blubbblülüllü

lib.py

@@ -0,0 +1,22 @@
+import os, pymupdf
+
+def read_files(path, output, filetypes=None):
+    if filetypes is None:
+        filetypes = ["pdf", "txt", "png", "jpg", "mp3"]
+
+    for root, dirs, files in os.walk(path):
+        for file in files:
+            if (file_type := file.split(".")[-1]) in filetypes:
+                output.append((file_type, os.path.join(path, file)))
+
+        for folder in dirs:
+            read_files(os.path.join(path, folder), output)
+
+        break
+
+def extract_pdf_content(pdf_datei):
+    doc = pymupdf.open(pdf_datei)
+    a = ""
+    for page in doc:
+        a += page.get_text()
+    return a

main.py

@@ -0,0 +1,31 @@
+import pymupdf
+import os
+import lib
+import json
+
+def retrieve_file_contents(path):
+    file_extraction_functions = {
+        "pdf": lambda path: lib.extract_pdf_content(path),
+        "jpg": lambda path: "",
+        "png": lambda path: "",
+        "txt": lambda path: lib.extract_pdf_content(path),
+        "mp3": lambda path: "test mp3"
+    }
+
+    lib.read_files(path, files := [])
+
+    contents = []
+
+    for file in files:
+        content = file_extraction_functions[file[0]](file[1])
+        contents.append({
+            "type": file[0],
+            "path": file[1],
+            "content": content
+        })
+
+    return contents
+
+contents = retrieve_file_contents("C:\\SoftwareEng")
+
+print(json.dumps(contents, indent="\t"))