Sat, Aug 3, 2024, 8:36 AM +03:00

images_scrapper.py

@@ -1,7 +1,21 @@
 import requests
 from bs4 import BeautifulSoup
 import scrapper
-import time
+import os
+
+def download_image(image_url, file_dir):
+    response = requests.get(image_url)
+
+    if response.status_code == 200:
+        directory = os.path.dirname(file_dir)
+        if not os.path.exists(directory):
+            os.makedirs(directory)
+
+        with open(file_dir, "wb") as fp:
+            fp.write(response.content)
+        print("Image downloaded successfully.")
+    else:
+        print(f"Failed to download the image. Status code: {response.status_code}")
 
 titles, engines = scrapper()
 for engine in engines:
@@ -26,4 +40,4 @@
                 if soup.find("table", {"class" : "infobox"}).find("td", {"class": "infobox-image"}).find("img").get("srcset"):
                     if len(soup.find("table", {"class" : "infobox"}).find("td", {"class": "infobox-image"}).find("img").get("srcset").split()) > 2:
                         pic_url = "https:" + str(soup.find("table", {"class" : "infobox"}).find("td", {"class": "infobox-image"}).find("img").get("srcset").split()[2])
-                        print(pic_url)
+                        download_image(pic_url, f"/images/{engine_name}.jpg")