From a6b691e7db7f6a3267afd431a3a6adb1144bdd8d Mon Sep 17 00:00:00 2001
From: "A. Svensson" <lmasvensson@gmail.com>
Date: Sun, 8 Feb 2015 14:38:02 +0100
Subject: [PATCH] Initial commit.

---
 LICENSE          | 16 +++++++++
 README.md        |  1 +
 requirements.txt |  3 ++
 src/parser.py    | 94 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 114 insertions(+)
 create mode 100644 LICENSE
 create mode 100644 README.md
 create mode 100644 requirements.txt
 create mode 100755 src/parser.py

diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000..079179f
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,16 @@
+The MIT License (MIT)
+Copyright (c) 2015 A. Svensson
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..1333ed7
--- /dev/null
+++ b/README.md
@@ -0,0 +1 @@
+TODO
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..ae46ca1
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,3 @@
+
+requests
+beautifulsoup4
diff --git a/src/parser.py b/src/parser.py
new file mode 100755
index 0000000..3156a9d
--- /dev/null
+++ b/src/parser.py
@@ -0,0 +1,94 @@
+#!/usr/bin/env python
+
+import re
+import logging
+
+import requests
+from bs4 import BeautifulSoup
+
+
+URL = 'http://www.byond.com/games/exadv1/spacestation13'
+PLAYER_COUNT = re.compile('Logged in: (\d+) player')
+
+
+logging.basicConfig(
+    format = '%(asctime)s %(levelname)s %(message)s',
+    level = logging.INFO,
+)
+
+
+class ServerParser(object):
+    def __init__(self):
+        self.url = URL
+
+    def run(self):
+        '''Run the parser and return a neat list of dicts containing server data.'''
+        raw_data = self._download_data()
+        servers = self._parse_data(raw_data)
+        return servers
+
+    def _download_data(self):
+        '''Download raw data, either from local file or a web page.'''
+        logging.info('Downloading data from {} ...'.format(self.url))
+        if self.url.startswith('http://') or self.url.startswith('https://'):
+            raw_data = requests.get(self.url).text.strip()
+        else:
+            # HACK: In case of local testing or debugging, since requests can't
+            # handle local files.
+            logging.debug('Opening local file...')
+            with open(self.url, 'r') as f:
+                raw_data = f.read().strip()
+        return raw_data
+
+    def _parse_data(self, raw_data):
+        '''Parse the raw data and run through all servers.'''
+        logging.info('Parsing raw data...')
+        servers = []
+        soup_data = BeautifulSoup(raw_data)
+        for server_data in soup_data.find_all('div', 'live_game_status'):
+            server = self._parse_server_data(server_data)
+            servers.append(server)
+
+        logging.info('Number of servers parsed: {}'.format(len(servers)))
+        return servers
+
+    def _parse_server_data(self, data):
+        '''Parse the individual parts of each server.'''
+        title = data.find('b').text.strip()
+        game_url = data.find('span', 'smaller').text
+
+        tmp = data.find('a')
+        site_url = None
+        # Default means the server hasn't set a custom site url
+        if tmp and not tmp.text == 'Default':
+            try:
+                site_url = tmp['href']
+                # Handle some funky servers...
+                if site_url == 'http://':
+                    site_url = ''
+            except KeyError:
+                # Sometimes there's a <a> tag without a href attribute
+                pass
+
+        tmp = data.text
+        player_count = 0
+        if tmp.find('No players.') == -1:
+            data = PLAYER_COUNT.search(tmp)
+            player_count = int(data.group(1))
+
+        server = dict(
+            title = title,
+            game_url = game_url,
+            site_url = site_url,
+            player_count = player_count,
+        )
+        return server
+
+
+if __name__ == '__main__':
+    parser = ServerParser()
+    parser.url = './dump.html' # Use a local file instead when testing
+    servers = parser.run()
+    for tmp in servers:
+        print '{}\nPlayers: {}\n'.format(tmp['title'], tmp['player_count'])
+