XML pretty print and find children.

Posted on December 19, 2019 by Jan

For some reason I always get stuck with finding children in an XML file especially if there are multiple matches with different attributes. Hence this script.

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: xmlPrettyAndUtils.
Description:

just some example xml utilities

'''

import xml.dom.minidom
from xml.etree import cElementTree


def toPrettyXml(root):
    if not type(root).__module__.startswith('lxml'):
        text = cElementTree.tostring(root)
        text = xml.dom.minidom.parseString(text).toprettyxml()
        text = text.replace('\r', '\n')
    else:
        text = cElementTree.tostring(root, pretty_print=True)
    return '\n'.join(line for line in text.split('\n') if line and line.strip())


def xmlFindChildren(xParent, tagName=None, **attributesToMatch):
    iterator = xParent
    if tagName is not None:
        iterator = xParent.findall(tagName)
    children = []
    for xChild in iterator:
        for key, val in attributesToMatch.iteritems():
            if xChild.attrib.get(key, None) != val:
                break
        else:
            # all attributes matched
            children.append(xChild)
    return children

## Example load from file
#filePath = r"C:\xmlfile.xml"
#with open(filePath, "r") as xFile:
#    root = cElementTree.parse(xFile)

## Example load from string
xmlData = '''&lt;?xml version="1.0" encoding="UTF-8"?>&lt;note>&lt;entry attribute="test">This&lt;/entry>  &lt;entry attribute2="test">is&lt;/entry>  &lt;body>Hoofd schouders knieen teen...&lt;/body>&lt;/note>'''
root = cElementTree.fromstring(xmlData)
print "Find child", xmlFindChildren(root,"entry", attribute="test")

print
print "Pretty XML from flat XML"
print "#"*20
print
print toPrettyXml(root)

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: xmlPrettyAndUtils.

Description:

just some example xml utilities

'''

import xml.dom.minidom

from xml.etree import cElementTree

def toPrettyXml(root):

if not type(root).__module__.startswith('lxml'):

text = cElementTree.tostring(root)

text = xml.dom.minidom.parseString(text).toprettyxml()

text = text.replace('\r', '\n')

else:

text = cElementTree.tostring(root, pretty_print=True)

return '\n'.join(line for line in text.split('\n') if line and line.strip())

def xmlFindChildren(xParent, tagName=None, **attributesToMatch):

iterator = xParent

if tagName is not None:

iterator = xParent.findall(tagName)

children = []

for xChild in iterator:

for key, val in attributesToMatch.iteritems():

if xChild.attrib.get(key, None) != val:

break

else:

# all attributes matched

children.append(xChild)

return children

## Example load from file

#filePath = r"C:\xmlfile.xml"

#with open(filePath, "r") as xFile:

# root = cElementTree.parse(xFile)

## Example load from string

xmlData = '''<?xml version="1.0" encoding="UTF-8"?><note><entry attribute="test">This</entry> <entry attribute2="test">is</entry> <body>Hoofd schouders knieen teen...</body></note>'''

root = cElementTree.fromstring(xmlData)

print "Find child", xmlFindChildren(root,"entry", attribute="test")

print "Pretty XML from flat XML"

print "#"*20

print toPrettyXml(root)

Find youtube video title from a url

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: youtubeUrlToName
Description:

Get the name of a video from a youtube link.
it handles the reading of the youtube html page.
its a nice example on how to parse any html page.

Note this might change in the future as youtube tends to change its page quite often.
'''

from HTMLParser import HTMLParser
import urllib

class HtmlYoutubeTitleFinder(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)

        ## Create a variable to hold the title once we found it.
        self.title = None

    def handle_starttag(self, tag, attributes):
        '''
            Here we overwrite the handle_starttag function.
            This function gets called for each tag the html parser finds.

            There are tons of places where you can find the title of a video
            in a youtube html page but this seemd to work well
        :param tag:
        :param attributes:
        :return:
        '''
        if not tag == 'span':
            ## We only want 'span' tags. If its not span. Just return.
            return

        ## Store all attribute name and value pairs.
        ## could also be a dict but doesnt matter much.
        names = []
        values = []
        for name, value in attributes:
            names.append(name )
            values.append(value )

        if 'id' in names:
            id_index = names.index("id")
            if "eow-title" == values[id_index]:
                title_index = names.index("title")
                self.title = values[title_index]
                #print values

    def get_title(self):
        return self.title


titleFinder = HtmlYoutubeTitleFinder()
## Read all the data and make sure its properly decoded.
#Liquid Drum and Bass Mix #60
data = urllib.urlopen("https://www.youtube.com/watch?v=aJoo79OwZEI").read().decode('utf-8')
titleFinder.feed( data )

print titleFinder.get_title()

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: youtubeUrlToName

Description:

Get the name of a video from a youtube link.

it handles the reading of the youtube html page.

its a nice example on how to parse any html page.

Note this might change in the future as youtube tends to change its page quite often.

'''

from HTMLParser import HTMLParser

import urllib

class HtmlYoutubeTitleFinder(HTMLParser):

def __init__(self):

HTMLParser.__init__(self)

## Create a variable to hold the title once we found it.

self.title = None

def handle_starttag(self, tag, attributes):

'''

Here we overwrite the handle_starttag function.

This function gets called for each tag the html parser finds.

There are tons of places where you can find the title of a video

in a youtube html page but this seemd to work well

:param tag:

:param attributes:

:return:

'''

if not tag == 'span':

## We only want 'span' tags. If its not span. Just return.

return

## Store all attribute name and value pairs.

## could also be a dict but doesnt matter much.

names = []

values = []

for name, value in attributes:

names.append(name )

values.append(value )

if 'id' in names:

id_index = names.index("id")

if "eow-title" == values[id_index]:

title_index = names.index("title")

self.title = values[title_index]

#print values

def get_title(self):

return self.title

titleFinder = HtmlYoutubeTitleFinder()

## Read all the data and make sure its properly decoded.

#Liquid Drum and Bass Mix #60

data = urllib.urlopen("https://www.youtube.com/watch?v=aJoo79OwZEI").read().decode('utf-8')

titleFinder.feed( data )

print titleFinder.get_title()

Export save data from a connected xbox one

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: exportXboxSaveDataToDisk
Description:

script that exports the save data from your connected xbox to disk
you do have to be in xbox developer mode I think.
also you need to have the xbox xdk

more info about the command here
https://docs.microsoft.com/en-us/gaming/xbox-live/storage-platform/connected-storage/connected-storage-xb-storage

'''

## Xbox quick save script
import os
import datetime
import subprocess

SCID = "&lt;your personal configuration identifier>"
USER_ACCOUNT = "an@example.com"

def exportSaveGame( savePath ):
    saveBin = r'"C:\Program Files (x86)\Microsoft Durango XDK\bin\xbstorage.exe" '
    command = 'export "{}" /msa:{} /f /scid:{}'.format(savePath, USER_ACCOUNT, SCID)
    print subprocess.check_output(saveBin + command )

## Ask the user for a file name
description = raw_input("Write a filename for the savegame:")

## construct path
baseDirectory = r"C:\saveGames"
fullFileName = "{}_{}_xboxSaveGame.xml".format(description, datetime.datetime.now().date())
fullPath = os.path.join(baseDirectory, fullFileName)

## export the save game
exportSaveGame(fullPath)

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: exportXboxSaveDataToDisk

Description:

script that exports the save data from your connected xbox to disk

you do have to be in xbox developer mode I think.

also you need to have the xbox xdk

more info about the command here

https://docs.microsoft.com/en-us/gaming/xbox-live/storage-platform/connected-storage/connected-storage-xb-storage

'''

## Xbox quick save script

import os

import datetime

import subprocess

SCID = "<your personal configuration identifier>"

USER_ACCOUNT = "an@example.com"

def exportSaveGame( savePath ):

saveBin = r'"C:\Program Files (x86)\Microsoft Durango XDK\bin\xbstorage.exe" '

command = 'export "{}" /msa:{} /f /scid:{}'.format(savePath, USER_ACCOUNT, SCID)

print subprocess.check_output(saveBin + command )

## Ask the user for a file name

description = raw_input("Write a filename for the savegame:")

## construct path

baseDirectory = r"C:\saveGames"

fullFileName = "{}_{}_xboxSaveGame.xml".format(description, datetime.datetime.now().date())

fullPath = os.path.join(baseDirectory, fullFileName)

## export the save game

exportSaveGame(fullPath)

Intercept the stdOut and stdErr to a log file

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: interceptStdOutAndStdErr
Description:

intercept the std out and write it to a log file.
it could cause a bunch of errors if any file operations are called on an std pipe though XD
    need to implement the std pipe functions in the class but you get the idea i hope.

'''
import sys
import tempfile 
import uuid
import time

import os

## Make a temp output folder to keep track of the logs.
TEMP_DIR = os.path.join(tempfile.gettempdir(), "StdOut")
if not os.path.exists(TEMP_DIR):
    os.makedirs(TEMP_DIR)

class stdOverwrite( object ):
    '''
        Should also add a get attr for any unimplemented std pipe functions like all the file functions
    '''
    def __init__( self, stdPipe, pipeName= "_output" ):
        self._terminal = stdPipe 
        unique_filename = str(uuid.uuid4())
        logPath = os.path.join(TEMP_DIR, unique_filename+"_{}.log".format(pipeName))
        self.log = open( logPath , "w")
        print "Saving: ", pipeName, " to: ", logPath

    def write( self, message ):
        self._terminal.write( message ) 
        self.log.write(message) 
        self.log.flush()
    def close( self ):
        self._terminal.close()
        self.log.close()

    def flush(self):
        self._terminal.flush()


sys.stdout = stdOverwrite(sys.stdout, "stdOut")
sys.stderr = stdOverwrite(sys.stderr, "stdErr")



print "漢字カタカナ"
raise Exception("ble")
## this should all have been written to the log files in the temp folder

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: interceptStdOutAndStdErr

Description:

intercept the std out and write it to a log file.

it could cause a bunch of errors if any file operations are called on an std pipe though XD

need to implement the std pipe functions in the class but you get the idea i hope.

'''

import sys

import tempfile

import uuid

import time

import os

## Make a temp output folder to keep track of the logs.

TEMP_DIR = os.path.join(tempfile.gettempdir(), "StdOut")

if not os.path.exists(TEMP_DIR):

os.makedirs(TEMP_DIR)

class stdOverwrite( object ):

'''

Should also add a get attr for any unimplemented std pipe functions like all the file functions

'''

def __init__( self, stdPipe, pipeName= "_output" ):

self._terminal = stdPipe

unique_filename = str(uuid.uuid4())

logPath = os.path.join(TEMP_DIR, unique_filename+"_{}.log".format(pipeName))

self.log = open( logPath , "w")

print "Saving: ", pipeName, " to: ", logPath

def write( self, message ):

self._terminal.write( message )

self.log.write(message)

self.log.flush()

def close( self ):

self._terminal.close()

self.log.close()

def flush(self):

self._terminal.flush()

sys.stdout = stdOverwrite(sys.stdout, "stdOut")

sys.stderr = stdOverwrite(sys.stderr, "stdErr")

print "漢字カタカナ"

raise Exception("ble")

## this should all have been written to the log files in the temp folder

Run a python function daily.

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: daylyRunFunction
Description:

Simple task scheduler to run at a daily interval.

'''

import datetime
import time
import sched

SCHEDULER = sched.scheduler(time.time,time.sleep)
def repeat_action( message,  timing ):
    '''
        Do whatever magic you want to do here :D
    :param message:
    :param timing:
    :return:
    '''

    print "Run forrest run!"

    ## Create the next scheduled event
    run_schedule_daily(repeat_action, *timing)

def run_schedule_daily( function, hours = 0,minutes = 0, seconds = 0 ):
    ## what time of the day do you want to run this
    runTime = datetime.time(hour = hours,
                            minute= minutes,
                            second = seconds)    
    nowPlus = datetime.datetime.combine(datetime.datetime.now(), runTime)
    if nowPlus &lt;= datetime.datetime.now():
        nowPlus = nowPlus + datetime.timedelta(days = 1)
    tTuple = time.mktime(nowPlus.timetuple())
    SCHEDULER.enterabs(tTuple,
                   1,
                   function,
                   ("",(hours,
                        minutes,
                        seconds),))
    
    print "Next run scheduled for: ", nowPlus
                       
run_schedule_daily(repeat_action, hours = 14,minutes =45, seconds = 0)

SCHEDULER.run()

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: daylyRunFunction

Description:

Simple task scheduler to run at a daily interval.

'''

import datetime

import time

import sched

SCHEDULER = sched.scheduler(time.time,time.sleep)

def repeat_action( message, timing ):

'''

Do whatever magic you want to do here :D

:param message:

:param timing:

:return:

'''

print "Run forrest run!"

## Create the next scheduled event

run_schedule_daily(repeat_action, *timing)

def run_schedule_daily( function, hours = 0,minutes = 0, seconds = 0 ):

## what time of the day do you want to run this

runTime = datetime.time(hour = hours,

minute= minutes,

second = seconds)

nowPlus = datetime.datetime.combine(datetime.datetime.now(), runTime)

if nowPlus <= datetime.datetime.now():

nowPlus = nowPlus + datetime.timedelta(days = 1)

tTuple = time.mktime(nowPlus.timetuple())

SCHEDULER.enterabs(tTuple,

function,

("",(hours,

minutes,

seconds),))

print "Next run scheduled for: ", nowPlus

run_schedule_daily(repeat_action, hours = 14,minutes =45, seconds = 0)

SCHEDULER.run()

Get time in iso format in a string.

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: timeInIsoStandardFormat
Description:

    For whatever reason I found it hard to get python to output a timestamp of a continuous string with all info in it.
    Hence making this function. Im sure there should be a better way to do this buuuuttttt this works XD

'''
from datetime import datetime

def get_now_time( ):
    '''
        I think this is called the iso format timestamp.
        I think in python 3 you can do this a lot easier but I keep this as a usefull time manipulation example
        Just prints a timestamp in a neat string with timezone information.
        2019-12-08T09:32:55.423000+09:00
    :return:
    '''

    ## Diff local now and utcnow 
    localnow = datetime.now()
    utcnow = datetime.utcnow()

    # compute the time difference in seconds
    tzd = localnow - utcnow
    secs = tzd.total_seconds()

    # get a positive or negative prefix for the timezone
    prefix = '+'
    if secs &lt; 0:
        prefix = '-'
        secs = abs(secs) ## fix the remaining seconds.

    # print the local time with the difference, correctly formatted
    suffix = "%s%02d:%02d" % (prefix, secs/3600, secs/60%60)
    return "%s%s" % (localnow.isoformat('T'), suffix)

print get_now_time()

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: timeInIsoStandardFormat

Description:

For whatever reason I found it hard to get python to output a timestamp of a continuous string with all info in it.

Hence making this function. Im sure there should be a better way to do this buuuuttttt this works XD

'''

from datetime import datetime

def get_now_time( ):

'''

I think this is called the iso format timestamp.

I think in python 3 you can do this a lot easier but I keep this as a usefull time manipulation example

Just prints a timestamp in a neat string with timezone information.

2019-12-08T09:32:55.423000+09:00

:return:

'''

## Diff local now and utcnow

localnow = datetime.now()

utcnow = datetime.utcnow()

# compute the time difference in seconds

tzd = localnow - utcnow

secs = tzd.total_seconds()

# get a positive or negative prefix for the timezone

prefix = '+'

if secs < 0:

prefix = '-'

secs = abs(secs) ## fix the remaining seconds.

# print the local time with the difference, correctly formatted

suffix = "%s%02d:%02d" % (prefix, secs/3600, secs/60%60)

return "%s%s" % (localnow.isoformat('T'), suffix)

print get_now_time()

Find json section in other text.

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: jsonFromBlob
Description:

simple example on how to read json data that has noise / random data surrounding it.
in a nutshell it just finds everything between { and } at the beginning of a line.


'''


import re


data = """
dsjkfkjdsaf;lkjsadklfjlksadjfklsjdfjlksajfks &lt; random data XD 
{
  "contents": "",
  "file_type": "json",
  "listy_things": [
    {
      "key": "sleutel",
      "value": "gratis"
    }
  ],
  "version": {
    "major_version": 0,
    "minor_version": 1
  }
}
jfkdsjfkdsajfsajlkfdsajfjskfdslkj other random data /o/
{
  "list": [
    "entry"
  ],
}
}
"""
import json
pattern = re.compile(r'{(.+?)\n}\n', flags = re.DOTALL)
for x in pattern.findall(data):
    jsonData = eval("{%s}"%x)
    print json.dumps(jsonData, indent=4)

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: jsonFromBlob

Description:

simple example on how to read json data that has noise / random data surrounding it.

in a nutshell it just finds everything between { and } at the beginning of a line.

'''

import re

data = """

dsjkfkjdsaf;lkjsadklfjlksadjfklsjdfjlksajfks < random data XD

{

"contents": "",

"file_type": "json",

"listy_things": [

{

"key": "sleutel",

"value": "gratis"

}

"version": {

"major_version": 0,

"minor_version": 1

}

jfkdsjfkdsajfsajlkfdsajfjskfdslkj other random data /o/

{

"list": [

"entry"

}

"""

import json

pattern = re.compile(r'{(.+?)\n}\n', flags = re.DOTALL)

for x in pattern.findall(data):

jsonData = eval("{%s}"%x)

print json.dumps(jsonData, indent=4)

Extract paths from a string

Posted on December 19, 2019 by Jan

On occasion i get the request to find a bunch of paths from a blob of text. Hence trying to figure out how to do this with a nice regex function. This is my favorite one so far.

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: pathsFromString
Description:

a regex solution that finds the paths from a string.
pro tip:
    this wonderfull site https://regex101.com
    if you write any regex add "/codegen?language=python"
    this will give you a python generated script.

'''

import re
import os

def extract_paths_from_string( string, requiresExt = False ):
    """
        Returns a list of file paths found in the string
        i.e. 
        sdkjflkjfakjkfjakljf,lasf://sdjkjsdfa/fjskaljf/dfsdf.exe,fdsjfksj,
        returns lasf://sdjkjsdfa/fjskaljf/dfsdf.exe

        whitespace file paths are not supported in this case
    """
    '''
        regex magic:
            [a-zA-Z]   one a,b,c.. character 
            [\:]        a colon 
            (\\|\/)     a backslash or forward slash 
            or
            |\\\\       two backslashes 
            |\/\/)      or two forward slashes 
            [a-zA-Z0-9\/\.\\:]* any a,b,c dot 0 to 9 character but not a colon.  
    '''

    ## Search the string with the provided expression
    regex = r"([a-zA-Z][\:](\\|\/)|\\\\|\/\/)[a-zA-Z0-9_\-\/\.\\:]*"
    matches = re.finditer(regex, string, re.MULTILINE)
    paths = []
    ## if we found any path
    for match in matches:
        path = match.group()
        if requiresExt and os.path.splitext(path)[1]:
            ## If we require an extension and we have an extension, return
            paths.append(path)
        elif not requiresExt:
            ## if we dont reqruire a nextension, return the path
            ## we could do a warning message here saying we found a path but no extension
            paths.append(path)
    return paths

test_str = (u"{'C:/this/is/an/example.tesst':'ble'}json\n"
                "&lt;xml>\\\\test/is/an/example.tesst&lt;html>\n"
                "//test\\is\\an\\example.tesst\n"
                "*otherMagi*//test\\is\\an\\example\\&lt;end> \n\n"
                "whatC:/this/is/an/example.tesst#%@$%@#\n"
                "a\\\\test/is/an/exampl_-0112371987509e.tesst#@&amp;^%$&amp;^%\n"
                "drag//test\\is\\an\\e-xample.tesst$@!$#@$!asdfds\\\\abc\\def g:\\bleee\n"
                "regex//a/nightmare//of\\slashes //a.saaa.;;fdsfws[ewrw")

print extract_paths_from_string( test_str , requiresExt=False)

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: pathsFromString

Description:

a regex solution that finds the paths from a string.

pro tip:

this wonderfull site https://regex101.com

if you write any regex add "/codegen?language=python"

this will give you a python generated script.

'''

import re

import os

def extract_paths_from_string( string, requiresExt = False ):

"""

Returns a list of file paths found in the string

i.e.

sdkjflkjfakjkfjakljf,lasf://sdjkjsdfa/fjskaljf/dfsdf.exe,fdsjfksj,

returns lasf://sdjkjsdfa/fjskaljf/dfsdf.exe

whitespace file paths are not supported in this case

"""

'''

regex magic:

[a-zA-Z] one a,b,c.. character

[\:] a colon

(\\|\/) a backslash or forward slash

|\\\\ two backslashes

|\/\/) or two forward slashes

[a-zA-Z0-9\/\.\\:]* any a,b,c dot 0 to 9 character but not a colon.

'''

## Search the string with the provided expression

regex = r"([a-zA-Z][\:](\\|\/)|\\\\|\/\/)[a-zA-Z0-9_\-\/\.\\:]*"

matches = re.finditer(regex, string, re.MULTILINE)

paths = []

## if we found any path

for match in matches:

path = match.group()

if requiresExt and os.path.splitext(path)[1]:

## If we require an extension and we have an extension, return

paths.append(path)

elif not requiresExt:

## if we dont reqruire a nextension, return the path

## we could do a warning message here saying we found a path but no extension

paths.append(path)

return paths

test_str = (u"{'C:/this/is/an/example.tesst':'ble'}json\n"

"<xml>\\\\test/is/an/example.tesst<html>\n"

"//test\\is\\an\\example.tesst\n"

"*otherMagi*//test\\is\\an\\example\\<end> \n\n"

"whatC:/this/is/an/example.tesst#%@$%@#\n"

"a\\\\test/is/an/exampl_-0112371987509e.tesst#@&^%$&^%\n"

"drag//test\\is\\an\\e-xample.tesst$@!$#@$!asdfds\\\\abc\\def g:\\bleee\n"

"regex//a/nightmare//of\\slashes //a.saaa.;;fdsfws[ewrw")

print extract_paths_from_string( test_str , requiresExt=False)

Catch close console script.

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: catchCloseRequest
Description:

How to handle user closing the command prompt with 
ctrl-c
alt-f4
or pressing the x button of the window.

Also "run a function on exit".

windows only i guess. 
'''

from ctypes import wintypes, WINFUNCTYPE
import signal
import ctypes
import time

MESSAGE_BOX = ctypes.windll.user32.MessageBoxW

def _ctrl_handler(sig):
    """
        Handle a sig event and return 0 to terminate the process.
        Note if there is any bug in here the process will terminate right away.

    """
    try:
        if sig == signal.CTRL_C_EVENT:
            print "User pressed: Ctrl C "
            MESSAGE_BOX(None, u'User pressed ctrl - C', u'User action', 0)
            #print "(╯°□°)╯︵ ┻━┻ ## We dont allow Ctrl C closing. muhuhahahahah"
            #return False
        elif sig == signal.CTRL_BREAK_EVENT:
            print "User pressed: Ctrl break "
            MESSAGE_BOX(None, u'User pressed ctrl - break', u'User action', 0)
        elif sig == signal.SIGINT:
            print "User closed window. (alt-f4, x button) "
            MESSAGE_BOX(None, u'User pressed alt f4 or x button', u'User action', 0)
        else:
            print "Unknown even number: ",sig,dir(signal)
            MESSAGE_BOX(None, u'Not sure what you did but cool :D', u'User action', 0)

        ## Certain things like time.sleep dont work anymore.

        MESSAGE_BOX(None, u'Closing now', u'Closing now', 0)
        ## If we return 0 it continues the close event.
        ## If we return 1 it ignores the event.
    except Exception as e:
        ## Just in case because any error will not show up.
        print e
        time.sleep(10)
    return 0


## This needs to be global. If its not global it gets garbage collected and it wont work.
# Register a function what returns a boolean, and takes a dword(8bit int ?) .
HANDLER_ROUTINE = WINFUNCTYPE(wintypes.BOOL, wintypes.DWORD)
SIGNAL_HANDLER = HANDLER_ROUTINE(_ctrl_handler)

def setup_signal_handling():

    SetConsoleCtrlHandler = ctypes.windll.kernel32.SetConsoleCtrlHandler
    SetConsoleCtrlHandler.argtypes = (HANDLER_ROUTINE, wintypes.BOOL)
    SetConsoleCtrlHandler.restype = wintypes.BOOL

    ## The first argument is the function, the second arument is add(1) or remove (0)
    if not SetConsoleCtrlHandler(SIGNAL_HANDLER, 1):
        print ("Unable to setup handler.")


if __name__ == "__main__":

    setup_signal_handling()
    print "Try closing the window with alt f4 or ctrl c"

    while True:
        time.sleep(0.01)
        pass

    print " end "

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: catchCloseRequest

Description:

How to handle user closing the command prompt with

ctrl-c

alt-f4

or pressing the x button of the window.

Also "run a function on exit".

windows only i guess.

'''

from ctypes import wintypes, WINFUNCTYPE

import signal

import ctypes

import time

MESSAGE_BOX = ctypes.windll.user32.MessageBoxW

def _ctrl_handler(sig):

"""

Handle a sig event and return 0 to terminate the process.

Note if there is any bug in here the process will terminate right away.

"""

try:

if sig == signal.CTRL_C_EVENT:

print "User pressed: Ctrl C "

MESSAGE_BOX(None, u'User pressed ctrl - C', u'User action', 0)

#print "(╯°□°)╯︵ ┻━┻ ## We dont allow Ctrl C closing. muhuhahahahah"

#return False

elif sig == signal.CTRL_BREAK_EVENT:

print "User pressed: Ctrl break "

MESSAGE_BOX(None, u'User pressed ctrl - break', u'User action', 0)

elif sig == signal.SIGINT:

print "User closed window. (alt-f4, x button) "

MESSAGE_BOX(None, u'User pressed alt f4 or x button', u'User action', 0)

else:

print "Unknown even number: ",sig,dir(signal)

MESSAGE_BOX(None, u'Not sure what you did but cool :D', u'User action', 0)

## Certain things like time.sleep dont work anymore.

MESSAGE_BOX(None, u'Closing now', u'Closing now', 0)

## If we return 0 it continues the close event.

## If we return 1 it ignores the event.

except Exception as e:

## Just in case because any error will not show up.

print e

time.sleep(10)

return 0

## This needs to be global. If its not global it gets garbage collected and it wont work.

# Register a function what returns a boolean, and takes a dword(8bit int ?) .

HANDLER_ROUTINE = WINFUNCTYPE(wintypes.BOOL, wintypes.DWORD)

SIGNAL_HANDLER = HANDLER_ROUTINE(_ctrl_handler)

def setup_signal_handling():

SetConsoleCtrlHandler = ctypes.windll.kernel32.SetConsoleCtrlHandler

SetConsoleCtrlHandler.argtypes = (HANDLER_ROUTINE, wintypes.BOOL)

SetConsoleCtrlHandler.restype = wintypes.BOOL

## The first argument is the function, the second arument is add(1) or remove (0)

if not SetConsoleCtrlHandler(SIGNAL_HANDLER, 1):

print ("Unable to setup handler.")

if __name__ == "__main__":

setup_signal_handling()

print "Try closing the window with alt f4 or ctrl c"

while True:

time.sleep(0.01)

pass

print " end "

Run function on script exit.

Posted on December 19, 2019 by Jan

# -*- coding: utf-8 -*-
##  Copyright 2019 Trevor van Hoof and Jan Pijpers.
##  Licensed under the Apache License, Version 2.0
##  Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers
##  See the license file attached or on https://www.janpijpers.com/script-licenses/

'''
Name: functionOnExit
Description:

Run a function on closing a console window.
windows only i guess.

'''


import atexit
import time


def _run_function_on_exit():
    '''
        Function that will be called when the program actually exits.
        This is also called on a ctrl-c event. alt-f4 or x button will skip the raw input, but the function will still be called.
    '''
    print "You are exiting, press enter to exit"
    raw_input()


if __name__ == "__main__":
    ## Register the function to be run when the system exits.
    atexit.register( _run_function_on_exit )

    for x in range(5,0,-1):
        print "Closing in:", x
        time.sleep(1)

# -*- coding: utf-8 -*-

## Licensed under the Apache License, Version 2.0

## Downloaded from https://janpijpers.com or https://gumroad.com/janpijpers

## See the license file attached or on https://www.janpijpers.com/script-licenses/

'''

Name: functionOnExit

Description:

Run a function on closing a console window.

windows only i guess.

'''

import atexit

import time

def _run_function_on_exit():

'''

Function that will be called when the program actually exits.

This is also called on a ctrl-c event. alt-f4 or x button will skip the raw input, but the function will still be called.

Jan Pijpers: Technical Artist

Category Archives: Python

XML pretty print and find children.

Find youtube video title from a url

Export save data from a connected xbox one

Intercept the stdOut and stdErr to a log file

Run a python function daily.

Get time in iso format in a string.

Find json section in other text.

Extract paths from a string

Catch close console script.

Run function on script exit.