Python error- cannot unpack non-iterable NoneType object-CodePudding

I am trying to merge sentences between two timestamps and return in the form of a list: Input data is:

[
'00:00:00.000 --> 00:00:00.740', '<v Davis, Tres>Hi, Tuim.</v>', 

'00:00:10.000 --> 00:01:00.581', '<v Crook, Tim. J.>Yeah. Hi, Tres.</v>', 

'00:00:10.000 --> 00:01:00.581', '<v Davis, Tres>On the deck. We will go back. I'm watching so not to what I'm thinking. </v>', 

'00:00:12.056 --> 00:00:00.721', '<v Davis, Tres>Ofcourse.</v>',

'00:00:25.643 --> 00:00:00.775', '<v Davis, Tres>Thanks, Bye.</v>'
]

Expected output is:

[
'00:00:00.000 --> 00:00:00.740', '<v Davis, Tres>Hi, Tuim.</v>', 

'00:00:10.000 --> 00:01:00.581', '<v Crook, Tim. J.>Yeah. Hi, Tres.</v>', 

'00:00:10.000 --> 00:01:00.581', '<v Davis, Tres>On the deck. We will go back. I'm watching so not to what I'm thinking. Ofcourse. Thanks, Bye.</v>'

]

Below is the code that I am trying-

import itertools

lines = [
'00:00:00.000 --> 00:00:00.740', '<v Davis, Tres>Hi, Tuim.</v>', 

'00:00:10.000 --> 00:01:00.581', '<v Crook, Tim. J.>Yeah. Hi, Tres.</v>', 
'00:00:10.000 --> 00:01:00.581', '<v Davis, Tres>On the deck. We will go back. Iam watching so not to what Iam thinking. </v>', 
'00:00:12.056 --> 00:00:00.721', '<v Davis, Tres>Ofcourse.</v>',
'00:00:25.643 --> 00:00:00.775', '<v Davis, Tres>Thanks, Bye.</v>'
]
def iterate_over_lines(lines):
    lines_iter = iter(lines) # create an iterator for the list
    while True:
        try:
            timestamp = next(lines_iter)
            speech = next(lines_iter)
            yield (timestamp, speech)  # Each "speech group" contains the timestamp, and what was said
        except StopIteration:
            break

def get_speaker(speech_group):
    line = speech_group[1]     # What was said is the second element of the group
    speaker_out = line.split('<v ')[1].split('>')[0]   # Extract speaker from line
    return speaker_out

line_groups = iterate_over_lines(lines)

for speaker, lines_spoken in itertools.groupby(line_groups, key=get_speaker):
    print(speaker)
    print(*lines_spoken, sep="\n")
    print("")

def get_speech(line):
    speech_out = line.split('<v ')[1].split('>')[1].split('</v')[0]   # Extract speech from line
    return speech_out

def merge_group(group):
    timestamp = None
    speech = []
    for ts, sp in group:
        if timestamp is None: 
            timestamp = ts
        speech.append(get_speech(sp))

line_groups = iterate_over_lines(lines)

result = []
for speaker, lines_spoken in itertools.groupby(line_groups, key=get_speaker):
    timestamp, speech = merge_group(lines_spoken)
    result.append(timestamp)
    result.append(f"<v {speaker}>{speech}</v>")
print(result)

Error that I am getting is:

Traceback (most recent call last):
  File "<stdin>", line 2, in <module>
TypeError: cannot unpack non-iterable NoneType object

CodePudding user response：

you forgot to return the tuple in function merge_group:

import itertools

lines = [
'00:00:00.000 --> 00:00:00.740', '<v Davis, Tres>Hi, Tuim.</v>',

'00:00:10.000 --> 00:01:00.581', '<v Crook, Tim. J.>Yeah. Hi, Tres.</v>',
'00:00:10.000 --> 00:01:00.581', '<v Davis, Tres>On the deck. We will go back. Iam watching so not to what Iam thinking. </v>',
'00:00:12.056 --> 00:00:00.721', '<v Davis, Tres>Ofcourse.</v>',
'00:00:25.643 --> 00:00:00.775', '<v Davis, Tres>Thanks, Bye.</v>'
]
def iterate_over_lines(lines):
    lines_iter = iter(lines) # create an iterator for the list
    while True:
        try:
            timestamp = next(lines_iter)
            speech = next(lines_iter)
            yield (timestamp, speech)  # Each "speech group" contains the timestamp, and what was said
        except StopIteration:
            break

def get_speaker(speech_group):
    line = speech_group[1]     # What was said is the second element of the group
    speaker_out = line.split('<v ')[1].split('>')[0]   # Extract speaker from line
    return speaker_out

line_groups = iterate_over_lines(lines)

for speaker, lines_spoken in itertools.groupby(line_groups, key=get_speaker):
    print(speaker)
    print(*lines_spoken, sep="\n")
    print("")

def get_speech(line):
    speech_out = line.split('<v ')[1].split('>')[1].split('</v')[0]   # Extract speech from line
    return speech_out

def merge_group(group):
    timestamp = None
    speech = []
    for ts, sp in group:
        if timestamp is None:
            timestamp = ts
        speech.append(get_speech(sp))
    return timestamp, ', '.join(speech)

line_groups = iterate_over_lines(lines)

result = []
for speaker, lines_spoken in itertools.groupby(line_groups, key=get_speaker):
    timestamp, speech = merge_group(lines_spoken)
    result.append(timestamp)
    result.append(f"<v {speaker}>{speech}</v>")

    '''
    [
'00:00:00.000 --> 00:00:00.740', '<v Davis, Tres>Hi, Tuim.</v>',

'00:00:10.000 --> 00:01:00.581', '<v Crook, Tim. J.>Yeah. Hi, Tres.</v>',

'00:00:10.000 --> 00:01:00.581', '<v Davis, Tres>On the deck. We will go back. I'm watching so not to what I'm thinking. Ofcourse. Thanks, Bye.</v>'

]
    '''
print(result)