Extracts the main Phrack article and writes it to a file for easier printing. (or download the tar of the issue if you are boring; ))

getphrack.py

#!/bin/env python2.7

from BeautifulSoup import BeautifulSoup
import requests
import sys
import re
import os
import argparse


def validateUrl(phrack_url):
    '''
    Prefix with http if missing and check it's in the expected format of
    http://phrack.org/issues/67/9.html
    '''
    if not phrack_url.startswith('htt'):
        phrack_url = 'http://'+phrack_url

    m = re.match('^http(s)?:\/\/phrack\.org\/issues\/(\d)+\/(\d)+\.htm(l)?', phrack_url)
    if m is None:
        print('%s is not a valid URL.' % phrack_url)
        print('Something like phrack.org/issues/43/42.html would be nice')
        sys.exit(1)

    issue_number = m.group(2)
    article_number = m.group(3)
    return phrack_url, issue_number, article_number


def prep_title_for_filename(title, number):
    title = title.replace(' : ', '')
    title = title.replace(' ', '_')
    title = title.replace('/', '')
    return '%02d_%s.txt' % (int(number), title)

def main(url, autofile, outfile=''):
    '''
    Get the requested URL and parse it to extract the article.
    Print to stdout or a file.
    '''
    phrack_url, issue_number, article_number = validateUrl(url)

    content = requests.get(phrack_url)
    if content.status_code != 200:
        print('Didn`t manage to fetch that page: %d' % content.status_code)
        return 1


    soup = BeautifulSoup(content.text)

    article_title = soup.find('div', {'id':'article'})
    article_author = article_title.findNext('div').contents

    out_filename = outfile

    if autofile:
        target_dir = os.path.join(os.getcwd(), 'phrack_'+issue_number)
        try:
            if not os.path.exists(target_dir):
                os.mkdir(target_dir)
        except:
            print "Unable to create directory."
            return 1

        title_filename = prep_title_for_filename(article_title.contents[1].string,
                article_number)

        out_filename = os.path.join(target_dir, title_filename)

    if out_filename:
        try:
            old_stdout = sys.stdout
            sys.stdout = open(out_filename, 'w')
        except IOError as e:
            print('Error opening %s %s' % (out_filename, e))
            return 1

    print('This article was extracted from: %s\n\n' % phrack_url)
    if article_title:
        print(article_title.contents[0].string + article_title.contents[1].string)
    if article_author:
        print(article_author[1].string + article_author[2].string)

    print
    article = soup.find('pre')
    print(article.contents[0])
    sys.stdout.close()
    sys.stdout = old_stdout

    return 0

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='Get a printable Phrack article')

    parser.add_argument('url',
            help='The URL to the Phrack article. eg: http://phrack.org/issues/67/9.html')
    parser.add_argument('-o', '--outfile',
            help='File to write output to. If omitted writes to stdout')
    parser.add_argument('-a', '--autofile', action='store_true',
            help='Filename is title of article and saved to issue number directory.')

    args = parser.parse_args()
    sys.exit(main(args.url, args.autofile, args.outfile))