| import gradio as gr |
| from scraper import crawl |
| import pandas as pd |
|
|
| def run_scraper(url, topic, depth): |
| if not url or not topic: |
| return "Please provide both URL and Topic.", None |
| |
| try: |
| depth = int(depth) |
| except ValueError: |
| return "Depth must be an integer.", None |
| |
| results = crawl(url, topic, depth) |
| |
| if not results: |
| return f"No content found for topic '{topic}' up to depth {depth}.", None |
| |
| |
| formatted_results = [] |
| for res in results: |
| for match in res['matches']: |
| formatted_results.append({ |
| "URL": res['url'], |
| "Matched Content": match |
| }) |
| |
| df = pd.DataFrame(formatted_results) |
| return f"Found {len(formatted_results)} matches across {len(results)} pages.", df |
|
|
| with gr.Blocks(title="Web Content Topic Scraper") as demo: |
| gr.Markdown("# 網站主題內容爬蟲 (Web Content Topic Scraper)") |
| gr.Markdown("輸入目標網址與主題，爬蟲會自動尋找相關內容。") |
| |
| with gr.Row(): |
| with gr.Column(): |
| url_input = gr.Textbox(label="目標網址 (URL)", placeholder="https://www.bbc.com/news") |
| topic_input = gr.Textbox(label="尋找主題 (Topic)", placeholder="technology") |
| depth_input = gr.Slider(minimum=0, maximum=3, step=1, value=1, label="爬取層數 (Depth)") |
| submit_btn = gr.Button("開始搜尋 (Search)", variant="primary") |
| |
| with gr.Column(): |
| status_output = gr.Textbox(label="狀態 (Status)") |
| results_output = gr.Dataframe(label="搜尋結果 (Results)", wrap=True) |
| |
| submit_btn.click( |
| fn=run_scraper, |
| inputs=[url_input, topic_input, depth_input], |
| outputs=[status_output, results_output] |
| ) |
|
|
| if __name__ == "__main__": |
| demo.launch(server_name="0.0.0.0", share=False) |
|
|
