From 886018e8f0238cb23d1ff4812b86e5d5492d61cd Mon Sep 17 00:00:00 2001
From: MSI <barik_25@mail.ru>
Date: Fri, 25 Aug 2023 14:55:39 +0600
Subject: [PATCH] Added new_directory

---
 main.py       | 101 ++++++++++++++++++++++++++++++++++++++++++++++++++
 url_finder.py |  39 +++++++++++++++++++
 2 files changed, 140 insertions(+)
 create mode 100644 main.py
 create mode 100644 url_finder.py

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..35df407
--- /dev/null
+++ b/main.py
@@ -0,0 +1,101 @@
+import requests
+from bs4 import BeautifulSoup
+import os
+import time
+import random
+import hashlib
+import threading
+from PIL import Image
+import io
+
+class ImageDownloaderBot:
+    def __init__(self, folder_name="downloaded_images"):
+        self.headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+        }
+        self.folder_name = folder_name
+        self.downloaded_images = set()
+        self.stop_bot = False
+        self.thread = None
+
+    def _get_image_hash(self, content):
+        return hashlib.md5(content).hexdigest()
+
+    def resize_image(self, content, base_width=300):
+        image = Image.open(io.BytesIO(content))
+        w_percent = base_width / float(image.size[0])
+        h_size = int(float(image.size[1]) * float(w_percent))
+        image = image.resize((base_width, h_size), Image.ANTIALIAS)
+        with io.BytesIO() as output:
+            image.save(output, format="JPEG")
+            return output.getvalue()
+
+    def get_images_from_url(self, url):
+        try:
+            response = requests.get(url, headers=self.headers, timeout=10)
+            response.raise_for_status()
+
+            soup = BeautifulSoup(response.content, 'html.parser')
+            img_tags = soup.find_all('img')
+
+            count = 0
+            for img_tag in img_tags:
+                if self.stop_bot:
+                    print("Stopping bot as requested.")
+                    return
+
+                img_url = img_tag.get('src', '')
+                if not img_url or not img_url.startswith(('http:', 'https:')):
+                    continue
+
+                content = requests.get(img_url, headers=self.headers, timeout=10).content
+                img_hash = self._get_image_hash(content)
+
+                if img_hash in self.downloaded_images:
+                    print(f"Skipped downloading duplicate image: {img_url}")
+                    continue
+
+                self.downloaded_images.add(img_hash)
+
+                # Resize the image
+                resized_content = self.resize_image(content)
+                # Create directory based on the domain name
+                directory = os.path.join(self.folder_name, url.split("//")[-1].split("/")[0])
+                if not os.path.exists(directory):
+                    os.makedirs(directory)
+
+                img_name = os.path.join(directory, os.path.basename(img_url))
+                with open(img_name, 'wb') as f:
+                    f.write(resized_content)
+                    count += 1
+
+                time.sleep(random.uniform(1, 3))
+
+            print(f"Downloaded {count} new images from {url}.")
+
+        except requests.RequestException as e:
+            print(f"Error during requests to {url} : {str(e)}")
+        except Exception as e:
+            print(f"Error: {str(e)}")
+
+    def start(self, url):
+        if self.thread and self.thread.is_alive():
+            print("Bot is already running.")
+            return
+
+        self.stop_bot = False
+        self.thread = threading.Thread(target=self.get_images_from_url, args=(url,))
+        self.thread.start()
+
+    def stop(self):
+        self.stop_bot = True
+        if self.thread:
+            self.thread.join()
+
+
+bot = ImageDownloaderBot()
+url = "YOUR_WEBSITE_URL_HERE"
+
+bot.start(url)
+# To stop the bot at any point, you can call:
+# bot.stop()
diff --git a/url_finder.py b/url_finder.py
new file mode 100644
index 0000000..057be9a
--- /dev/null
+++ b/url_finder.py
@@ -0,0 +1,39 @@
+from selenium import webdriver
+from bs4 import BeautifulSoup
+import os
+
+BASE_URL = "https://3ddd.ru/3dmodels/"
+CHROME_DRIVER_PATH = 'C:\\Program Files\\Google\\Chrome\\Application\\chromedriver-win64\\chromedriver.exe'
+
+os.environ["webdriver.chrome.driver"] = CHROME_DRIVER_PATH
+
+def get_item_urls(page_number=1):
+    options = webdriver.ChromeOptions()
+    # options.add_argument('--headless')  # Commented out for now to see the loaded page
+    #options.add_argument('--disable-gpu')  # Disable GPU acceleration, useful for headless
+
+    driver = webdriver.Chrome(options=options)
+    try:
+        driver.get(f"{BASE_URL}?page={page_number}")
+    
+        # Wait for the content to load. You can adjust the sleep time
+        driver.implicitly_wait(10)
+    
+        soup = BeautifulSoup(driver.page_source, 'html.parser')
+        
+        # Debugging prints
+        print(soup.prettify()[:1000])  # Print out first 1000 characters of page source
+        all_links = soup.find_all('a', href=True)
+        print(f"Total 'a' tags found: {len(all_links)}")
+    
+        # Extracting all 'a' tags with the specific pattern
+        urls = ['https://3ddd.ru' + link['href'] for link in all_links if '/3dmodels/show/' in link['href']]
+    finally:
+        driver.quit()
+    
+    return urls
+
+# Example: Get items from the main page
+urls = get_item_urls()
+for url in urls:
+    print(url)