Automation & Bots | VoidX Academy

Build With Me: News Scraper & Digest

Build With Me 03

The Daily Briefing Pipeline

Today we are building an end-to-end data pipeline. We will scrape top headlines from HackerNews, summarize them using an LLM API, and automatically dispatch a formatted HTML email digest to our subscribers.

Step 1: Extract & Transform

import requests
from bs4 import BeautifulSoup

def scrape_headlines():
    print("Fetching headlines...")
    url = "https://news.ycombinator.com/"
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    
    articles = []
    # Find the title rows
    for item in soup.find_all('tr', class_='athing')[:5]: # Get top 5
        title_element = item.find('span', class_='titleline').find('a')
        title = title_element.text
        link = title_element['href']
        articles.append({'title': title, 'link': link})
        
    return articles

Step 2: Generate the Digest & Load (Email)

import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart

def send_digest(articles):
    print("Formatting digest...")
    
    html_content = "Your Daily Tech Briefing
"
    for article in articles:
        html_content += f"{article['title']}"
    html_content += ""
    
    # Email Setup
    msg = MIMEMultipart()
    msg['Subject'] = "Daily HackerNews Digest"
    msg['From'] = "bot@voidxhq.com"
    msg['To'] = "subscriber@example.com"
    
    msg.attach(MIMEText(html_content, 'html'))
    
    print("Connecting to SMTP server...")
    # Example using Mailtrap or standard SMTP
    # with smtplib.SMTP('smtp.mailtrap.io', 2525) as server:
    #     server.login("user", "password")
    #     server.send_message(msg)
        
    print("Digest successfully delivered!")

# Run the pipeline
news = scrape_headlines()
send_digest(news)

Build With Me: News Scraper & Digest

Build With Me 03

The Daily Briefing Pipeline

Step 1: Extract & Transform

import requests
from bs4 import BeautifulSoup

def scrape_headlines():
    print("Fetching headlines...")
    url = "https://news.ycombinator.com/"
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    
    articles = []
    # Find the title rows
    for item in soup.find_all('tr', class_='athing')[:5]: # Get top 5
        title_element = item.find('span', class_='titleline').find('a')
        title = title_element.text
        link = title_element['href']
        articles.append({'title': title, 'link': link})
        
    return articles

Step 2: Generate the Digest & Load (Email)

import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart

def send_digest(articles):
    print("Formatting digest...")
    
    html_content = "Your Daily Tech Briefing
"
    for article in articles:
        html_content += f"{article['title']}"
    html_content += ""
    
    # Email Setup
    msg = MIMEMultipart()
    msg['Subject'] = "Daily HackerNews Digest"
    msg['From'] = "bot@voidxhq.com"
    msg['To'] = "subscriber@example.com"
    
    msg.attach(MIMEText(html_content, 'html'))
    
    print("Connecting to SMTP server...")
    # Example using Mailtrap or standard SMTP
    # with smtplib.SMTP('smtp.mailtrap.io', 2525) as server:
    #     server.login("user", "password")
    #     server.send_message(msg)
        
    print("Digest successfully delivered!")

# Run the pipeline
news = scrape_headlines()
send_digest(news)

Build With Me: News Scraper & Digest

The Daily Briefing Pipeline

Step 1: Extract & Transform

Step 2: Generate the Digest & Load (Email)

Your Daily Tech Briefing

Knowledge Check

Build With Me: News Scraper & Digest

The Daily Briefing Pipeline

Step 1: Extract & Transform

Step 2: Generate the Digest & Load (Email)

Your Daily Tech Briefing

Knowledge Check