Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 import requests
 from bs4 import BeautifulSoup
 import time
-import os
 import zipfile
 from urllib.parse import urlparse
 import re
@@ -59,24 +58,56 @@ def scrape_kemono(links_text, delay_sec, max_retries):
                 # Parse HTML for Text and Title extraction
                 soup = BeautifulSoup(html_content, 'html.parser')
                 
-                # Extract Title (Kemono specifically uses h1 with class 'post__title')
+                # Check for Cloudflare block
+                page_title = soup.find('title')
+                if page_title and "Just a moment" in page_title.get_text():
+                    extracted_data.append(f"--- BLOCKED BY CLOUDFLARE: {link} (Increase your delay!) ---\n")
+                    continue
+
+                # 1. EXTRACT TITLE (Better Fallbacks)
                 title_tag = soup.find('h1', class_='post__title')
-                title = title_tag.get_text(strip=True) if title_tag else f"Untitled_Post_{i+1}"
+                if title_tag:
+                    title = title_tag.get_text(strip=True)
+                elif page_title:
+                    title = page_title.get_text(strip=True).replace(" | Kemono", "")
+                else:
+                    title = f"Untitled_Post_{i+1}"
                 
-                # Extract Content Text (Kemono uses 'post__content' or 'post__body')
-                content_tag = soup.find('div', class_='post__content')
-                if not content_tag:
-                    content_tag = soup.find('div', class_='post__body')
+                # 2. EXTRACT TEXT CONTENT
+                content_tag = soup.find('div', class_='post__content') or soup.find('div', class_='post__body')
+                text_content = content_tag.get_text(separator='\n', strip=True) if content_tag else ""
                 
-                text_content = content_tag.get_text(separator='\n', strip=True) if content_tag else "[No text content found in this post.]"
+                # 3. EXTRACT ATTACHMENTS & IMAGES
+                media_links = []
+                # Look for attachments
+                attachments = soup.find_all('a', class_='post__attachment-link')
+                for atk in attachments:
+                    href = atk.get('href')
+                    if href:
+                        media_links.append("Attachment: " + (href if href.startswith('http') else f"https://kemono.cr{href}"))
                 
-                # Append formatted data to our combined text string
+                # Look for images inside the post
+                images = soup.find_all('img', class_='post__image')
+                for img in images:
+                    src = img.get('src')
+                    if src:
+                        media_links.append("Image: " + (src if src.startswith('http') else f"https://kemono.cr{src}"))
+                
+                # Build the final text block
                 post_text = f"========================================================================\n"
                 post_text += f"TITLE: {title}\n"
                 post_text += f"URL: {link}\n"
                 post_text += f"========================================================================\n\n"
-                post_text += f"{text_content}\n\n\n"
                 
+                if not text_content and not media_links:
+                    post_text += "[No text or media content found. The post might be empty or locked.]\n\n"
+                else:
+                    if text_content:
+                        post_text += f"--- TEXT ---\n{text_content}\n\n"
+                    if media_links:
+                        post_text += f"--- MEDIA LINKS ---\n" + "\n".join(media_links) + "\n\n"
+                
+                post_text += "\n"
                 extracted_data.append(post_text)
                 
             except Exception as e:
@@ -91,7 +122,7 @@ def scrape_kemono(links_text, delay_sec, max_retries):
 # --- Gradio UI Layout ---
 with gr.Blocks(theme=gr.themes.Soft()) as app:
     gr.Markdown("# 🦊 Kemono.cr Batch Scraper & Extractor")
-    gr.Markdown("Paste a list of links (or raw HTML tags from your `links.txt` file). The scraper will fetch each link, extract the title and text, save the raw HTMLs in a ZIP, and give you a combined TXT document.")
+    gr.Markdown("Paste a list of links (or raw HTML tags from your `links.txt` file). The scraper will fetch each link, extract the title, text, and media links, save the raw HTMLs in a ZIP, and give you a combined TXT document.")
     
     with gr.Row():
         with gr.Column(scale=2):
@@ -102,7 +133,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as app:
             )
             
             with gr.Row():
-                delay_input = gr.Slider(minimum=0, maximum=15, value=2, step=0.5, label="Delay Between Requests (Seconds)")
+                delay_input = gr.Slider(minimum=0, maximum=15, value=2.5, step=0.5, label="Delay Between Requests (Seconds)")
                 retry_input = gr.Slider(minimum=1, maximum=5, value=3, step=1, label="Max Retries per Link")
                 
             start_btn = gr.Button("🚀 Start Extraction", variant="primary")