{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import os\n", "import requests\n", "from bs4 import BeautifulSoup\n", "from urllib.parse import urljoin\n", "from PIL import Image\n", "from io import BytesIO\n", "\n", "# ウェブページのURL\n", "url = 'https://www.gameleap.com/articles/every-pal-in-palworld-a-complete-paldeck-list'\n", "\n", "# ウェブページからHTMLを取得\n", "response = requests.get(url)\n", "html = response.text\n", "\n", "# BeautifulSoupでHTMLを解析\n", "soup = BeautifulSoup(html, 'html.parser')\n", "\n", "# \"large-section-container\"クラスの子要素にあるすべてのimgタグを検索\n", "image_tags = soup.select('.large-section-container img')\n", "\n", "# 保存先フォルダのパス\n", "folder_path = '../data/every-pal-in-palworld-a-complete-paldeck-list'\n", "\n", "# フォルダが存在しない場合は作成\n", "if not os.path.exists(folder_path):\n", " os.makedirs(folder_path)\n", "\n", "# 画像のダウンロードと保存\n", "for i, img in enumerate(image_tags):\n", " # 画像のURLを取得\n", " img_url = urljoin(url, img['src'])\n", "\n", " # 画像をダウンロード\n", " img_response = requests.get(img_url)\n", " if img_response.status_code == 200:\n", "\n", " file_name = img.get('alt', 'default_name') + '.webp'\n", "\n", " # 画像を開いて保存\n", " image = Image.open(BytesIO(img_response.content))\n", " image.save(os.path.join(folder_path, file_name))\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "til-machine-learning", "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": "3.11.7" } }, "nbformat": 4, "nbformat_minor": 2 }