pdfQA / pdf_reader.py
engrtm's picture
Upload 5 files
d4db0fd verified
Raw History Blame Contribute Delete
197 Bytes
import fitz # PyMuPDF
def extract_text_from_pdf(file):
text = ""
pdf = fitz.open(stream=file.read(), filetype="pdf")
for page in pdf:
text += page.get_text()
return text