add-api-extract-pdf-content

MinioExtract.py

@@ -0,0 +1,9 @@
+from pdf2image import convert_from_path
+import pytesseract
+
+pages = convert_from_path("images/sample.pdf", dpi=300)
+
+for i, page in enumerate(pages):
+    text = pytesseract.image_to_string(page, config="--psm 6")
+    print(f"--- Page {i+1} ---")
+    print(text)