Python Parsing text file into Dictionary

Question

I am using Python 3.6 and suppose I have data that looks like following

data = """

Mod 123  
Trainee Name: John Doe 
Date: 11-11-1111 
MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question.
1. 2 + 2 = 4? 
a. True 
b. False 
correct: c 
ignore this line
and this one too
2. US Population  is _____ Million. 
a. 271 
b. 292 
c. 319 
d. 328 
correct: d"""

I want a dictionary object that looks like following

[ 
    {'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {'Option_1': 'True', 'Option_2': 'False'}, 'Correct': "Option_1"},
    {'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {'Option_1': '271', 'Option_2': '292', 'Option_3': '319', 'Option_4': '328', 'Correct': "Option_4"}}

]

Things to note is that choices can be up to a,b,c,d,e (5) and there is junk stuff to remove thats just extra lines.

My code is following

dt = {}
lt = []
dc = {}
lc = []


d = data.split('\n')

for x in range(len(d)):
    line = d[x]

    if x < len(d) -1:
        nl = d[x+1]
        try:
            if (nl[0].isdigit() and nl[1] == ".") or (nl[0].isdigit() and nl[1].isdigit() and nl[2] == "."):
                next_line = "Question"
        except:
            next_line = ""

    try:
        if (line[0].isdigit() and line[1] == ".") or (line[0].isdigit() and line[1].isdigit() and line[2] == ".") :
            Question = line.split(". ")[1]
            Sequence_Number = line.split(". ")[0]



        if line.startswith('a. ') :
            dc['Option_1'] = line.split(". ")[1]
            if next_line != "Question":
                continue


        if line.startswith('b. '):
            dc['Option_2'] = line.split(". ")[1]
            if next_line != "Question":
                continue

        if line.startswith('c. ') :
            dc['Option_3'] = line.split(". ")[1]
            if next_line != "Question":
                continue


        if line.startswith('d. '):
            dc['Option_4'] = line.split(". ")[1]
            if next_line != "Question":
                continue

        if line.startswith('e. '):
            dc['Option_5'] = line.split(". ")[1]
            if next_line != "Question":
                continue


        if next_line == "Question" :
            dt['Question'] = Question
            dt['Sequence_Number'] = Sequence_Number
            dt["Answers"] = dc
            lt.append(dt)
            dt = {}
            dc = {}



    except:
        continue



for i in lt:
    print(i)

Result looks like

{'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {}}
{'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {}}
{'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {'Option_1': 'True'}}
{'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {'Option_2': 'False'}}
{'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {}}
{'Question': '2 + 2 = 4', 'Sequence_Number': '1', 'Answers': {}}
{'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {}}
{'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {'Option_1': '271'}}
{'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {'Option_2': '292'}}
{'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {'Option_3': '319'}}
{'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {'Option_4': '328'}}

and result is not clean, I can't seem to skip the empty dictionary inserts. It must be something simple and I can't see it.

Can anyone help

Answer 1

Here's a solution that uses some regex to parse the data and store the results in a list of dictionaries:

import re

data = """

Mod 123  
Trainee Name: John Doe 
Date: 11-11-1111 
MULTIPLE CHOICE. Choose the one alternative that best completes the statement or answers the question.
1. 2 + 2 = 4? 
a. True 
b. False 
correct: a 
ignore this line
and this one too
2. US Population  is _____ Million. 
a. 271 
b. 292 
c. 319 
d. 328 
correct: d"""

OP = 'abcde'
rv = []
matches = re.findall(r'(\d)\. (.*)\n(([a-e]\. .*\n){1,5})correct: (.*)', data)
for match in matches:
    sequence_number, question, options, _, correct = match
    options = re.findall(r'[a-z]\. (.*)', options)
    rv.append({'Question': question.strip(),
               'Sequence_Number': sequence_number.strip(),
               'Answers': {f'Option_{idx}': opt.strip() for idx, opt in enumerate(options, start=1)},
               'Correct': f'Option_{OP.index(correct.strip()) + 1}',
               }
              )

print(rv)

Output:

[{'Question': '2 + 2 = 4?', 'Sequence_Number': '1', 'Answers': {'Option_1': 'True', 'Option_2': 'False'}, 'Correct': 'Option_1'},
 {'Question': 'US Population  is _____ Million.', 'Sequence_Number': '2', 'Answers': {'Option_1': '271', 'Option_2': '292', 'Option_3': '319', 'Option_4': '328'}, 'Correct': 'Option_4'}]