biosummarize-ai / utils /pdf_parser.py
AryanRajSaxena's picture
initial commit
7c114b1
raw
history blame contribute delete
174 Bytes
import fitz # PyMuPDF
def extract_text_from_pdf(pdf_path):
text = ""
doc = fitz.open(pdf_path)
for page in doc:
text += page.get_text()
return text