diff --git a/dist/hfdb_xml_converter-0.1-py3-none-any.whl b/dist/hfdb_xml_converter-0.1-py3-none-any.whl
new file mode 100644
index 0000000000000000000000000000000000000000..1d80db8d34da817d439a54f203a6e55900719273
Binary files /dev/null and b/dist/hfdb_xml_converter-0.1-py3-none-any.whl differ
diff --git a/dist/hfdb_xml_converter-0.1.tar.gz b/dist/hfdb_xml_converter-0.1.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..e70851cd19491f7baff4a36296c1f61a6761d61d
Binary files /dev/null and b/dist/hfdb_xml_converter-0.1.tar.gz differ
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000000000000000000000000000000000000..1b68d94ecd0dc92bb45c7722df8642e0afe836e1
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
\ No newline at end of file
diff --git a/setup.cfg b/setup.cfg
new file mode 100644
index 0000000000000000000000000000000000000000..50f4798907552b50c9950bb7f3b1924ce65d811c
--- /dev/null
+++ b/setup.cfg
@@ -0,0 +1,3 @@
+[metadata]
+name = hfdb_xml_converter
+version = 0.1
\ No newline at end of file
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000000000000000000000000000000000000..d20859edac6257b4f10b3da3b3bf6d9d89bad2ca
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,14 @@
+from setuptools import setup, find_packages
+
+setup(
+ name="hfdb_xml_converter",
+ version="0.1",
+ package_dir={"": "src"},
+ packages=find_packages(where="src"),
+ install_requires=[],
+ author="Jan Seipel",
+ author_email="jan.seipel@swr.de",
+ description="Ein Paket zum Parsen der XML-Datei einer HFDB Merkliste und Konvertieren in JSON",
+ long_description=open("README.md").read(),
+ long_description_content_type="text/markdown",
+)
\ No newline at end of file
diff --git a/src/hfdb_xml_converter.egg-info/PKG-INFO b/src/hfdb_xml_converter.egg-info/PKG-INFO
new file mode 100644
index 0000000000000000000000000000000000000000..74ef0e807bba7ece1e09612684e876d278254d62
--- /dev/null
+++ b/src/hfdb_xml_converter.egg-info/PKG-INFO
@@ -0,0 +1,57 @@
+Metadata-Version: 2.1
+Name: hfdb_xml_converter
+Version: 0.1
+Summary: Ein Paket zum Parsen der XML-Datei einer HFDB Merkliste und Konvertieren in JSON
+Author: Jan Seipel
+Author-email: jan.seipel@swr.de
+Description-Content-Type: text/markdown
+
+# hfdb_xml_converter
+
+XML-Datei einer Merkliste auf Korpusebene auslesen und in ein JSON-Format übersetzen.
+
+## Installation
+
+## Verwendung
+
+1. XML-Datei einer HFDB Merkliste aus dem HFDB-Rich-Client herunterladen (Datei -> Export -> XML)
+2. Datei mit Python-Script laden und als JSON ausgeben lassen:
+
+```python
+from hfdb_xml_converter import xml_to_json
+
+input_file = './data/konf_data.xml'
+output_dir = './output'
+output_file = process_xml_to_json(input_file, output_dir)
+
+# Output
+
+[
+ {
+ "id": 1,
+ "traegertitel": "Reaktion Bischof Ackermann auf Bericht zu Missbrauch und Bischof Stein",
+ "tracktitel": "Reaktion Bischof Ackermann auf Bericht zu Missbrauch und Bischof Stein",
+ "keywords": [
+ "Bistumsgeschichte",
+ "Deutlichkeit",
+ "Mehrzahl",
+ ...
+ ],
+ "transkript": "Ich sage schon auch, dass es für mich bedrückend ist, dass ...",
+ "link": "https://linkresolver2.ivz.cn.ard.de/linkresolver/resolve?context=hfdb2&hfdb-recherche/permalink?typ=vollinfoAnzeige&vollinfoArt=vollinfokonf&ak=43073187&ko=53232625&amo=17350850&gkonf=53232624&destination=swrhfdb1"
+ },
+ {
+ "id": 2,
+ "traegertitel": "Unwetter am Bodensee und im Allgäu. Bericht aus Meckenbeuren",
+ "tracktitel": "Unwetter am Bodensee und im Allgäu. Bericht aus Meckenbeuren",
+ "keywords": [
+ "Hochwasser",
+ "Pegel",
+ "Feuerwehr",
+ ...
+ ],
+ "transkript": "Es war eine dramatische Nacht in Meckenbeuren im Bodenseekreis ...",
+ "link": "https://linkresolver2.ivz.cn.ard.de/linkresolver/resolve?context=hfdb2&hfdb-recherche/permalink?typ=vollinfoAnzeige&vollinfoArt=vollinfokonf&ak=42598879&ko=52736037&amo=17124572&gkonf=52736033&destination=swrhfdb1"
+ }
+]
+```
diff --git a/src/hfdb_xml_converter.egg-info/SOURCES.txt b/src/hfdb_xml_converter.egg-info/SOURCES.txt
new file mode 100644
index 0000000000000000000000000000000000000000..8e8a0edfae8efec642d8f9058505be0e6d359f8b
--- /dev/null
+++ b/src/hfdb_xml_converter.egg-info/SOURCES.txt
@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+setup.cfg
+setup.py
+src/hfdb_xml_converter/__init__.py
+src/hfdb_xml_converter/parser.py
+src/hfdb_xml_converter.egg-info/PKG-INFO
+src/hfdb_xml_converter.egg-info/SOURCES.txt
+src/hfdb_xml_converter.egg-info/dependency_links.txt
+src/hfdb_xml_converter.egg-info/top_level.txt
\ No newline at end of file
diff --git a/src/hfdb_xml_converter.egg-info/dependency_links.txt b/src/hfdb_xml_converter.egg-info/dependency_links.txt
new file mode 100644
index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc
--- /dev/null
+++ b/src/hfdb_xml_converter.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/src/hfdb_xml_converter.egg-info/top_level.txt b/src/hfdb_xml_converter.egg-info/top_level.txt
new file mode 100644
index 0000000000000000000000000000000000000000..df33646883c5cb574acfbd1e19c70bc3e54a27a2
--- /dev/null
+++ b/src/hfdb_xml_converter.egg-info/top_level.txt
@@ -0,0 +1 @@
+hfdb_xml_converter
diff --git a/src/hfdb_xml_converter/__init__.py b/src/hfdb_xml_converter/__init__.py
new file mode 100644
index 0000000000000000000000000000000000000000..a2e86ead82640c23093b7fbaa9b5015816064598
--- /dev/null
+++ b/src/hfdb_xml_converter/__init__.py
@@ -0,0 +1 @@
+from .parser import parse_xml, xml_to_json
\ No newline at end of file
diff --git a/src/hfdb_xml_converter/parser.py b/src/hfdb_xml_converter/parser.py
new file mode 100644
index 0000000000000000000000000000000000000000..ca0c1d2ca57a572e5da7a776f08f4475181b53c7
--- /dev/null
+++ b/src/hfdb_xml_converter/parser.py
@@ -0,0 +1,86 @@
+import xml.etree.ElementTree as ET
+import json
+import os
+
+def parse_xml(xml_file):
+ tree = ET.parse(xml_file)
+ root = tree.getroot()
+
+ # Namespace-Definition
+ ns = {'ns': 'http://ard.de/sad/hfdb/vollinfo'}
+
+ result = []
+ id_counter = 1
+
+ for index, vi in enumerate(root.findall('ns:VI', ns)):
+ item = {'id': id_counter}
+ id_counter += 1
+
+ # Traegertitel
+ ak_full = vi.find(".//ns:AK[@voll='j']", ns)
+ if ak_full is not None:
+ rhti = ak_full.find('ns:RHTI', ns)
+ if rhti is not None and rhti.text:
+ item['traegertitel'] = rhti.text.strip()
+ else:
+ print("Kein RHTI Element in AK[@voll='j'] gefunden oder leerer Text")
+ else:
+ print("Kein AK Element mit voll='j' gefunden")
+
+ # Tracktitel
+ ak = vi.find('ns:AK', ns)
+ if ak is not None:
+ rhti = ak.find('ns:RHTI', ns)
+ if rhti is not None and rhti.text:
+ item['tracktitel'] = rhti.text.strip()
+ else:
+ print("Kein RHTI Element in AK gefunden oder leerer Text")
+ else:
+ print("Kein AK Element gefunden")
+
+ # Nur das erste KONF-Element verarbeiten
+ konf = vi.find('.//ns:KONF', ns)
+ if konf is not None:
+ # Keywords
+ keywords = []
+ for kwe in konf.findall('.//ns:KWE/ns:TEXT', ns):
+ if kwe.text:
+ keywords.append(kwe.text.strip())
+ item['keywords'] = keywords
+
+ # Transkript
+ transcript = ""
+ for speaker in konf.findall('.//ns:TRANSCRIPT/ns:SPEAKER', ns):
+ if speaker.text:
+ transcript += speaker.text.strip() + " "
+ item['transkript'] = transcript.strip()
+ else:
+ print("Kein KONF Element gefunden")
+
+ # Link aus PLUGPARA erstellen
+ plugpara = vi.find('.//ns:PLUGPARA', ns)
+ if plugpara is not None:
+ instance = plugpara.get('instance')
+ konf = plugpara.get('konf')
+ amo = plugpara.get('amo')
+ ak = plugpara.get('ak')
+ gk = plugpara.get('gk')
+
+ link = f"https://linkresolver2.ivz.cn.ard.de/linkresolver/resolve?context=hfdb2&hfdb-recherche/permalink?typ=vollinfoAnzeige&vollinfoArt=vollinfokonf&ak={ak}&ko={konf}&amo={amo}&gkonf={gk}&destination={instance}"
+ item['link'] = link
+ else:
+ print("Kein PLUGPARA Element gefunden")
+
+ result.append(item)
+
+ return result
+
+def xml_to_json(input_file, output_dir):
+ data = parse_xml(input_file)
+ output_file = os.path.join(output_dir, os.path.splitext(os.path.basename(input_file))[0] + '.json')
+
+ with open(output_file, 'w', encoding='utf-8') as f:
+ json.dump(data, f, ensure_ascii=False, indent=2)
+
+ print(f"Die JSON-Datei wurde erstellt: {output_file}")
+ return output_file