An efficient Link Validator written in Python using the Python modules Pandas and Requests.

Link_Validator.py

import pandas
import requests
import time
# Custom headers in key value pair
headers = {'user-agent': 'Link-Validator/0.0.1'}
# Create a session
session = requests.Session()
# Throttle requests/ min
throttle = 30
# DataFrame.apply subroutine
def get_url_for_status(row):
    # access global varaiables
    global session, headers, throttle
    # get URL from URL column
    url = row['URL']
    # Handle common Erros
    if url == "":
        return    
    if url.startswith('#'):
        return row.append(pandas.Series(dict([('Request Error', '# Link')])))
    if not url.startswith('http'):
        return row.append(pandas.Series(dict([('Request Error', 'Invalid Link')])))
    # Handle other errors using Try Catch
    try:
        start = time.time()
        # Streaming request: using a 'with' statement to ensure it's always closed
        with session.get(url, headers=headers, stream=True, timeout=30, verify=False) as r:
            # Access data if required, the data is transfered when r.content is accessed
            #output_value = r.content
            final_url = r.url
            code = r.status_code
        stop = time.time()
        print("Status: {0} Time: {1} \nFinal URL: {2}".format(code, (stop-start), final_url))
        # Throttle the requests
        if ((stop-start) < (60/throttle)):
            time.sleep((60/throttle)-(stop-start))
        # Return Status
        return row.append(pandas.Series(dict([('Response Code', code), ('Response Time', (stop-start)), ('Final URL', final_url)])))
    except Exception as e:
        #raise e # Raise exception for debugging
        return row.append(pandas.Series(dict([('Request Error',str(e))])))
# Read URLs from Excel file
df = pandas.read_excel("D:\\Selenium\\Link_Validator.xlsx",sheet_name="Links")
# Call the DataFrame.apply subroutine
df = df.apply(get_url_for_status, axis=1)
# Write status as Excel file
with pandas.ExcelWriter("D:\\Selenium\\Link_Status.xlsx") as writer:
    df.to_excel(writer, sheet_name="Link Status", index=False)