dumpmycode · March 26, 2016 06:09
diff --git a/logpuzzle.py b/logpuzzle.py
 #!/usr/bin/python
 # Copyright 2010 Google Inc.
 # Licensed under the Apache License, Version 2.0
 # http://www.apache.org/licenses/LICENSE-2.0

 # Google's Python Class
 # http://code.google.com/edu/languages/google-python-class/

 import os
 import re
 import sys
 import urllib2
 import time

 """Logpuzzle exercise
 Given an apache logfile, find the puzzle urls and download the images.

 Here's what a puzzle url looks like:
 10.254.254.28 - - [06/Aug/2007:00:13:48 -0700] "GET /~foo/puzzle-bar-aaab.jpg HTTP/1.0" 302 528 "-" "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.6) Gecko/20070725 Firefox/2.0.0.6"
 """

 def read_urls(filename):
    """
    Returns a list of the puzzle urls from the given log file,
    extracting the hostname from the filename itself.
    Screens out duplicate urls and returns the urls sorted into
    increasing order.
    """
    url = []
    base = 'http://code.google.com'
    with open(filename) as fo:
        data = fo.readlines()
    for line in data:
        if 'puzzle' in line:
            url.append('{}{}'.format(base, line.split(' ')[6]))
    url = sorted(set(url), key=lambda x:x[-8:])
    return url

 def download_images(urls, directory):
    x = 0
    imgfn = []
    if not os.path.exists(directory):
        os.makedirs(directory)
    for url in urls:
        filedir = '{}img{}.jpg'.format(directory, x)
        imgfn.append('<img src="./img{}.jpg">'.format(x))
        with open(filedir, 'w') as fobj:
            try:
                print('Retrieving file [{}/{}]:img{}'.format(x, len(urls)-1, x))
                response = urllib2.urlopen(url)
                fobj.write(response.read())
                print('Complete.')
                x += 1
            except urllib2.URLError as e:
                print("[-] Couldn't connect to server")
                print('[-] Error: {}'.format(e))
            except urllib2.HTTPError as e:
                print('[-] HTTP error.')
                print('[-] Error: {}'.format(e))
    with open('{}index.html'.format(directory), 'w') as fobj:
        fobj.write('<verbatim>\n<html>\n<body>\n{}\n</body>\n</html>'.format(''.join(imgfn)))


 def main():
  args = sys.argv[1:]

  if not args:
    print 'usage: [--todir dir] logfile '
    sys.exit(1)
  todir = ''
  if args[0] == '--todir':
    todir = args[1]
    del args[0:2]

  img_urls = read_urls(args[0])

  if todir:
    download_images(img_urls, todir)
  else:
    print '\n'.join(img_urls)

 if __name__ == '__main__':
  main()
	#!/usr/bin/python
	# Copyright 2010 Google Inc.
	# Licensed under the Apache License, Version 2.0
	# http://www.apache.org/licenses/LICENSE-2.0

	# Google's Python Class
	# http://code.google.com/edu/languages/google-python-class/

	import os
	import re
	import sys
	import urllib2
	import time

	"""Logpuzzle exercise
	Given an apache logfile, find the puzzle urls and download the images.

	Here's what a puzzle url looks like:
	10.254.254.28 - - [06/Aug/2007:00:13:48 -0700] "GET /~foo/puzzle-bar-aaab.jpg HTTP/1.0" 302 528 "-" "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.6) Gecko/20070725 Firefox/2.0.0.6"
	"""

	def read_urls(filename):
	"""
	Returns a list of the puzzle urls from the given log file,
	extracting the hostname from the filename itself.
	Screens out duplicate urls and returns the urls sorted into
	increasing order.
	"""
	url = []
	base = 'http://code.google.com'
	with open(filename) as fo:
	data = fo.readlines()
	for line in data:
	if 'puzzle' in line:
	url.append('{}{}'.format(base, line.split(' ')[6]))
	url = sorted(set(url), key=lambda x:x[-8:])
	return url

	def download_images(urls, directory):
	x = 0
	imgfn = []
	if not os.path.exists(directory):
	os.makedirs(directory)
	for url in urls:
	filedir = '{}img{}.jpg'.format(directory, x)
	imgfn.append('<img src="./img{}.jpg">'.format(x))
	with open(filedir, 'w') as fobj:
	try:
	print('Retrieving file [{}/{}]:img{}'.format(x, len(urls)-1, x))
	response = urllib2.urlopen(url)
	fobj.write(response.read())
	print('Complete.')
	x += 1
	except urllib2.URLError as e:
	print("[-] Couldn't connect to server")
	print('[-] Error: {}'.format(e))
	except urllib2.HTTPError as e:
	print('[-] HTTP error.')
	print('[-] Error: {}'.format(e))
	with open('{}index.html'.format(directory), 'w') as fobj:
	fobj.write('<verbatim>\n<html>\n<body>\n{}\n</body>\n</html>'.format(''.join(imgfn)))


	def main():
	args = sys.argv[1:]

	if not args:
	print 'usage: [--todir dir] logfile '
	sys.exit(1)
	todir = ''
	if args[0] == '--todir':
	todir = args[1]
	del args[0:2]

	img_urls = read_urls(args[0])

	if todir:
	download_images(img_urls, todir)
	else:
	print '\n'.join(img_urls)

	if __name__ == '__main__':
	main()