python_scraping_images.py

# ブログに含まれる画像をクロールするコード
import requests 
from bs4 import BeautifulSoup 

import urllib.request

url = 'https://www.crossroad-tech.com/entry/babylonjs-editor-postprocess'
res = requests.get(url) 
soup = BeautifulSoup(res.text,'html.parser') 

img_tags = soup.find_all("img")
img_urls = []

for img_tag in img_tags:
  url = img_tag.get("src")
  if url != None:
    img_urls.append(url)
    # 今回はこのような画像URLが取得できる
    #image_urls[0]="https://cdn-ak.f.st-hatena.com/images/fotolife/T/Takyu/20251221/20251221073656.jpg" 
    #image_urls[1]="https://cdn-ak.f.st-hatena.com/images/fotolife/T/Takyu/20251221/20251221170649.jpg" 


for img_url in img_urls:
  # "Takyu"以降の文字列を取得
  if "Takyu" in img_url:
    # "Takyu"の位置を見つける
    takyu_index = img_url.find("Takyu")
    # "Takyu"以降の文字列を取得
    filename_part = img_url[takyu_index:]
    # "/"を"_"に変換
    filename = filename_part.replace("/", "_")
    # 保存先のパスを作成
    dst_path = './images/' + filename
    # 画像をダウンロードして保存
    urllib.request.urlretrieve(img_url, dst_path)
    print(f"Downloaded: {filename}")

#実行結果
# $ python3 ./python_scraping_images.py
#Downloaded: Takyu_20251221_20251221073656.jpg
#Downloaded: Takyu_20251221_20251221170649.jpg
#Downloaded: Takyu_20251221_20251221154945.jpg
#Downloaded: Takyu_20251221_20251221160632.jpg
#Downloaded: Takyu_20251221_20251221170340.gif
#Downloaded: Takyu_profile.png?1584799880
#Downloaded: Takyu_20181225_20181225224730.jpg