pdfHighlight_word_grabber

#grab_Highlighted_texts_and_its_page_Number_from_PDF
#python3
#python3 highlight.py example.pdf

#skip420@skip420:~/Desktop/pdfhighlight$ python3 highlight.py example.pdf
challenge  11
(nutritional  11
legumes,  16
Pritikin  17
4 annotation(s) found





#Author:Skip420

# python3 test5.py example.pdf
#Note: Where it says "example.pdf" You may replace the file name to whatever it is.


import popplerqt5 # sudo apt-get install -y python3-poppler-qt5
import sys
import PyQt5
import urllib
import os
import PyPDF2


def main():

    doc = popplerqt5.Poppler.Document.load(sys.argv[1])
    total_annotations = 0
    for x in range(doc.numPages()):
        #print("========= PAGE {} =========".format(i+1))
        page = doc.page(x)
        annotations = page.annotations()
        (pwidth, pheight) = (page.pageSize().width(), page.pageSize().height())
        if len(annotations) > 0:
            for annotation in annotations:
                if  isinstance(annotation, popplerqt5.Poppler.Annotation):
                    total_annotations += 1
                    if(isinstance(annotation, popplerqt5.Poppler.HighlightAnnotation)):
                        quads = annotation.highlightQuads()
                        txt = ""
                        for quad in quads:
                            rect = (quad.points[0].x() * pwidth,
                                    quad.points[0].y() * pheight,
                                    quad.points[2].x() * pwidth,
                                    quad.points[2].y() * pheight)
                            bdy = PyQt5.QtCore.QRectF()
                            bdy.setCoords(*rect)
                            txt = txt + str(page.text(bdy)) + ' '

                        #print("========= ANNOTATION =========")
                        print (txt, x)

    if total_annotations > 0:
        print (str(total_annotations) + " annotation(s) found")
    else:
        print ("no annotations found")

if __name__ == "__main__":
    main()