Nexus_Post_AI / Pdf_utils.py
krishbaresha's picture
Rename pdf_utils.py to Pdf_utils.py
7a13ea7 verified
raw
history blame contribute delete
341 Bytes
import fitz # PyMuPDF
def extract_text_from_pdf(file_path):
"""
Extract text from PDF using PyMuPDF
"""
text = ""
try:
doc = fitz.open(file_path)
for page in doc:
text += page.get_text()
except Exception as e:
text = ""
print(f"PDF extraction error: {e}")
return text