Create test_PDFparser.py

2024-12-10 19:16:02 +01:00
parent 57caa420a9
commit 055657939e
1 changed files with 13 additions and 0 deletions
@@ -0,0 +1,13 @@
+import pymupdf
+
+def extrahiere_text_als_string(pdf_datei):
+    doc = pymupdf.open(pdf_datei)
+    a = ""
+    for page in doc:
+        a += page.get_text()
+    return a
+
+pdf_datei = 'InformatikModulhandbuch.pdf'
+a = extrahiere_text_als_string(pdf_datei)
+
+print(a)