combine the site with annotations of many PDFs to one file

annot.py

import poppler, os.path
import os

filenames = []

handels = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"

for  name in os.listdir('.'):
    if name[-4:] == ".pdf":
        filenames.append(name)


filenames.sort()

pdfjam_str = "pdftk "
for i in range(0,len(filenames)):
    pdfjam_str += str(handels[i]) + "=" + filenames[i] + " "

pdfjam_str += "cat "
for file_id in range(0,len(filenames)):
    filename=filenames[file_id]
    print(filename)
    path = 'file://%s' % os.path.realpath(filename)
    doc = poppler.document_new_from_file(path, None)
    pages = [doc.get_page(i) for i in range(doc.get_n_pages())]
    
    pages_with_annot = []

    for page_no, page in enumerate(pages):
        #items = [i.annot.get_contents() for i in page.get_annot_mapping()]
        items = page.get_annot_mapping()
        for i in items:
            if i != None:
                #print (i.annot.get_annot_type().value_name)
                
                #if i.annot.get_annot_type().value_name != 'POPPLER_ANNOT_INK' and i.annot.get_annot_type().value_name != 'POPPLER_ANNOT_LINK':
                #    print(i.annot.get_annot_type().value_name)
                
                if i.annot.get_annot_type().value_name == 'POPPLER_ANNOT_INK':
                    print(page_no)
                    pages_with_annot.append(page_no)
                    break
        #items = [i for i in items if i]
        #print "page: %s comments: %s " % (page_no + 1, items)
    if len(pages_with_annot) > 0:
        #pdfjam_str += filename + " " + str(min(pages_with_annot)) + ":" + str(max(pages_with_annot)) + " "
        pdfjam_str += handels[file_id] + str(min(pages_with_annot)+1) + "-" + str(max(pages_with_annot)+1) + " "
    #print()

pdfjam_str += " output merged.pdf"
print(pdfjam_str)