From 055657939e21dc9de3ca6b8cd89f33c52743e6a1 Mon Sep 17 00:00:00 2001 From: Amira24523 <85802878+Amira24523@users.noreply.github.com> Date: Tue, 10 Dec 2024 19:16:02 +0100 Subject: [PATCH] Create test_PDFparser.py --- test_PDFparser.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 test_PDFparser.py diff --git a/test_PDFparser.py b/test_PDFparser.py new file mode 100644 index 0000000..fe11fe1 --- /dev/null +++ b/test_PDFparser.py @@ -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) \ No newline at end of file