{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "Download various data formats from the internet using the Python `requests` library and save them to disk.\n", "\n", "Data formats:\n", " - XML\n", " - CSV\n", " - Image" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import requests\n", "from pathlib import Path\n", "\n", "data_folder = Path('data')\n", "data_folder.mkdir(exist_ok=True)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# XML\n", "# TEI-XML file from the Blotius edition (https://edition.onb.ac.at/blotius)\n", "xml_data = requests.get('https://edition.onb.ac.at/blotius/o:blo.inventar-mz/datastreams/TEI_SOURCE/content')\n", "\n", "with open(data_folder / 'tei-xml_example.xml', 'wb') as file:\n", " file.write(xml_data.content)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# CSV\n", "# Historic postcards metadata sheet\n", "\n", "csv_data = requests.get('https://labs.onb.ac.at/gitlab/labs-team/raw-metadata/-/raw/master/akon_postcards_public_domain.csv.bz2?ref_type=heads&inline=false')\n", "\n", "with open(data_folder / 'csv_example.csv.bz2', 'wb') as file:\n", " file.write(csv_data.content)" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Image\n", "# Stock image from pexels.com\n", "img_data = requests.get('https://images.pexels.com/photos/572056/pexels-photo-572056.jpeg?cs=srgb&dl=pexels-serpstat-572056.jpg&fm=jpg&w=5664&h=3778')\n", "\n", "with open(data_folder / 'image_example.jpg', 'wb') as file:\n", " file.write(img_data.content)" ] } ], "metadata": { "kernelspec": { "display_name": ".venv", "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": "3.11.2" } }, "nbformat": 4, "nbformat_minor": 2 }