justpeanuts · April 4, 2021 13:38 · Jan 5, 2018
diff --git a/dumppdfcomments.py b/dumppdfcomments.py
@@ -0,0 +1,40 @@
+import popplerqt4
+import sys
+import PyQt4
+
+
+def main():
+
+    doc = popplerqt4.Poppler.Document.load(sys.argv[1])
+    total_annotations = 0
+    for i in range(doc.numPages()):
+        #print("========= PAGE {} =========".format(i+1))
+        page = doc.page(i)
+        annotations = page.annotations()
+        (pwidth, pheight) = (page.pageSize().width(), page.pageSize().height())
+        if len(annotations) > 0:
+            for annotation in annotations:
+                if  isinstance(annotation, popplerqt4.Poppler.Annotation):
+                    total_annotations += 1
+                    if(isinstance(annotation, popplerqt4.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 = PyQt4.QtCore.QRectF()
+                            bdy.setCoords(*rect)
+                            txt = txt + str(page.text(bdy)) + ' '
+
+                        #print("========= ANNOTATION =========")
+                        print(txt)
+
+    if total_annotations > 0:
+        print (str(total_annotations) + " annotation(s) found")
+    else:
+        print ("no annotations found")
+
+if __name__ == "__main__":
+    main()