Develop Reference

ValueError: substring not found on lip reading code

This is what I have gotten while trying to run step 3 of this source code:
https://github.com/carykh/lazykh
Error:
Traceback (most recent call last):
File "C:\Users\User\Desktop\lazykh-main\code\scheduler.py", line 93, in
OS_nextIndex = originalScript.index(wordString,OS_IndexAt)+len(wordString)
ValueError: substring not found
Code:
import argparse
import os.path
import json
import numpy as np
import random
def addPhoneme(p, t):
global prevPhoneme
global f
if p != prevPhoneme:
strings[4] += (str.format('{0:.3f}', t)+",phoneme,"+p+"\n")
prevPhoneme = p
def pickNewPose(t):
global pose
global prevPose
global POSE_COUNT
global prevPhoneme
global f
newPose = -1
while newPose == -1 or newPose == pose or newPose == prevPose:
newPose = int(random.random()*POSE_COUNT)
prevPose = pose
pose = newPose
strings[3] += (str.format('{0:.3f}', t)+",pose,"+str(pose)+"\n")
prevPhoneme = "na"
strings = [""]*5
POSE_COUNT = 5
emotions = {}
emotions["explain"] = 0
emotions["happy"] = 1
emotions["sad"] = 2
emotions["angry"] = 3
emotions["confused"] = 4
emotions["rq"] = 5
mouthList = [["aa","a"],["ae","a"],["ah","a"],["ao","a"],["aw","au"],
["ay","ay"],["b","m"],["ch","t"],["d","t"],["dh","t"],
["eh","a"],["er","u"],["ey","ay"],["f","f"],["g","t"],
["hh","y"],["ih","a"],["iy","ay"],["jh","t"],["k","t"],
["l","y"],["m","m"],["n","t"],["ng","t"],["ow","au"],
["oy","ua"],["p","m"],["r","u"],["s","t"],["sh","t"],
["t","t"],["th","t"],["uh","u"],["uw","u"],["v","f"],
["w","u"],["y","y"],["z","t"],["zh","t"],
["oov","m"]] # For unknown phonemes, the stick figure will just have a closed mouth ("mmm")
mouths = {}
for x in mouthList:
mouths[x[0]] = x[1]
ENDING_PHONEME = "m"
STOPPERS = [",",";",".",":","!","?"]
parser = argparse.ArgumentParser(description='blah')
parser.add_argument('--input_file', type=str, help='the script')
args = parser.parse_args()
INPUT_FILE = args.input_file
f = open(INPUT_FILE+".txt","r+")
originalScript = f.read()
f.close()
f = open(INPUT_FILE+".json","r+")
fileData = f.read()
f.close()
data = json.loads(fileData)
WORD_COUNT = len(data['words'])
pose = -1
prevPose = -1
prevPhoneme = "na"
emotion = "0"
pararaph = 0
image = 0
OS_IndexAt = 0
pickNewPose(0)
strings[1] += "0,emotion,0\n"
strings[0] += "0,paragraph,0\n"
strings[2] += "0,image,0\n"
strings[4] += "0,phoneme,m\n"
for i in range(WORD_COUNT):
word = data['words'][i]
if "start" not in word:
continue
wordString = word["word"]
timeStart = word["start"]
OS_nextIndex = originalScript.index(wordString,OS_IndexAt)+len(wordString)
if "<" in originalScript[OS_IndexAt:]:
tagStart = originalScript.index("<",OS_IndexAt)
tagEnd = originalScript.index(">",OS_IndexAt)
if OS_nextIndex > tagStart and tagEnd >= OS_nextIndex:
OS_nextIndex = originalScript.index(wordString,tagEnd)+len(wordString)
nextDigest = originalScript[OS_IndexAt:OS_nextIndex]
if "\n" in nextDigest and data['words'][i-1]['case'] != 'not-found-in-audio' and (prevPhoneme == "a" or prevPhoneme == "f" or prevPhoneme == "u" or prevPhoneme == "y"):
addPhoneme("m", data['words'][i-1]["end"])
"""print(wordString)
print(str(OS_IndexAt)+", "+str(OS_nextIndex))
print(nextDigest)
print("")"""
pickedPose = False
for stopper in STOPPERS:
if stopper in nextDigest:
pickNewPose(timeStart)
pickedPose = True
if "<" in nextDigest:
leftIndex = nextDigest.index("<")+1
rightIndex = nextDigest.index(">")
emotion = emotions[nextDigest[leftIndex:rightIndex]]
strings[1] += (str.format('{0:.3f}', timeStart)+",emotion,"+str(emotion)+"\n")
prevPhoneme = "na"
if "\n\n" in nextDigest:
pararaph += 1
image += 1 # The line of the script advances 2 lines whenever we hit a /n/n.
strings[0] += (str.format('{0:.3f}', timeStart)+",paragraph,"+str(pararaph)+"\n")
prevPhoneme = "na"
if "\n" in nextDigest:
image += 1
strings[2] += (str.format('{0:.3f}', timeStart)+",image,"+str(image)+"\n")
prevPhoneme = "na"
if not pickedPose:
pickNewPose(timeStart) # A new image means we also need to have a new pose
phones = word["phones"]
timeAt = timeStart
for phone in phones:
timeAt += phone["duration"]
phoneString = phone["phone"]
if phoneString == "sil":
truePhone = "m"
else:
truePhone = mouths[phoneString[:phoneString.index("_")]]
if len(truePhone) == 2:
addPhoneme(truePhone[0], timeAt-phone["duration"])
addPhoneme(truePhone[1], timeAt-phone["duration"]*0.5)
else:
addPhoneme(truePhone, timeAt-phone["duration"])
OS_IndexAt = OS_nextIndex
f = open(INPUT_FILE+"_schedule.csv","w+")
for i in range(len(strings)):
f.write(strings[i])
if i < len(strings)-1:
f.write("SECTION\n")
f.flush()
f.close()
print(f"Done creating schedule for {INPUT_FILE}.")

The
ValueError: substring not found
occurs when you try to find the index of a substring in a string which does not contain it in the specified (or default) section, using the index function.
The index method takes 3 parameters:
value
start
end
and it searches for the value between start and end.
So, the error occurred because the substring was not found in the section where it was searched for. The line of
OS_nextIndex = originalScript.index(wordString,tagEnd)+len(wordString)
searches for wordString, starting from tagEnd and searches for the likes of
<span>yourwordstring</span>
, but in your case it was not found. You can do one of the following to solve the issue:
you can fix your input if it should always have a match for the search
you can handle the error when the index throws the error
you can use find instead, see https://bobbyhadz.com/blog/python-valueerror-substring-not-found
Note that find also has three parameters, as you can read from https://www.w3schools.com/python/ref_string_find.asp

Python - Write a new row for each list data under same header into csv

I have a text file, 'student.txt'. Some keys have multiple values. I only want data that is tied to the name, and the sibling & hobby values below that name.
'student.txt'
ignore me
name-> Alice
name-> Sam
sibling-> Kate,
unwanted
sibling-> Luke,
hobby_1-> football
hobby_2-> games
name-> Ramsay
hobby_1-> dance
unwanted data
hobby_2-> swimming
hobby_3-> jogging
ignore data
Code I've done:
file = open("student.txt", "r")
with open("student.csv", "w") as writer:
main_dict = {}
student_dict = {"Siblings": "N/A", "Hobbies": "N/A"}
sibling_list = []
hobby_list = []
flag = True
writer.write ('name,siblings,hobbies\n')
header = 'Name,Siblings,Hobbies'.split(',')
sib_str = ''
hob_str =''
for eachline in file:
try:
key, value = eachline.split("-> ")
value = value.strip(",\n")
if flag:
if key == "name":
print (key,value)
if len(sibling_list) > 0:
main_dict[name]["Siblings"] = sib_str
#print (main_dict)
if len(hobby_list) > 0:
main_dict[name]["Hobbies"] = hob_str
sibling_list = []
hobby_list = []
name = value
main_dict[name] = student_dict.copy()
main_dict[name]["Name"] = name
elif key == "sibling":
sibling_list.append(value)
sib_str= ' '.join(sibling_list).replace(' ', '\n')
elif key.startswith("hobby"):
hobby_list.append(value)
hob_str = ' '.join(hobby_list)
if len(sibling_list) > 0:
main_dict[name]["Siblings"] = sib_str
if len(hobby_list) > 0:
main_dict[name]["Hobbies"] = hob_str
if 'name' in eachline:
if 'name' in eachline:
flag = True
else:
flag = False
except:
pass
for eachname in main_dict.keys():
for eachkey in header:
writer.write(str(main_dict[eachname][eachkey]))
writer.write (',')
if 'Hobbies' in eachkey:
writer.write ('\n')
CSV Output from Code above:
Expected CSV Output:
P.S: I can't seem to figure out how to not forgo the try/pass. As some lines (without '->') are unwanted, and I can't use the eachline.split("-> "). Would appreciate help on this too.
Thanks so much!

The code below gives the csv file which you can import in your Excel and it will be in exact format you are expecting.
You can use something like
if "->" not in line:
continue
To skip lines that don't contain "->" values, see in the code below:
import csv
file = open("student.txt", "r")
students = {}
name = ""
for line in file:
if "->" not in line:
continue
line = line.strip(",\n")
line = line.replace(" ", "")
key, value = line.split("->")
if key == "name":
name = value
students[name] = {}
students[name]["siblings"] = []
students[name]["hobbies"] = []
else:
if "sibling" in key:
students[name]["siblings"].append(value)
elif "hobby" in key:
students[name]["hobbies"].append(value)
#print(students)
csvlines = []
for student in students:
name = student
hobbies = students[name]["hobbies"]
siblings = students[name]["siblings"]
maxlength = 0
if len(hobbies) > len(siblings) :
maxlength = len(hobbies)
else:
maxlength = len(siblings)
if maxlength == 0:
csvlines.append([name, "N/A", "N/A"])
continue
for i in range(maxlength):
if i < len(siblings):
siblingvalue = siblings[i]
elif i == len(siblings):
siblingvalue = "N/A"
else:
siblingvalue = ""
if i < len(hobbies):
hobbyvalue = hobbies[i]
elif i == len(siblings):
hobbyvalue = "N/A"
else:
hobbyvalue = ""
if i == 0:
csvlines.append([name, siblingvalue, hobbyvalue])
else:
csvlines.append(["", siblingvalue, hobbyvalue])
print(csvlines)
fields = ["name", "siblings", "hobbies"]
with open("students.csv", 'w') as csvfile:
# creating a csv writer object
csvwriter = csv.writer(csvfile)
# writing the fields
csvwriter.writerow(fields)
# writing the data rows
csvwriter.writerows(csvlines)

why it say "the action cannot be completed because the file is open in python“？

def main_loop():
global errname, errtime, error_detail, conclusion
error_detail = ""
facts_all = {}
facts = []
buffer = 0
current_time = datetime.now()
while os.path.exists("C:\Winusr"):
print(paths["wintrace"])
try:
start_point = 0
old_size = os.path.getsize(paths["wintrace"])
while os.path.getsize(paths["wintrace"])>= old_size:
#fo = open(paths["wintrace"], "rb")
#fo.seek(start_point,1)
shutil.copyfile(paths["wintrace"], "C:\Winusr\wintrace1.log")
fo = open("C:\Winusr\wintrace1.log", "rb")
fo.seek(start_point, 1)
errtime = datetime(1900, 1, 1)
old_size = os.path.getsize(paths["wintrace"])
#start from here
for line in fo.readlines():
line = str(line.decode('ISO-8859-1'))
print(line)
if fnmatch.fnmatch(line, "*START DUMP LOG BUFFER*"):
buffer = 1
if fnmatch.fnmatch(line, "*END DUMP LOG BUFFER*"):
buffer = 0
if buffer == 1:
continue
facts_all = collect_facts(line,facts_all,key_string,key_value_dic)
for pattern in error_detect:
if fnmatch.fnmatch(line, pattern):
try:
err_type = df[df["Error Detect Keyword"] == pattern]["Err Type"].to_string(index=False).lstrip()
errname = df[df["Err Type"] == err_type]["Error Name"].tolist()[0].lstrip()
errtime = datetime.strptime(
datetime.fromtimestamp(os.path.getmtime(paths["wintrace"])).strftime("%Y-%m-%d") + " " + line[:8], "%Y-%m-%d %H:%M:%S") #"%d-%b-%Y %H:%M:%S"
#errtime = datetime.fromtimestamp(os.path.getmtime(paths["wintrace"])).strftime("%Y-%m-%d") + " " + line[:8]
#errtime = errtime.strftime('%Y-%m-%d %H:%M:%S')
product = re.findall(r"[/](.+?)[.]", paths["cur"])
product = product[0].split("/")[-1]
tester = tester_name(paths["cur"])
if len(facts_all) != 0:
facts.append(errname)
#idex = 9999
for fact, line in facts_all.items():
if fact in dic1[errname]:
error_detail = error_detail + line + '\n'
facts.append(fact)
print("err_detail1", error_detail)
if len(facts) != 1:
facts = list(set(facts))
conclusion = inference_engine(facts)
print("errtime", errtime)
print("current_time", current_time)
if conclusion != "cannot find solution for this error" and errtime > current_time:
solutions = sop2(errlist, errname, conclusion)
row = recording(tester, product, errname, errtime, error_detail, conclusion)
print("gg pop out GUI!!!")
#send_email(errname, errtime, tester, error_detail)
GUI(errname, errtime, error_detail, conclusion, solutions, row)
current_time = datetime.now()
workbook = xlrd.open_workbook(r"G:\expert system data\Machine Database.xls")
workbook1 = copy(workbook)
ws1 = workbook1.get_sheet(0)
style = xlwt.XFStyle()
style.num_format_str = 'yyyy-mm-dd hh:mm:ss'
ws1.write(row, 8, current_time, style)
workbook1.save(r"G:\expert system data\Machine Database.xls")
error_detail = ""
facts_all = {}
facts = []
error_detail = ""
facts_all = {}
facts = []
except:
continue
start_point = fo.tell()
fo.close()
except:
continue
else:
main_loop()
the paths["wintrace"] is ""C:\Winusr\Wintrace.log", i dont want it is open cause sometimes need to change its name or delete, i copy this file and open the copied one, but it still show it is open, can u help me check where it is opened? besides, i use "filepath = tkinter.filedialog.askopenfilename()", but dont think it will open the wintrace file.the error screenshot

fastest way to check a .rar file password - other than rarfile extractall

So i have written a little .rar password "cracker" based on tutorials, using the code underneath. It works fine, but is very slow when the file size is big. The best reason i could find is, that ever so often when you put in a wrong password, it extracts the whole file, before refusing the password. With small files that is not a big problem, but with big files it slows the process a lot.
Is there a way to just check a hashed version of the password against a iterated hash?
import itertools
import rarfile
import time
rarfile.UNRAR_TOOL = "path"
rar = rarfile.RarFile("path")
done = False
n = 0
inputList = ["A","B","1","2"]
class h():
startword = ""
rep = 1
start = 0
itrTot = 0
f = open("save.txt")
for x,each in enumerate(f):
if x == 0:
h.rep = int(each)
else:
h.start = int(each)-3
f.close()
if h.start < 0:
h.start = 0
h.itrTot = len(inputList)**h.rep
def pw_guess():
res = itertools.product(inputList, repeat=h.rep)
for guess in res:
yield guess
start_time = time.time()
while True:
guess_generator = pw_guess()
for guess in guess_generator:
n += 1
if h.startword == "":
h.startword = guess
else:
if guess == h.startword:
h.rep += 1
n = 0
h.itrTot = len(inputList)**h.rep
h.start = 0
print("next rotation, itr rep: "+str(h.rep))
h.startword = ""
break
if n < h.start:
continue
txt = f"({n}/{h.itrTot}, {round((100/h.itrTot)*n,2)}%) - {h.rep}: {''.join(guess)}"
print(txt)
try:
rar.extractall(path="path",members=None,pwd=''.join(guess))
print("Pass found!")
print(str(n) + " - " + str(h.rep) + ": " + str(''.join(guess)))
done = True
txt2 = f"({n}/{h.itrTot}, {round((100/h.itrTot)*n,2)}%) - {h.rep}: {''.join(guess)}\n"
f = open("pass.txt", "a")
f.write(txt2)
f.close()
break
except:
f = open("save.txt", "w")
f.write(str(h.rep) + "\n" + str(n))
f.close()
if done:
end_time = time.time()
break
print("End time: " + str(end_time-start_time))

John the ripper is the answer. +20k passwords checked in 2 minutes. But using parts of the script for wordlist generation, is still very fast and functional.
wordlist generator i used:
import itertools
inputList = ["A","B","C","D","1","2","3","4","5"]
itr = 7
WL_path = "path"
f = open(WL_path,"w")
f.write("")
f.close()
class h():
startword = ""
rep = 1
itrTot = 0
txt = ""
h.itrTot = len(inputList)**itr
print("Wordlist length: " + str(h.itrTot))
def pw_guess():
res = itertools.product(inputList, repeat=h.rep)
for guess in res:
yield guess
while True:
guess_generator = pw_guess()
for guess in guess_generator:
if h.startword == "":
h.startword = guess
else:
if guess == h.startword:
h.rep += 1
print("next rotation, itr rep: " + str(h.rep))
h.startword = ""
break
h.txt = ''.join(guess)
f = open(WL_path, "a")
f.write(h.txt+"\n")
f.close()
if h.rep > itr:
break

Why is my Code Printing the same Last Name?

The Code Below I wrote takes input from a sample file which contains First and Last names. Then it converts those names to sample emails. For some reason the Script keeps printing the same Last name over and over.
namess.txt looks like this:
firstname,lastname
CODE:
import os, re, time, getpass, linecache
Original = os.path.join(os.path.expanduser('~'), 'Desktop','namess.txt')
File = os.path.join(os.path.expanduser('~'), 'Desktop','output.txt')
badNames = []
Names = []
def RemCommas():
outfile = open(os.path.join('C:\\', 'Users', getpass.getuser(), 'Desktop','output.txt'),'w')
Filedata = open(Original).read()
outfile.write(re.sub(',', ' ', Filedata))
outfile.close()
def ClassNum():
count = 6
Year = int(time.strftime('%Y'))
Class = str((Year - 2013) + 6)
return Class
def ReadStoreFile():
i = 0
OpenFile = open(File)
LenFile = len(OpenFile.readlines())
while i < LenFile:
i += 1
badNames.append(linecache.getline(File, i))
def CleanNames():
i = 0
while i < len(badNames):
cleaned = badNames[i].rstrip()
Names.append(cleaned)
i += 1
def NamePrint():
Interns = 'makchessclub.org'
arrayname = []
i = 0
j = 0
m = 0
while m < len(Names):
Name = Names[m]
Name = Name.lower()
InternName = Name[0] + Name[1]
#------------Checking for space and first name--
while i < len(Name):
if Name[i] == ' ':
i = Name.index(' ')
break;
i += 1
#---------------adding last name in an array----
Namelen = len(Name) - (i+1)
while j < Namelen:
arrayname.append(Name[i+1])
j += 1
i += 1
#---------------Final Name Print----------------
Lastname = ''.join(arrayname)
#print arrayname
#Lastname = Lastname.strip(' ')
#print InternName + Lastname + ClassNum() + Interns
file = open('C:\\Users\\username\\Desktop\\emails.txt', 'a')
file.write(InternName + Lastname + ClassNum() + Interns + '\n')
file.close()
m += 1
RemCommas()
ReadStoreFile()
CleanNames()
NamePrint()
print ''
os.system('pause')

The reason the last name doesn't change is because you are not resetting arrayname in your loop. You keep appending names to it, and the program picks the first one. So you should put your arrayname = [] after the while m < len(Names):

I guess this what you are trying to do:
import os
import re
import time
def create_mails(input_path, output_path, year, addr):
with open(input_path, 'r') as data:
mail = re.sub(r'(\w+)\s*,\s*(\w+)\n?', r'\1\g<2>%s%s\n' % (year, addr), data.read())
with open(output_path, 'w') as output:
output.write(mail.lower())
print 'Mail addresses generated and saved to', output_path
Demo:
create_mails(
os.path.join(os.path.expanduser('~'), 'Desktop', 'namess.txt'),
os.path.join(os.path.expanduser('~'), 'Desktop', 'output.txt'),
str(int(time.strftime('%Y')) - 2013 + 6),
'#makchessclub.org'
)
If namess.txt is something like this:
First, Last
John,Doe
Spam, Ham
Cabbage, egg
Then output.txt is going to be like this:
firstlast6#makchessclub.org
johndoe6#makchessclub.org
spamham6#makchessclub.org
cabbageegg6#makchessclub.org