import gradio as gr import requests import pandas as pd from bs4 import BeautifulSoup # Define the sources to scrape RFPs from (Example: Placeholder URL) RFP_SOURCES = [ "https://www.example.com/rfp/environment", "https://www.example.com/rfp/sustainability", "https://www.example.com/rfp/health", "https://www.example.com/rfp/behaviour", "https://www.example.com/rfp/pollution" ] # Domains to filter RFPs by DOMAINS = ["Environment", "Sustainability", "Health", "Behaviour", "Pollution"] # Scraping function def scrape_rfps(domain): rfp_list = [] # Iterate through the sources for url in RFP_SOURCES: if domain.lower() not in url.lower(): continue # Skip irrelevant sources try: response = requests.get(url, timeout=10) response.raise_for_status() soup = BeautifulSoup(response.text, "lxml") # Example scraping logic: Adapt this to the actual RFP website structure rfp_items = soup.find_all("div", class_="rfp-item") for rfp in rfp_items: title = rfp.find("h2").text.strip() if rfp.find("h2") else "N/A" deadline = rfp.find("span", class_="deadline").text.strip() if rfp.find("span", class_="deadline") else "N/A" budget = rfp.find("span", class_="budget").text.strip() if rfp.find("span", class_="budget") else "N/A" geography = rfp.find("span", class_="geography").text.strip() if rfp.find("span", class_="geography") else "N/A" funder = rfp.find("span", class_="funder").text.strip() if rfp.find("span", class_="funder") else "N/A" partner = rfp.find("span", class_="partner").text.strip() if rfp.find("span", class_="partner") else "N/A" summary = rfp.find("p", class_="summary").text.strip() if rfp.find("p", class_="summary") else "N/A" rfp_list.append([title, deadline, budget, geography, funder, partner, summary]) except requests.exceptions.RequestException as e: print(f"Error scraping {url}: {str(e)}") continue # Convert to DataFrame columns = ["Title", "Deadline", "Budget", "Geography", "Funder", "Partner", "Summary"] return pd.DataFrame(rfp_list, columns=columns) if rfp_list else pd.DataFrame(columns=columns) # To-Do List for selected RFPs todo_list = [] # Function to add RFP to to-do list def add_to_todo_list(title, deadline, budget, geography, funder, partner, summary): todo_list.append([title, deadline, budget, geography, funder, partner, summary]) return f"Added '{title}' to your to-do list!" # Function to export the to-do list def export_todo_list(): if not todo_list: return "No items in your to-do list." df = pd.DataFrame(todo_list, columns=["Title", "Deadline", "Budget", "Geography", "Funder", "Partner", "Summary"]) file_path = "/mnt/data/todo_list.xlsx" df.to_excel(file_path, index=False) return file_path # Gradio Interface def display_rfps(domain): df = scrape_rfps(domain) return df with gr.Blocks() as demo: gr.Markdown("## Automated RFP Tracking Tool") gr.Markdown("Select a domain to fetch RFPs.") domain_dropdown = gr.Dropdown(choices=DOMAINS, label="Select a Domain", value="Environment") rfps_output = gr.Dataframe() fetch_button = gr.Button("Fetch RFPs") fetch_button.click(display_rfps, inputs=domain_dropdown, outputs=rfps_output) gr.Markdown("### Add RFPs to To-Do List") title_input = gr.Textbox(label="Title") deadline_input = gr.Textbox(label="Deadline") budget_input = gr.Textbox(label="Budget") geography_input = gr.Textbox(label="Geography") funder_input = gr.Textbox(label="Funder") partner_input = gr.Textbox(label="Partner") summary_input = gr.Textbox(label="Summary") add_button = gr.Button("Add to To-Do List") add_status = gr.Textbox(label="Status") add_button.click(add_to_todo_list, inputs=[title_input, deadline_input, budget_input, geography_input, funder_input, partner_input, summary_input], outputs=add_status) gr.Markdown("### Export To-Do List as Excel") export_button = gr.Button("Export To-Do List") export_status = gr.File() export_button.click(export_todo_list, outputs=export_status) # Launching the app demo.launch(share=True, server_name="0.0.0.0")