email_scrape.py

import re
import csv
import time
import urllib.request

# Enter the URL you want to start from
url = input("Enter the starting URL: ")

# This is where we store the links we've already visited
visited = set()

# This is where we store the emails we've found
emails = set()

# Let the user know what's going on
print("Scanning for email addresses...")

# We want to keep track of how many links we've visited
link_count = 0
queue = []

# We also want to keep track of how many emails we've found
email_count = 0

# This is a regular expression for finding email addresses
email_regex = re.compile(r"[a-z0-9\.\-\_\+]+@[a-z0-9\-\_]+(\.[a-z0-9\-\_]+){1,}", re.I)

# This is a regular expression for finding links
link_regex = re.compile(r"<a [^>]*href=['\"]([^'\"]+)", re.I)

# This is a regular expression for finding the domain of a link
domain_regex = re.compile(r"^(?:https?:\/\/)?(?:[^@\/\n]+@)?(?:www\.)?([^:\/\n]+)", re.I)

# This is the domain we're interested in
domain = domain_regex.match(url).group(1)

# We use this to keep track of when we should display a status update
last_time = time.time()

# This is the main loop
while True:
    # Try to request the URL
    try:
        # Get the URL's contents
        response = urllib.request.urlopen(url)

        # Convert the response to text
        html = response.read().decode("utf-8")
    except:
        # Something went wrong, so just skip this URL
        print("Error fetching %s" % url)
        break

    # We visited one more link
    link_count += 1

    # Update the user every 10 links
    if link_count % 10 == 0 and time.time() - last_time > 1:
        print("Found %s email addresses in %s links" % (email_count, link_count))
        last_time = time.time()

    # Find all the email addresses in the response
    for match in email_regex.finditer(html):
        # We found one more email address
        email_count += 1

        # Add it to our list
        emails.add(match.group(0))

    # Find all the links in the response
    for match in link_regex.finditer(html):
        # Get the link
        link = match.group(1)

        # If it's not a link to our domain, skip it
        if not domain_regex.match(link):
            continue

        # If we haven't visited it yet, add it to the queue
        if link not in visited:
            # Mark it as visited
            visited.add(link)

            # Add it to the queue
            queue.append(link)

    # If we're out of links, we're done
    if len(queue) == 0:
        break

    # Get the next link in the queue
    url = queue.pop(0)

# Let the user know we're done
print("Done! Found %s email addresses in %s links" % (email_count, link_count))

# Ask the user if they want to save the results
save = input("Do you want to save the results to a CSV file? (y/n) ")

# If they want to save the results
if save.lower() == "y":
    # Get a filename from the user
    filename = input("Enter a filename: ")

    # Open the file for writing
    with open(filename, "w") as file:
        # Create a CSV writer
        writer = csv.writer(file)

        # Write the emails to the CSV file
        for email in emails:
            writer.writerow([email])