autoscraper / README.md
samihalawa's picture
Sync changes - automated commit
a9556a5

A newer version of the Gradio SDK is available: 5.35.0

Upgrade
metadata
title: AI Lead Scraper & Email Tool
emoji: 📧
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.4.0
app_file: app.py
pinned: false

AI Lead Scraper & Email Tool

Overview

This tool helps automate lead generation and email outreach by combining the power of AI scraping with email automation. It enables users to extract contact information from websites and automatically send personalized emails to potential leads.

Features

  • AI-Powered Lead Scraping: Extract contact information from websites using advanced AI models.
  • Email Automation: Configure SMTP settings and send personalized emails to leads.
  • Customizable Templates: Create and customize email templates for different outreach campaigns.
  • Batch Sending: Send emails to multiple leads with configurable delays to avoid spam filters.
  • User-Friendly Interface: Easy-to-use Gradio interface with separate tabs for scraping, email settings, and campaign sending.

Setup

  1. Create a .env file in the root directory with your Hugging Face API token:

    HUGGINGFACEHUB_API_TOKEN=your_huggingface_api_token
    

    (You can copy from the provided .env.example file and fill in your token)

  2. Install dependencies:

    pip install -r requirements.txt
    playwright install
    
  3. Run the application:

    python app.py
    

Usage

Lead Scraping

  1. Navigate to the "Lead Scraping" tab
  2. Enter the website URL to scrape for contact information
  3. Adjust the number of leads to extract
  4. Click "Scrape Leads" to start the extraction process

Email Settings

  1. Navigate to the "Email Settings" tab
  2. Configure your SMTP server settings
  3. Create your email template with subject and body
  4. Test your configuration by sending a test email

Send Campaign

  1. Navigate to the "Send Campaign" tab
  2. Set the delay between emails to avoid spam filters
  3. Click "Send Emails to All Leads" to start the campaign

Dependencies

  • gradio==5.4.0
  • langchain_community==0.3.5
  • langchain_huggingface==0.0.2
  • huggingface_hub>=0.19.0
  • python-dotenv==1.0.1
  • scrapegraphai==1.28.0
  • playwright==1.40.0

HuggingFace API Token

This tool requires a HuggingFace API token to access the language models:

  1. Create a free account at HuggingFace
  2. Generate an API token from your account settings
  3. Add the token to your .env file:
    HUGGINGFACEHUB_API_TOKEN=your_huggingface_api_token
    

The application uses the following models:

  • Language model: Qwen/Qwen2.5-72B-Instruct
  • Embeddings model: sentence-transformers/all-MiniLM-l6-v2

Note

This tool uses AI models from Hugging Face for scraping and personalization. You need to obtain an API token from Hugging Face and add it to your .env file for the application to work.

Contributing

Contributions are welcome! Please submit pull requests or open issues to suggest improvements.