dfasdfsdfsd

lib.py

@@ -1,5 +1,9 @@
 import os, pymupdf, whisper, json
 
+import cv2
+import pytesseract
+
+
 def read_files(path, output, filetypes=None):
     if filetypes is None:
         filetypes = ["pdf", "txt", "png", "jpg", "mp3"]
@@ -27,5 +31,12 @@ def extract_mp3_content(mp3_datei):
 
     result = model.transcribe(str(mp3_datei), language='de', verbose=True)
 
-    with open('transcript.json', "w") as f:
-        json.dump(result['text'], f, indent=4)
+    # with open('transcript.json', "w") as f:
+    #     json.dump(result['text'], f, indent=4)
+
+    return result["text"]
+
+def extract_image_content(path):
+    pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
+    img = cv2.imread(path)
+    return pytesseract.image_to_string(img)

main.py

@@ -6,8 +6,8 @@ import json
 def retrieve_file_contents(path):
     file_extraction_functions = {
         "pdf": lambda path: lib.extract_pdf_content(path),
-        "jpg": lambda path: "",
-        "png": lambda path: "",
+        "jpg": lambda path: lib.extract_image_content(path),
+        "png": lambda path: lib.extract_image_content(path),
         "txt": lambda path: lib.extract_pdf_content(path),
         "mp3": lambda path: lib.extract_mp3_content(path),
     }