parser.py

#!/usr/bin/env python
import os
import json
import re

raw_input = """
ID                     : fa5bd3ba-5e60-4499-be7c-3b9556b89e7b
Gossip active          : true
Thrift active          : true
Native Transport active: true
Load                   : 827.55 KiB
Generation No          : 1494935993
Uptime (seconds)       : 777385
Heap Memory (MB)       : 192.55 / 990.00
Off Heap Memory (MB)   : 0.00
Data Center            : eu-west
Rack                   : 1b
Exceptions             : 0
Key Cache              : entries 195, size 18.92 KiB, capacity 49 MiB, 5438 hits, 5630 requests, 0.966 recent hit rate, 14400 save period in seconds
Row Cache              : entries 0, size 0 bytes, capacity 0 bytes, 0 hits, 0 requests, NaN recent hit rate, 0 save period in seconds
Counter Cache          : entries 0, size 0 bytes, capacity 24 MiB, 0 hits, 0 requests, NaN recent hit rate, 7200 save period in seconds
Chunk Cache            : entries 17, size 1.06 MiB, capacity 215 MiB, 1425 misses, 7146 requests, 0.801 recent hit rate, NaN microseconds miss latency
Percent Repaired       : 100.0%
Token                  : (invoke with -T/--tokens to see all 256 tokens)

"""

def parse_status(raw_data, filters=None):
    lines = raw_data.split(os.linesep)
    status = dict()
    for line in lines:
        if len(line.strip()) == 0:
            continue
        if filters is not None:
            if apply_filters(text=line, filters=filters) == 0:
                continue

        key_value = line.split(":")
        status.update({key_value[0].strip():key_value[1].strip()})
    return status

def apply_filters(text, filters):
    match_count = 0
    for f in filters:
        regex = re.compile(f, re.IGNORECASE)
        match = regex.search(text)
        if match:
            match_count += 1
    return match_count

def to_json(data):
    return json.dumps(data, indent=4, sort_keys=True)


filters = ["cache", "token", "Gossip Active"]
print to_json(parse_status(raw_input, filters))