This gist is created in response to a request for debugging backlink on a mailing list

backlink.py

import logging
from urllib2 import urlopen, Request
import re
from bs4 import BeautifulSoup as Soup
from optparse import OptionParser
from collections import namedtuple, Mapping
import sys

__author__ = "Supreet Sethi <supreet.sethi@gmail.com>"
__copyright__ = "Copyright (C) 2014 Supreet Sethi"
__license__ = "Public Domain"
__version__ = "1.0"
__doc__ =""" This a backlink checker. It allows mass checking of a backlinked URL"""
log = logging.getLogger('backlink-checker')



def namedtuple_with_defaults(typename, field_names, default_values=[]):
    T = namedtuple(typename, field_names)
    T.__new__.__defaults__ = (None,) * len(T._fields)
    if isinstance(default_values, Mapping):
        prototype = T(**default_values)
    else:
        prototype = T(*default_values)
    T.__new__.__defaults__ = tuple(prototype)
    return T


backlink_data = namedtuple_with_defaults('Backlink', ['url', 'backlink', 'a_links', 'img_links', 'err'], [None, None, [], [], False])


def check_url_backlink_exist(url, backlink, a_flag=True, img_flag=False):
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:22.0) djinn Gecko/20100101 Firefox/22.0'}
        req = Request(url, data=None, headers=headers)
        dtfd = urlopen(req)
    except Exception, e:
        log.warning("URL: %(url)s could not be fetched: error -> %(error)s" %
                    {'url': url,
                     'error': str(e)}
                    )
        dtfd.close()
        return backlink_data(url=url, backlink=backlink, err=True)
    
    resp = dtfd.getcode()
    if resp == 200 and dtfd.info()['Content-type'].startswith('text/html'):
        sp = Soup(dtfd.read())
        a_list, img_list = [], []
        if a_flag == True:
            a_list = sp.findAll('a', href=re.compile('^%s' % backlink))
            a_list = [(a.text, a['href']) for a in a_list]
        if img_flag == True:
            img_list = sp.findAll('img', src=re.compile('^%s' % backlink))
            img_list = [(img['alt'], img['src']) for img in img_list]
        return backlink_data(url=url, backlink=backlink, 
                             a_links=a_list, img_links=img_list)
    else:
        return backlink_data(url=url, backlink=backlink, err=True)

def main():
    usage = "usage: %prog [options] -b http://<url> --url urls.txt -l backlinks.log"
    parser = OptionParser(usage=usage)
    parser.add_option("-u", "--url", dest="url_filename",
                      help="List of URLS to be checked", 
                      metavar="FILE")
    parser.add_option("-l", "--log", dest="log_file",
                      help="Log file where the data will be written. By default writes to /tmp/backlink.log",
                      metavar="FILE", default="/tmp/backlink.log")
    parser.add_option("-b", "--backlink", dest="backlink",
                      help="backlink to be checked",
                      type="str", metavar="URL")
    (options, args) = parser.parse_args(sys.argv)
    if not options.url_filename:
        parser.error("URL file is needed")
    if not options.backlink:
        parser.error("Backlink is needed")

    hdlr = logging.FileHandler(options.log_file)
    formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
    hdlr.setFormatter(formatter)
    log.addHandler(hdlr) 
    log.setLevel(logging.DEBUG)
    try:
        urlfd = open(options.url_filename)
    except Exception, e:
        log.error("URL file is not available %(error)s" % {'error', e})
        sys.exit(1)
    for row in urlfd.readlines():
        row = row.strip()
        # There is no easy way to validate url but to check by sending request
        dt = check_url_backlink_exist(row, options.backlink)
        for text, link in dt.a_links:
            log.info("URL: %s with backlink: %s: Found a tag text: %s with url: %s" % (row, options.backlink, text, link))
        for text, link in dt.img_links:
            log.info("URL: %s with backlink: %s: Found img tag text: %s with url: %s" % (row, options.backlink, text, link))
        



if __name__ == '__main__':
    main()

Thank you Supreet for writing mature code for me :)

Great share! This backlink.py script is very useful for verifying backlinks across multiple URLs, especially for SEO tasks. Using BeautifulSoup and regex to detect anchor and image backlinks helps automate link audits and improve workflow efficiency. For more advanced automation and accuracy, backlink management software can enhance results even further.