Count Anchor Tags is a small program that counts the number of a tags in an HTML document that is fetched from the web. Also provides the option to write out that fetched document or the list of anchor tags on command.

cats.py

#!/usr/bin/env python
# cats
# Count Anchor Tags
#
# Author:   Benjamin Bengfort <[email protected]>
# Created:  Thu Jun 19 06:34:50 2014 -0400
#
# Copyright (C) 2014 Bengfort.com
# For license information, see LICENSE.txt
#
# ID: cats [] [email protected] $

"""
Count Anchor Tags is a small program that counts the number of a tags in
an HTML document that is fetched from the web. Also provides the option to
write out that fetched document or the list of anchor tags on command.
"""

##########################################################################
## Imports
##########################################################################

import os
import sys
import json
import argparse
import requests

from datetime import datetime
from bs4 import BeautifulSoup, SoupStrainer

##########################################################################
## CATs Class
##########################################################################

class CountAnchorTags(object):

    def __init__(self, url):
        self.url      = url
        self.response = None
        self.soup     = None
        self.elapsed  = None

        # Fetch the URL and parse it
        self.fetch()

    def fetch(self):
        """
        Fetches the URL and parses it with BeautifulSoup
        """
        start         = datetime.now()

        # Fetch
        self.response = requests.get(self.url)
        self.response.raise_for_status()

        # Parse
        strainer      = SoupStrainer('a')
        self.soup     = BeautifulSoup(self.response.content, 'lxml', parse_only=strainer)

        finit         = datetime.now()
        self.elapsed  = finit - start

    def links(self):
        """
        Returns an array with all the anchor tags.
        """
        if self.soup is not None:
            for tag in self.soup.find_all('a'):
                yield tag['href']

    def dump(self, stream, **kwargs):
        """
        Dumps out a JSON array of the links
        """
        data = {
            "url": self.response.url,
            "status_code": self.response.status_code,
            "elapsed": self.elapsed.total_seconds(),
            "redirects": len(self.response.history),
            "count": len(self),
            "links": list(self.links()),
        }
        json.dump(data, stream, **kwargs)

    def __len__(self):
        return len(self.soup.find_all('a'))

##########################################################################
## Main
##########################################################################

def main(*argv):
    kwargs = {
        "description": "Counts the anchor tags on a web page",
        "epilog": "For help, please see Ben",
        "version": "1.0.0"
    }

    parser = argparse.ArgumentParser(**kwargs)
    parser.add_argument('url', nargs=1, type=str, help='The URL to download and count tags on')
    parser.add_argument('-o', '--outpath', metavar='PATH', type=argparse.FileType('w'), default=sys.stdout, help='Dump the results to a JSON file.')

    args   = parser.parse_args()
    cats   = CountAnchorTags(args.url[0])
    cats.dump(args.outpath, indent=4)

if __name__ == '__main__':
    main(*sys.argv)