diff --git a/workshops/2024_Digital_History_Halle/02_Autoren_extrahieren.ipynb b/workshops/2024_Digital_History_Halle/02_Autoren_extrahieren.ipynb
new file mode 100644
index 0000000..9096d6e
--- /dev/null
+++ b/workshops/2024_Digital_History_Halle/02_Autoren_extrahieren.ipynb
@@ -0,0 +1,127 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "56184c51-b4cd-4009-b53c-40f73bb4e14a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22cfe659-cb0d-42c4-830f-d10deb947f4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"Studentenbewegung.csv\", encoding=\"utf-8\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49e471cb-3e2f-46ae-8b44-3707b8dd5d79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.drop(['titel', 'rela'], axis=1)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3b37bdbf-cf0f-4ebe-a1f3-3d0406a411dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df[df['author'] != 'unknown']\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "54b7dbc7-4bb0-42b2-b642-c97dcbf6b3fe",
+   "metadata": {},
+   "source": [
+    "### Bereinigen: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d2b544f6-c1d9-4391-8fe5-12815a31a09d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.loc[:, 'gnd_modified'] = df['gnd'].str.split(';').str.get(0)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83716027-df06-4469-a03e-b40905f937b0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.drop(['gnd'], axis=1)\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "66378256-9230-44b8-9243-026c7ca5e171",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "count_unknown = (df['gnd_modified'] == 'unknown').sum()\n",
+    "print(\"Einträge in gnd_modified mit value 'unknown': \", count_unknown)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37202ea-4067-483f-bd93-41f4d6dc43a3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"authors.csv\", encoding=\"utf-8\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ffad82ee-3945-4a99-a11b-b36f127500df",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/workshops/2024_Digital_History_Halle/04_Kartendarstellung.ipynb b/workshops/2024_Digital_History_Halle/04_Kartendarstellung.ipynb
new file mode 100644
index 0000000..9c9392b
--- /dev/null
+++ b/workshops/2024_Digital_History_Halle/04_Kartendarstellung.ipynb
@@ -0,0 +1,180 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0a353f0-04f8-4d56-8285-5ce440aa88fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from geopy.geocoders import Nominatim\n",
+    "from geopy.exc import GeocoderTimedOut\n",
+    "import plotly.express as px"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85fd2f76-4a65-4310-a82f-d1e0b6168748",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"authors-csv.csv\", encoding=\"utf-8\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd119b8f-ff17-4055-8a0d-9c1b571c3b38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialisieren des Geolocators: \n",
+    "geolocator = Nominatim(user_agent=\"geoapiExercises\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce67491f-88de-44ae-8ebb-62707b78a477",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Funktion, um Longitude und Latitude zu ermitteln:\n",
+    "def get_lat_long(place):\n",
+    "    try:\n",
+    "        location = geolocator.geocode(place)\n",
+    "        if location:\n",
+    "            return location.latitude, location.longitude\n",
+    "        else:\n",
+    "            return None, None\n",
+    "    except GeocoderTimedOut:\n",
+    "        return None, None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ec029f1f-20d2-4bd9-86ab-91aee865fe1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Funktion auf der Spalte \"place\" ausführen, um neue Spalten \"lat\" und \"long\" zu ergänzen: \n",
+    "df[['lat', 'long']] = df['place'].apply(lambda x: pd.Series(get_lat_long(x)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "880d0dd3-7164-4091-985b-dca67334ec3e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8dcbaa61-c183-4f97-a0fd-168e5871ec9d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.dropna(subset=['lat', 'long'])\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1c122059-d170-4c5c-9134-317c684d30b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Gruppieren bei \"place\" und zählen der Vorkommen der einzelnen Orte:\n",
+    "place_counts = df.groupby('place').size().reset_index(name='count')\n",
+    "place_counts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3952f9a7-8d8c-45bd-ac7a-eb6239ef51af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Zusammenführen der Zählungen mit dem ursprünglichen Dataframe in einem neuen Dataframe \"df_with_counts\":\n",
+    "df_with_counts = df.merge(place_counts, on='place')\n",
+    "df_with_counts"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0d8647d3-ac4c-4bd4-aa44-1829e2707484",
+   "metadata": {},
+   "source": [
+    "### Kartenvisualisierung erstellen:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "64e8cadd-be66-4dff-a9f6-206b02b5a963",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Karte erstellen:\n",
+    "fig = px.scatter_mapbox(df_with_counts, \n",
+    "                        lat=\"lat\", \n",
+    "                        lon=\"long\", \n",
+    "                        hover_name=\"place\", \n",
+    "                        hover_data=[\"count\"],\n",
+    "                        size=\"count\",\n",
+    "                        color=\"count\",\n",
+    "                        zoom=4,\n",
+    "                        height=600)\n",
+    "\n",
+    "# Update des Layouts\n",
+    "fig.update_layout(mapbox_style=\"open-street-map\")\n",
+    "fig.update_layout(margin={\"r\":0,\"t\":0,\"l\":0,\"b\":0})\n",
+    "\n",
+    "# Karte anzeigen: \n",
+    "fig.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83307d4d-f459-4064-a4ae-e08b6e6648da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Karte bei Bedarf als HTML-Datei speichern: \n",
+    "fig.write_html(\"places_map_plotly.html\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/workshops/2024_Digital_History_Halle/05_PDFs_herunterladen.ipynb b/workshops/2024_Digital_History_Halle/05_PDFs_herunterladen.ipynb
new file mode 100644
index 0000000..2e530d3
--- /dev/null
+++ b/workshops/2024_Digital_History_Halle/05_PDFs_herunterladen.ipynb
@@ -0,0 +1,360 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3e35d02-d746-4493-967a-8bc0147b4db9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import os\n",
+    "import wget\n",
+    "import PyPDF2\n",
+    "from PyPDF2 import PdfReader\n",
+    "import urllib.parse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2978b485-bd48-45e0-8460-22f9fe9b5d4f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"Studentenbewegung_pdfs.csv\", encoding=\"utf-8\")\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "48b358c3-23a5-449a-8a6b-39a8d258c097",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "links = df[\"links\"]\n",
+    "print(links)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1dc537a0-8479-4a17-a08d-296cefe38b7c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(links[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c41d1db-3784-4111-80ef-eecb0e9f84c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "linklist = []\n",
+    "\n",
+    "for element in links:\n",
+    "    related_links = element.split(\"; \")\n",
+    "    for link in related_links: \n",
+    "        if link.startswith(\"https://d-nb.info/\"):\n",
+    "            #print(link)\n",
+    "            linklist.append(link)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e9c46e26-546c-46af-bef4-cc06d12fc7d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(len(linklist))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ae473829-9add-4ba2-8d37-d4e5eb3a974f",
+   "metadata": {},
+   "source": [
+    "#### Alternative: \n",
+    "```\n",
+    "linklist = []\n",
+    "\n",
+    "for idn in df.idn: \n",
+    "    link = \"https://d-nb.info/\" + idn + \"/34\"\n",
+    "    linklist.append(link) ```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9f958ef9-e31c-4b3e-b958-36b89b5c4bfc",
+   "metadata": {},
+   "source": [
+    "## Herunterladen der PDF-Dateien\n",
+    "\n",
+    "Gekürzte Liste erstellen (damit es schneller geht):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d133ad99-b713-4bea-9ada-2ab5f5ba2111",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testlist = linklist[60:70]\n",
+    "print(testlist)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48f7c8d5-29c0-4210-baf5-5caf3557dce0",
+   "metadata": {},
+   "source": [
+    "Funktion zum Herunterladen definieren, die zunächst ein neues Verzeichnis für die gesammelten Dateien erstellt und diese dann herunterlädt und unter Nutzung der IDN als Dateiname abspeichert: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "975bffd0-f668-428d-b189-69aee98afd97",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "def download_text(testlist, save_directory):\n",
+    "    # Erstellen des später definierten Speicherverzeichnis, falls es dieses noch nicht gibt\n",
+    "    if not os.path.exists(save_directory):\n",
+    "        os.makedirs(save_directory)\n",
+    "    \n",
+    "    for link in testlist: \n",
+    "        # IDN ermitteln:\n",
+    "        idn = link.split('/')[-2]\n",
+    "        # Original-Dateiname und -Endung aus Content-Disposition header ermitteln und als Basis nutzen:\n",
+    "        response = requests.head(link)\n",
+    "        content_disposition = response.headers.get('Content-Disposition')\n",
+    "        orig_filename = content_disposition.split('filename=')[-1].strip('\";')\n",
+    "        print(orig_filename)\n",
+    "\n",
+    "        # Dateiname aus IDN und originalem Dateiname zusammensetzen: \n",
+    "        file_name = f\"{idn}_{orig_filename}\"\n",
+    "        file_path = os.path.join(save_directory, file_name)\n",
+    "        print(f\" Starte Download: {file_name}\")\n",
+    "        try: \n",
+    "            #Datei herunterladen:\n",
+    "            wget.download(link, out=file_path)\n",
+    "        except Exception as e:\n",
+    "            print(f\"Fehler beim Herunterladen von {link}: {e}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "64fdc34b-49fe-41c9-b5e9-99545e4c7ac2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "save_directory = \"downloads\"\n",
+    "\n",
+    "download_text(testlist, save_directory)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2d5864c5-a1d3-4bf3-9d71-9739c1da02fb",
+   "metadata": {},
+   "source": [
+    "### Test: Einlesen einer Seite eines PDFs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d808a4a6-ae0d-4569-96be-fc1d86544f93",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test_read_pdf(file_path, file_name):\n",
+    "    reader = PdfReader(file_path + \"/\" + file_name)\n",
+    "    number_of_pages = len(reader.pages)\n",
+    "    page = reader.pages[10]\n",
+    "    text = page.extract_text()\n",
+    "    print(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a10b0292-be99-4bcf-aa23-2e0b786d9842",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_read_pdf(\"downloads\", \"1334711879.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b96d9085-3900-4794-a2fc-09bd4d25429a",
+   "metadata": {},
+   "source": [
+    "### Einlesen einer kompletten PDF-Datei:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c18ddf2f-c7e7-444e-9a47-9253a5cba71f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def read_pdf_content(file_path, filename):\n",
+    "    try:\n",
+    "        reader = PdfReader(file_path + \"/\" + filename)\n",
+    "        number_of_pages = len(reader.pages)\n",
+    "        text = \"\"\n",
+    "        for page in reader.pages:\n",
+    "            text += page.extract_text()  # + \"\\n\"\n",
+    "        return text\n",
+    "    except Exception as e:\n",
+    "        print(f\"Fehler beim Einlesen der Datei {filename}: {e}\")\n",
+    "        return \"Fehler beim Einlesen der Datei\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75610ab9-e0c7-43c4-947a-9598a00bcb9b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test = read_pdf_content(\"downloads\", \"1192129652_40257_1.pdf\")\n",
+    "print(test)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "37d3998e-a306-4cc6-9b5a-de2b69d31634",
+   "metadata": {},
+   "source": [
+    "### Einlesen **aller** Dateien aus dem \"downloads\"-Verzeichnis, die auf .pdf enden. Anschließend werden die Texte im Zusammenhang mit ihrem Dateinamen in ein Pandas_Dataframe überführt: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bcb98ba6-cbe1-4822-ad1d-e05a70cfe918",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_text_from_pdfs(file_path):\n",
+    "    pdf_text = {}\n",
+    "    for filename in os.listdir(file_path):\n",
+    "        if filename.endswith(\".pdf\"):\n",
+    "            text = read_pdf_content(file_path, filename)\n",
+    "            pdf_text[filename] = text\n",
+    "    return pdf_text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "952f19bd-3c11-48e5-a991-c886293e2c15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pdf_texts = get_text_from_pdfs(\"downloads\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3b201873-d005-4cc9-a00f-54125700b326",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(pdf_texts)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fea2a889-9390-413e-b132-ffba8a1eae90",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Löschen der ganzen Zeilenumbrüche (\"\\n\"): \n",
+    "pdf_texts = {key: value.replace('\\n', ' ') for key, value in pdf_texts.items()}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b1c33883-3180-408b-a92e-bce7df796b46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for key, value in pdf_texts.items():\n",
+    "    print(f\"Key: {key}, Type of value: {type(value)}\")\n",
+    "    if value is None:\n",
+    "        print(f\"None value found for key: {key}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7fc6db13-f1e0-4716-a3d6-114bcbf19bac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Umwandeln in ein Dataframe:\n",
+    "df_texts = pd.DataFrame.from_dict(pdf_texts, orient='index', columns=['Text'])\n",
+    "df_texts.reset_index(inplace=True)\n",
+    "df_texts.columns = ['filename', 'text']\n",
+    "df_texts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c755735-c172-4911-a8ae-73d7e24dc4c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_texts.to_hdf(\"pdf_texts.h5\", key=\"df_texts\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9da4a877-fd9f-4ed2-b100-37c5022bd34d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}