Write log_extract.py to extract timestamps as datetime objects

Author: jaf7

days/01-03-datetimes/code/log_example

@@ -0,0 +1,33 @@
+ERROR 2014-07-03T23:24:31 supybot Invalid user dictionary file, resetting to empty.
+ERROR 2014-07-03T23:24:31 supybot Exact error: IOError: [Errno 2] No such file or directory: 'conf/users.conf'
+ERROR 2014-07-03T23:24:31 supybot Invalid channel database, resetting to empty.
+ERROR 2014-07-03T23:24:31 supybot Exact error: IOError: [Errno 2] No such file or directory: 'conf/channels.conf'
+WARNING 2014-07-03T23:24:31 supybot Couldn't open ignore database: [Errno 2] No such file or directory: 'conf/ignores.conf'
+INFO 2014-07-03T23:27:51 supybot Shutdown initiated.
+INFO 2014-07-03T23:27:51 supybot Killing Driver objects.
+INFO 2014-07-03T23:27:51 supybot Killing Irc objects.
+INFO 2014-07-03T23:27:51 supybot Shutdown complete.
+INFO 2014-07-03T23:30:37 supybot Creating new Irc for freenode.
+INFO 2014-07-03T23:30:37 supybot Connecting to irc.freenode.net:8001.
+INFO 2014-07-03T23:30:38 supybot Loading plugins (connecting to freenode).
+INFO 2014-07-03T23:30:46 supybot Server orwell.freenode.net has version ircd-seven-1.1.3
+INFO 2014-07-03T23:30:48 supybot Got end of MOTD from orwell.freenode.net
+INFO 2014-07-03T23:30:54 supybot Join to #timvideos on freenode synced in 2.41 seconds.
+INFO 2014-07-03T23:31:22 supybot Exiting due to Ctrl-C.  If the bot doesn't exit within a few seconds, feel free to press Ctrl-C again to make it exit without flushing its message queues.
+INFO 2014-07-03T23:31:22 supybot Flushers flushed and garbage collected.
+INFO 2014-07-03T23:31:22 supybot Driver for Irc object for freenode dying.
+INFO 2014-07-03T23:31:22 supybot Irc object for freenode dying.
+INFO 2014-07-03T23:31:22 supybot Driver for Irc object for freenode dying.
+WARNING 2014-07-03T23:31:22 supybot Disconnect from irc.freenode.net:8001: error: [Errno 9] Bad file descriptor.
+INFO 2014-07-03T23:31:22 supybot Reconnecting to freenode at 2014-07-03T23:31:32.
+INFO 2014-07-03T23:31:22 supybot Removing driver SocketDriver(Irc object for freenode).
+INFO 2014-07-03T23:31:22 supybot Total uptime: 45 seconds.
+INFO 2014-07-03T23:31:22 supybot Total CPU time taken: 1.12 seconds.
+INFO 2014-07-03T23:31:22 supybot No more Irc objects, exiting.
+INFO 2014-07-03T23:31:22 supybot Shutdown initiated.
+INFO 2014-07-03T23:31:22 supybot Killing Driver objects.
+INFO 2014-07-03T23:31:22 supybot Killing Irc objects.
+INFO 2014-07-03T23:31:22 supybot Writing registry file to planet-news.conf
+INFO 2014-07-03T23:31:22 supybot Finished writing registry file.
+INFO 2014-07-03T23:31:22 supybot Shutdown complete.
+

days/01-03-datetimes/code/log_extract.py

@@ -0,0 +1,53 @@
+'''Extract datetimes from log entries and calculate the time
+between the first and last shutdown events'''
+
+from datetime import datetime
+import os
+import urllib.request
+import re
+
+SHUTDOWN_EVENT = 'Shutdown initiated'
+
+# read in the log file
+logfile = os.path.join('/tmp', 'log')
+urllib.request.urlretrieve('http://bit.ly/2AKSIbf', logfile)
+with open(logfile) as f:
+    loglines = f.readlines()
+
+
+def convert_to_datetime(line):
+    '''TODO 1:
+       Given a log line extract its timestamp and convert it to a datetime
+       object.
+       For example calling the function with:
+       INFO 2014-07-03T23:27:51 supybot Shutdown complete.
+       returns:
+       datetime(2014, 7, 3, 23, 27, 51)'''
+    timestamp = re.findall(r'\d{4}-\d{2}-\w+:\d{2}:\d{2}', line)
+    timestamp_fmt = re.sub('T', ' ', timestamp[0])
+    # print('Found timestamp: ', timestamp_fmt)
+    # print(datetime.strptime(timestamp_fmt, "%Y-%m-%d %H:%M:%S"))
+    d = datetime.strptime(timestamp_fmt, "%Y-%m-%d %H:%M:%S")
+    return d
+
+
+def time_between_shutdowns(loglines):
+    '''TODO 2:
+       Extract shutdown events ("Shutdown initiated") from loglines and
+       calculate the
+       timedelta between the first and last one.
+       Return this datetime.timedelta object.'''
+    lines = []
+    for line in loglines:
+        if 'Shutdown initiated' in line:
+            lines.append(line)
+
+    delta = convert_to_datetime(lines[len(lines)-1]) - convert_to_datetime(lines[0])
+    # print(delta)
+    return delta
+
+
+for line in loglines:
+    convert_to_datetime(line)
+
+time_between_shutdowns(loglines)