project: type: website website: title: "🧭 Einstieg ins Web Scraping - Daten sammeln leicht gemacht" page-navigation: true repo-actions: [edit, source, issue] repo-url: https://huggingface.co/spaces/datenwerkzeuge/CDL-Webscraping-Workshop-2025/ repo-subdir: src repo-link-target: _blank issue-url: https://huggingface.co/spaces/datenwerkzeuge/CDL-Webscraping-Workshop-2025/discussions navbar: left: - href: index.qmd text: "1️⃣ Start" - href: basics.qmd text: "2️⃣ No Code" - href: low_code.qmd text: "3️⃣ Low Code" - href: use_case.qmd text: "4️⃣ Anwendungsfall" sidebar: - title: "Start" contents: - href: index.qmd section: "Willkommen👋" contents: - href: 01_setup/agenda.qmd text: "Agenda📅" - section: "Vorbereitung🛠️" href: 01_setup/vorbereitung.qmd contents: - href: 01_setup/erforderlich/google-konto.qmd text: "Google Konto erstellen" - href: 01_setup/erforderlich/colab.qmd text: "Colab nutzen" - href: 01_setup/erforderlich/huggingface.qmd text: "Huggingface Ressourcen" - section: "Optional" href: 01_setup/vorbereitung.html#optional contents: - href: 01_setup/optional/colab-github.qmd text: "Colab & GitHub🤝" - href: 01_setup/optional/quarto-lokal.qmd text: "Hallo Quarto✨" - href: 01_setup/aufbereitung.qmd text: "Aufbereitung🤩" - href: 01_setup/glossar.qmd text: "Glossar" - href: 01_setup/ressourcen.qmd text: "Weitere Ressourcen" - title: "No Code" contents: - href: basics.qmd section: "No Code Übersicht" contents: - section: "PDF📝" href: 02_basics/pdf.qmd contents: - href: 02_basics/pdf/pdf-link-extractor.qmd text: "PDF Sammler🔍" - href: 02_basics/pdf/pdf-grouping.qmd text: "PDFs gruppieren🗂️" - href: 02_basics/app_market/google-play-search.qmd text: "Google Play Search🛒" - section: "Webspider🕸️" href: 02_basics/webspider.qmd contents: - href: 02_basics/webspider/website-url-extractor.qmd text: "URL Extractor" - href: 02_basics/webspider/webspider.qmd text: "Webspider" - title: "Low Code" contents: - section: "Low Code Übersicht" href: low_code.qmd contents: - section: "Kataloge erfassen" href: 03_low_code/catalogue.qmd contents: - href: 03_low_code/catalogue/bookstoscrape.ipynb text: "Bücherliste scrapen📚" - href: 03_low_code/catalogue/quotes_scraper.ipynb text: "Zitate scrapen💬" - href: 03_low_code/app_market_scraping/app_market_scraping.ipynb text: "App Markt analysieren📱" - section: "Video Transkripte" href: 03_low_code/video_transcripts.qmd contents: - href: 03_low_code/video_transcripts/social-media.qmd text: "Hinweise Scraping Social Media⚠️" - href: 03_low_code/video_transcripts/get_videos_for_youtube_channels.ipynb text: "YouTube Channel Videos🎥" - href: 03_low_code/video_transcripts/youtube-transcript-extraction.ipynb text: "YouTube Video Transcripts📝" - title: "Use-Case" contents: - section: "Anwendungsfall Übersicht" href: use_case.qmd contents: - href: 04_use_case/laws/Gesetze_im_Internet_Aktualitätendienst.ipynb text: "Aktualitätendienst Gesetze📜" - href: 04_use_case/jobs/Jobboerse_API.ipynb text: "Jobbörse💼" - href: 04_use_case/forum/buergergeld_forum.ipynb text: "Buergergeld Forum💬" - section: "Anwendungsfall Bonus" contents: - href: 04_use_case_bonus/podcasts/aggregate_podcast_episodes_to_markdown.ipynb 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: theme: cosmo css: styles.css toc: true