#!/usr/bin/env python

"""
Spider steam boycott group and tally who followed through and who didn't.
"""

import logging
import urllib2
from cStringIO import StringIO
from multiprocessing import Pool
from lxml.html import parse

def glean_games(url):
    logging.debug('Getting %s' % url)
    doc = parse(urllib2.urlopen(url)).getroot()
    game_elements = doc.cssselect('#mainContents h4')
    return [e.text_content() for e in game_elements]

def glean_users(url=None, html=None):
    if html is None:
        logging.debug('Getting %s' % url)
        doc = parse(urllib2.urlopen(url)).getroot()
    else:
        doc = parse(StringIO(html)).getroot()
    user_links = doc.cssselect(
    'a.linkFriend_offline, a.linkFriend_online, a.linkFriend_in-game')
    return [(link.text_content(), link.attrib['href']) for link in user_links]

def spider(url, pool_size=20):
    logging.debug('Getting %s' % url)
    response = urllib2.urlopen(url)
    html = response.read() # Necessary for mulitprocessing, needs to be pickleable
    group_page = parse(StringIO(html)).getroot()
    page_links = group_page.cssselect('.pageLinks a')
    page_count = page_links[-2].attrib['href'].split('=')[-1]
    urls = ['%s?p=%d' % (url, page) for page in xrange(2, int(page_count) + 1)]

    pool = Pool(pool_size)
    results = []
    results.append(pool.apply_async(glean_users, (), {'html': html}))
    results.extend([pool.apply_async(glean_users, (url,)) for url in urls])

    users = []
    for result in results:
        users.extend(result.get())

    logging.info('Found %d users!' % len(users))

    games = []
    for username, url in users:
        games.append((username, pool.apply_async(glean_games, (url + '/games',))))

    for username, result in games:
        games = result.get()
        yield username, games

def main():
    import sys
    logging.basicConfig(stream=sys.stderr, level=logging.DEBUG)
    game = 'Call of Duty: Modern Warfare 2'
    has = []
    has_not = []
    for username, games in spider(
        'http://steamcommunity.com/groups/BOYCOTTMW2/members'):
        if game in games:
            logging.info('%s has %s' % (username, game))
            has.append(username)
        else:
            logging.info('%s has not' % (username))
            has_not.append(username)
    print '%d users have %s and %d do not.' % (len(has), game, len(has_not))

if __name__ == '__main__':
    main()

#!/usr/bin/env python

from mechanize import Browser
from optparse import OptionParser

# Exit statuses recognized by Nagios
UNKNOWN = -1
OK = 0
WARNING = 1
CRITICAL = 2

def open_url(br, url):
    """Use a given mechanize.Browser to open url.

    If an exception is raised, then exit with CRITICAL status for Nagios.
    """
    try:
        response = br.open(url)
    except Exception, e:
        # Catching all exceptions is usually a bad idea.  We want to catch
        # them all to report to Nagios here.
        print 'CRITICAL - Could not reach page at %s: %s' % (url, e)
        raise SystemExit, CRITICAL
    return response

# I'm going to be using optparse.OptionParser from now on.  It makes
# command-line args a breeze.
parser = OptionParser()
parser.add_option('-H', '--hostname', dest='hostname')
parser.add_option('-u', '--username', dest='username')
parser.add_option('-p', '--password', dest='password')
parser.add_option('-r', '--report_url', dest='url',
    help="""Path to report relative to root, like
    /NetPerfMon/Report.asp?Report=Hostname+__+IPs""")
parser.add_option('-v', '--verbose', dest='verbose', action='store_true',
    default=False)
parser.add_option('-q', '--quiet', dest='verbose', action='store_false')

options, args = parser.parse_args()

# Check for required options
for option in ('hostname', 'username', 'password', 'url'):
    if not getattr(options, option):
        print 'CRITICAL - %s not specified' % option.capitalize()
        raise SystemExit, CRITICAL

# Go to the report and get a login page
br = Browser()
report_url = 'https://%s%s' % (options.hostname, options.url)
open_url(br, report_url)
br.select_form('aspnetForm')

# Solarwinds has interesting field names
# Maybe something with asp.net
br['ctl00$ContentPlaceHolder1$Username'] = options.username
br['ctl00$ContentPlaceHolder1$Password'] = options.password

# Attempt to login.  If we can't, tell Nagios.
try:
    report = br.submit()
except Exception, e:
    print 'CRITICAL - Error logging in: e' % e
    raise SystemExit, CRITICAL

report_html = report.read()
# class=Property occurs in every cell in a Solarwinds report.  If it's not
# there, something is wrong.
if 'class=Property' not in report_html:
    print 'CRITICAL - Report at %s is down' % report_url
    raise SystemExit, CRITICAL

# If we got this far, let's tell Nagios the report is okay.
print 'OK - Report at %s is up' % report_url
raise SystemExit, OK

#!/usr/bin/env python

from BeautifulSoup import BeautifulSoup
from mechanize import Browser

br = Browser()
response = br.open('http://tylerlesmann.com/')
soup = BeautifulSoup(response.read())
headers = soup.findAll('div', attrs={'class': 'header'})
headlines = []
for header in headers:
    links = header.findAll('a')
    for link in links:
        headlines.append(link.string)
for headline in headlines:
    print headline

#!/usr/bin/env python

from lxml.html import parse
from mechanize import Browser

br = Browser()
response = br.open('http://tylerlesmann.com/')
doc = parse(response).getroot()
for link in doc.cssselect('div.header a'):
    print link.text_content()