys.argv[1] | |
# http://blog.hartwork.org/?p=612 | |
document = poppler.document_new_from_file('file://%s' % \ | |
urllib.pathname2url(os.path.abspath(input_filename)), None) | |
n_pages = document.get_n_pages() | |
all_annots = 0 | |
pages = [] | |
comments = [] | |
for i in range(n_pages): | |
page = document.get_page(i) | |
annot_mappings = page.get_annot_mapping () | |
num_annots = len(annot_mappings) | |
if num_annots > 0: | |
pages.append(i) | |
comments.append([]) | |
for annot_mapping in annot_mappings: | |
if annot_mapping.annot.get_annot_type().value_name != 'POPPLER_ANNOT_LINK': | |
if type(annot_mapping.annot.get_contents()) is str: | |
all_annots += 1 | |
comments[-1].append(annot_mapping.annot.get_contents()) | |
for cl,p in zip(comments,pages): | |
if len(cl) > 0: | |
print "Page "+str(p+1) | |
print "=====" | |
for c in cl: | |
print '- '+c | |
if all_annots > 0: | |
print str(all_annots) + " annotation(s) found" | |
else: | |
print "no annotations found" | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment