Get annotation text from its position (PDFMiner) - pdfminer

Question

I want to extract the text of annotations (such as highlighted text of hyperlinks) from its position. For this I could scrape the positions and urls by using PDFminer as in the below code. Is that possible passing this position to a layout object and get out the text?
Here are the code blocks I used for this purpose.
First part includes a function, named parse_annotation, to parse annotations from each page.
def parse_annotations(page):
positions = []
urls = []
for annot in pdftypes.resolve1(page.annots):
if isinstance(annot, pdftypes.PDFObjRef):
annotationDict = annot.resolve()
# Skip over any annotations that are not links
if str(annotationDict["Subtype"]) != "/'Link'":
continue
destID = 0
position = annotationDict["Rect"]
uriDict = "None"
if any(k in annotationDict for k in {"Dest", "D"}):
destID = (annotationDict["Dest"][0]).objid
url = "Cross reference"
elif "A" in annotationDict:
# Key A contains PDFObjRef, then resolve it again
if isinstance(annotationDict["A"], pdftypes.PDFObjRef):
uriDict = pdftypes.resolve1(annotationDict["A"])
if any(k in uriDict for k in {"Dest", "D"}):
destID = (uriDict["D"][0]).objid
else:
uriDict = annotationDict["A"]
# Check if the key exists within resolved uriDict
if str(uriDict["S"]) == "/'GoTo'":
url = "Cross reference"
elif str(uriDict["S"]) == "/'URI'":
url = str(uriDict["URI"])
url = url.lstrip("b")
url = url.replace("'", "")
else:
# Skip if key S in uriDict does not contain value URI, GoTo
continue
else:
sys.stderr.write("Warning: unknown key in annotationDict : ", annotationDict)
#print(annot, '\n', annotationDict, '\n', destID, '\n', position, '\n', uriDict, '\n', url, '\n')
print(position, '\n', url, '\n')
positions.append(position)
urls.append(url)
else:
sys.stderr.write("Warning: unknown annotation: %s\n" % annot)
return positions, urls
Example PDF file can be found from the following link below.
https://www2.ed.gov/about/offices/list/ocr/docs/20200512-qa-psi-covid-19.pdf
Now, by using PDFMiner, created a document object and start looping over the pages found in PDF.
manager = PDFResourceManager()
output = StringIO()
codec = 'utf-8'
laparams = LAParams()
converter = TextConverter(manager, output, codec=codec, laparams=laparams)
device = PDFPageAggregator(manager, laparams=laparams)
interpreter = PDFPageInterpreter(manager, device)
page_interpreter = PDFPageInterpreter(manager, converter)
filename = '20200512-qa-psi-covid-19.pdf'
fp = open(filename, 'rb')
parser = PDFParser(fp)
document = PDFDocument(parser)
if not document.is_extractable:
raise PDFTextExtractionNotAllowed
page_no = 0
for pageNumber, page in enumerate(PDFPage.create_pages(document)):
print("\n================ PageNumber ", pageNumber+1, "===================\n")
if pageNumber == page_no:
page_interpreter.process_page(page)
raw_text = output.getvalue()
output.truncate(0)
output.seek(0)
interpreter.process_page(page)
layout = device.get_result()
if page.annots:
positions, urls = parse_annotations(page)
for obj in layout:
print('Object name and position %s \t %s \n' % (obj.__class__.__name__ , obj.bbox))
page_no += 1
fp.close()
converter.close()
output.close()
device.close()
Thanks in advance,
A.