Rewrite Metadata Validator/SoC 2008/IRC Scanner - Revision history

Robert Gust‐Bardon: Python 2.6 and Python 3.1 translation

2010-04-19T21:12:58Z

Python 2.6 and Python 3.1 translation

Hdworak: Syntax highlighting

2008-06-16T08:02:29Z

Syntax highlighting

Hdworak: Initial writing

2008-06-15T15:30:13Z

Initial writing

New page

If one wants to search for his or her activity at [[IRC|the IRC channel of Creative Commons]], he or she can use [http://www.google.com/search?&q=john+site%3Ahttp%3A%2F%2Fmirrors.creativecommons.org%2Firc%2Fcc%2F Google] or the following public domain script written in PHP 5:
<pre><?php

$nick = 'john';
$path = 'http://mirrors.creativecommons.org/irc/cc/';
preg_match_all('/%23cc\.'.date('Y').'\-\d\d\-\d\d\.log\.html/', file_get_contents($path), $matches);
$irrelevant = array();
if (file_exists('irrelevant.txt')) {
$irrelevant = unserialize(file_get_contents('irrelevant.txt'));
}
foreach ($matches[0] as $url) {
if (file_exists('relevant/'.($filename = str_replace('%23', '', $url)))
|| in_array($filename, $irrelevant)) {
echo 'Skipped ', $filename, PHP_EOL;
continue;
}
$contents = file_get_contents($path.$url);
if (!strstr($contents, $nick.'</th><td class="text"')) {
echo 'Irrelevant ', $filename, PHP_EOL;
$irrelevant[] = $filename;
continue;
}
file_put_contents('relevant/'.$filename, $contents);
echo 'Downloaded ', $filename, PHP_EOL;
}
file_put_contents('irrelevant.txt', serialize($irrelevant));
echo 'Saved irrelevant.txt', PHP_EOL;</pre>
Please note that the herewith enclosed script searches the logs saved the current year. All relevant logs are downloaded to the local machine.

← Older revision		Revision as of 21:12, 19 April 2010
Line 27:		Line 27:
	echo 'Saved irrelevant.txt', PHP_EOL;</source>		echo 'Saved irrelevant.txt', PHP_EOL;</source>
	Please note that the herewith enclosed script searches the logs saved the current year. All relevant logs are downloaded to the local machine.		Please note that the herewith enclosed script searches the logs saved the current year. All relevant logs are downloaded to the local machine.
		+
		+	What follows is the above program translated into Python 2.6 and Python 3.1.
		+	<source lang="python">#!/usr/bin/env python
		+	# -- coding: utf-8 --
		+
		+	import datetime
		+	import os
		+	import pickle
		+	import re
		+	try:
		+	import urllib.request as connection
		+	except ImportError:
		+	import urllib as connection
		+
		+	nick = 'john'
		+	path = 'http://mirrors.creativecommons.org/irc/cc/'
		+	irrelevant = []
		+	if os.path.exists('irrelevant.txt'):
		+	f = open('irrelevant.txt', 'r')
		+	irrelevant = pickle.load(f)
		+	f.close()
		+	conn = connection.urlopen(path)
		+	index = conn.read().decode('utf-8', 'ignore')
		+	conn.close()
		+	if not os.path.isdir('relevant'):
		+	os.mkdir('relevant')
		+	for url in re.findall('%23cc\.{0}\-\d\d\-\d\d\.log\.html'.\
		+	format(datetime.date.today().year), index):
		+	filename, contents = url.replace('%23', ''), ''
		+	if os.path.exists('relevant/{0}'.format(filename)) or \
		+	filename in irrelevant:
		+	print('Skipped {0}'.format(filename))
		+	continue
		+	conn = connection.urlopen('{0}{1}'.format(path, url))
		+	contents = conn.read().decode('utf-8', 'ignore')
		+	conn.close()
		+	if contents.find('{0}</th><td class="text"'.format(nick)) == -1:
		+	print('Irrelevant {0}'.format(filename))
		+	irrelevant.append(filename)
		+	continue
		+	f = open('relevant/{0}'.format(filename), 'w')
		+	f.write(str(contents.encode('ascii', 'xmlcharrefreplace')))
		+	f.close()
		+	print('Downloaded {0}'.format(filename))
		+	f = open('irrelevant.txt', 'w+')
		+	pickle.dump(irrelevant, f)
		+	f.close()
		+	print('Saved irrelevant.txt')</source>

@@ Line 1: / Line 1: @@
 If one wants to search for his or her activity at [[IRC|the IRC channel of Creative Commons]], he or she can use [http://www.google.com/search?&q=john+site%3Ahttp%3A%2F%2Fmirrors.creativecommons.org%2Firc%2Fcc%2F Google] or the following public domain script written in PHP 5:
-<pre><?php
+<source lang="php"><?php
 $nick = 'john';
@@ Line 25: / Line 25: @@
+}
 file_put_contents('irrelevant.txt', serialize($irrelevant));
-echo 'Saved irrelevant.txt', PHP_EOL;</pre>
+echo 'Saved irrelevant.txt', PHP_EOL;</source>
 Please note that the herewith enclosed script searches the logs saved the current year. All relevant logs are downloaded to the local machine.