Merge branch 'add-bonus-tutorials'

src/04_use_case_bonus/events/veranstaltungen_aggregieren.ipynb

@@ -0,0 +1,172 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "title: \"Von HTML zu CSV: Veranstaltungsinformationen sammeln\"\n",
+        "description: \"Veranstaltungsinformationen mit BeautifulSoup und Pandas extrahiert und aufbereitet.\"\n",
+        "image: _dbd423b9-5d05-4857-a0be-b7136518e7ff.jpeg\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "::: {.callout-tip}\n",
+        "## Lernziele\n",
+        "\n",
+        "* Lernen, wie man spezifische HTML-Elemente extrahiert. Anwendung von Selektoren zur gezielten Extraktion von Text aus HTML-Elementen wie `<h2 class=\"teaser__title\">`, `<p class=\"teaser__subtitle\">`, usw.\n",
+        "* Verstehen, wie man Informationen über Veranstaltungen in der politischen Bildung in Brandenburg sammelt und analysiert, um sie für weiterführende Projekte oder Studien zu nutzen.\n",
+        ":::"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/spaces/datenwerkzeuge/CDL-Webscraping-Workshop-2025/blob/main/src/04_use_case_bonus/events/veranstaltungen_aggregieren.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "EsBwSUgTzKLH"
+      },
+      "outputs": [],
+      "source": [
+        "# bundeszentrale für politische bildung bietet RSS für veranstaltungen https://www.bpb.de/die-bpb/ueber-uns/service/rss/\n",
+        "# an anderer stelle kommt bei fehlen von RSS oder API, scraping in betracht"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "wUuU7z1jxzTf"
+      },
+      "outputs": [],
+      "source": [
+        "# view-source:https://www.politische-bildung-brandenburg.de/veranstaltungen?page=2"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "aHP0vByew7PX",
+        "outputId": "301f3797-99ab-463f-9448-b925e1f01a1e"
+      },
+      "outputs": [],
+      "source": [
+        "# prompt: bitte extrahiere alle article elemente aus dem html dokument und extrahiere den text der folgenden element in jedem article element : <h2 class=\"teaser__title\">\n",
+        "# <p class=\"teaser__subtitle\">\n",
+        "# <p class=\"teaser__meta\">\n",
+        "# <p class=\"teaser__kicker\">\n",
+        "# <p class=\"teaser__data\">\n",
+        "\n",
+        "import requests\n",
+        "from bs4 import BeautifulSoup\n",
+        "\n",
+        "url = \"https://www.politische-bildung-brandenburg.de/veranstaltungen\"\n",
+        "\n",
+        "extracted_data = []\n",
+        "\n",
+        "for page in range(1, 10):\n",
+        "    url = f\"https://www.politische-bildung-brandenburg.de/veranstaltungen?page={page}\"\n",
+        "    try:\n",
+        "        response = requests.get(url)\n",
+        "        response.raise_for_status()\n",
+        "\n",
+        "        soup = BeautifulSoup(response.content, \"html.parser\")\n",
+        "\n",
+        "        articles = soup.find_all(\"article\")\n",
+        "\n",
+        "\n",
+        "        for article in articles:\n",
+        "            title = article.find(\"h2\", class_=\"teaser__title\")\n",
+        "            subtitle = article.find(\"p\", class_=\"teaser__subtitle\")\n",
+        "            meta = article.find(\"p\", class_=\"teaser__meta\")\n",
+        "            date = article.find(\"p\", class_=\"teaser__kicker\")\n",
+        "            location = article.find(\"p\", class_=\"teaser__data\") # corrected class name\n",
+        "\n",
+        "            extracted_data.append({\n",
+        "                \"title\": title.text.strip() if title else None,\n",
+        "                \"subtitle\": subtitle.text.strip() if subtitle else None,\n",
+        "                \"meta\": meta.text.strip() if meta else None,\n",
+        "                \"date\": date.text.strip() if date else None,\n",
+        "                \"location\": location.text.strip() if location else None\n",
+        "            })\n",
+        "\n",
+        "        print(url, len(articles))\n",
+        "        if len(articles) == 0:\n",
+        "            break\n",
+        "\n",
+        "    except requests.exceptions.RequestException as e:\n",
+        "        print(f\"An error occurred during the request: {e}\")\n",
+        "    except Exception as e:\n",
+        "        print(f\"An error occurred during processing: {e}\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "id": "vqxi7Fkkyogw"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "\n",
+        "df = pd.DataFrame(extracted_data)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "id": "u41T06D7y6Yk"
+      },
+      "outputs": [],
+      "source": [
+        "df.to_csv(\"extracted_events.csv\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        },
+        "id": "4R46y6phy8xU",
+        "outputId": "0d466855-efba-4c94-9e34-c99851d165ce"
+      },
+      "outputs": [],
+      "source": [
+        "pd.read_csv(\"extracted_events.csv\", index_col=0)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

src/04_use_case_bonus/news/zeitungsartikel.ipynb

@@ -0,0 +1,181 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "title: \"Nachrichten-Data Mining\"\n",
+        "description: \"Extraktion und Analyse von Nachrichtenartikeln mithilfe von Python und spezifischen Bibliotheken wie newspaper3k.\"\n",
+        "image: _5e53f950-55e9-4158-9404-88d41af64cfb.jpeg\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "::: {.callout-tip}\n",
+        "## Lernziele\n",
+        "\n",
+        "* Entwicklung von Fähigkeiten zur Erstellung von Skripten, die wiederholt Nachrichtenartikel von einer bestimmten Quelle sammeln und analysieren können.\n",
+        "* Methoden der newspaper-Bibliothek, wie build, download, parse und nlp, zur Verarbeitung und Analyse von Nachrichtenartikeln.\n",
+        "* Einblick in die Struktur von Nachrichten-Webseiten und wie diese für analytische Zwecke genutzt werden können.\n",
+        ":::\n",
+        "\n",
+        "[RSS Feeds der Süddeutschen Zeitung in der Übersicht ](https://www.sueddeutsche.de/service/updates-mit-rss-uebersicht-aller-rss-feeds-fuer-sz-de-sz-magazin-und-jetzt-de-1.393950)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/spaces/datenwerkzeuge/CDL-Webscraping-Workshop-2025/blob/main/src/04_use_case_bonus/news/zeitungsartikel.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Y1uXvjoY4fap",
+        "outputId": "95e6c22b-5b37-47ab-f1ec-f5aac34c1f3f"
+      },
+      "outputs": [],
+      "source": [
+        "! pip install newspaper3k -q"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "gFRiyo7M4xZ_",
+        "outputId": "096a2225-ecfa-4e4c-bc88-f1e9f5ba03eb"
+      },
+      "outputs": [],
+      "source": [
+        "! pip install lxml_html_clean -q # Install the required package"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "rGGgwoZa4pRo"
+      },
+      "outputs": [],
+      "source": [
+        "import newspaper"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "metadata": {
+        "id": "6eejA6K0484J"
+      },
+      "outputs": [],
+      "source": [
+        "sueddeutsche_paper = newspaper.build('https://www.sueddeutsche.de/')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "-XjEtFnv5Q8u",
+        "outputId": "3c2efabd-bec2-4af2-bb63-c952cd1d6816"
+      },
+      "outputs": [],
+      "source": [
+        "for article in sueddeutsche_paper.articles:\n",
+        "    print(article.url)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "q44TXocf5cHg",
+        "outputId": "16d01c1e-6cc9-4882-aeee-1e46f2c63859"
+      },
+      "outputs": [],
+      "source": [
+        "for category in sueddeutsche_paper.category_urls():\n",
+        "    print(category)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "QlVcueZQ55I4",
+        "outputId": "7226d35d-3a6b-4399-8cd3-9ec2e92ac404"
+      },
+      "outputs": [],
+      "source": [
+        "import nltk\n",
+        "nltk.download('punkt_tab')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "id": "x2FsV8a-5mEh"
+      },
+      "outputs": [],
+      "source": [
+        "sueddeutsche_article = sueddeutsche_paper.articles[0]\n",
+        "sueddeutsche_article.download()\n",
+        "sueddeutsche_article.parse()\n",
+        "sueddeutsche_article.nlp()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 105
+        },
+        "id": "lKem_ggG6CoY",
+        "outputId": "cbd0d8c9-a66b-4deb-b94e-94a3ebab4fe3"
+      },
+      "outputs": [],
+      "source": [
+        "sueddeutsche_article.text"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

src/04_use_case_bonus/trend-monitoring/innovationsmanagement.ipynb

@@ -0,0 +1,129 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "---\n",
+        "title: \"Pytrends zur Analyse von Suchinteresse\"\n",
+        "description: \"Nutzung der Pytrends-Bibliothek für die Analyse des Suchinteresses.\"\n",
+        "image: _3e3e2e53-2755-4ee2-b245-7222dc1ae7f8.jpeg\n",
+        "---"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "::: {.callout-tip}\n",
+        "## Lernziele\n",
+        "\n",
+        "* Grundlegende Manipulation und Analyse von Zeitreihendaten in Pandas DataFrames.\n",
+        "* Analyse und Interpretation von Trends in der Internet-Suchverhaltensdaten, was nützlich für Marktforschung sein kann.\n",
+        ":::"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/spaces/datenwerkzeuge/CDL-Webscraping-Workshop-2025/blob/main/src/04_use_case_bonus/trend-monitoring/innovationsmanagement.ipynb)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "FTMJrfp61duL"
+      },
+      "outputs": [],
+      "source": [
+        "# https://trends.google.com/trends/"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "szDfBN0F0ZjE"
+      },
+      "outputs": [],
+      "source": [
+        "! pip install pytrends -q"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "id": "fUe4GvOY0TkW"
+      },
+      "outputs": [],
+      "source": [
+        "from pytrends.request import TrendReq\n",
+        "\n",
+        "pytrends = TrendReq(hl='en-US', tz=360)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "id": "F6Gl7RpF0eo8"
+      },
+      "outputs": [],
+      "source": [
+        "kw_list = [\"Blockchain\"]\n",
+        "pytrends.build_payload(kw_list, cat=0, timeframe='today 5-y', geo='', gprop='')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000
+        },
+        "id": "8144JVpI0hn7",
+        "outputId": "ef9f123d-9cbc-42c4-ad22-d53108720d50"
+      },
+      "outputs": [],
+      "source": [
+        "pytrends.interest_over_time()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 410
+        },
+        "id": "321ielTs0sPK",
+        "outputId": "c8dbb162-268a-4352-9970-1e3c7c408ea1"
+      },
+      "outputs": [],
+      "source": [
+        "from matplotlib import pyplot as plt\n",
+        "_df_2['Blockchain'].plot(kind='line', figsize=(8, 4), title='Blockchain')\n",
+        "plt.gca().spines[['top', 'right']].set_visible(False)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

src/_quarto.yml

@@ -106,7 +106,14 @@ website:
         - section: "Anwendungsfall Bonus"
           contents: 
           - href: 04_use_case_bonus/podcasts/aggregate_podcast_episodes_to_markdown.ipynb
-            text: "Podcasts aggregieren"
+            text: "Podcasts aggregieren" 
+          - href: 04_use_case_bonus/news/zeitungsartikel.ipynb
+            text: "Nachrichten-Data Mining" 
+          - href: 04_use_case_bonus/trend-monitoring/innovationsmanagement.ipynb
+            text: "Pytrends & Suchinteresse" 
+          - href: 04_use_case_bonus/events/veranstaltungen_aggregieren.ipynb
+            text: "Veranstaltungen sammeln
+"
 
 format:
   html: