nid-snmp/snmp-tojson.py

#!/usr/bin/env python3
"""
SNMP Walk Parser - Combined Nested JSON + Flat CSV + Basic Analysis

Reads a snmpwalk output file (net-snmp style with -On -OQ format)
Creates:
- nested JSON tree
- flat CSV with oid + value columns
- shows basic statistics and example filters
"""

import json
import re
import sys
from pathlib import Path
import pandas as pd

# ────────────────────────────────────────────────
#  CONFIG - change these as needed
# ────────────────────────────────────────────────

INPUT_FILE = Path("~/snmp-walks/10-13-60-102_2026-02-27_11-23-07_walk.txt").expanduser()

# Where to save results (same folder as input by default)
OUTPUT_JSON = INPUT_FILE.with_suffix('.tree.json')
OUTPUT_CSV  = INPUT_FILE.with_suffix('.flat.csv')

# ────────────────────────────────────────────────
#  Helper functions
# ────────────────────────────────────────────────

def parse_line(line: str) -> tuple[str, str] | None:
    """Split oid and value, clean value quotes"""
    line = line.strip()
    if not line or 'No more variables left' in line:
        return None

    # Matches: .1.3.6.1....  "value with \"escaped\" quotes"   or   .1.3.6.1....  12345
    match = re.match(r'^(\.\d+(?:\.\d+)*)\s+(.*)$', line)
    if not match:
        return None

    oid, value = match.groups()
    value = value.strip()

    # Remove surrounding quotes if present (simple case)
    if value.startswith('"') and value.endswith('"'):
        value = value[1:-1]

    # Optional: you could add more cleaning here (unescape \", etc.)
    return oid, value


def build_nested_tree(flat_data: dict[str, str]) -> dict:
    """Convert flat oid → value into nested dictionary"""
    tree = {}
    for oid, value in flat_data.items():
        parts = oid.lstrip('.').split('.')
        current = tree
        for part in parts[:-1]:
            current = current.setdefault(part, {})
        current[parts[-1]] = value
    return tree


def main():
    if not INPUT_FILE.is_file():
        print(f"File not found: {INPUT_FILE}", file=sys.stderr)
        sys.exit(1)

    print(f"Reading: {INPUT_FILE}")
    print(f"Output:  {OUTPUT_JSON}")
    print(f"         {OUTPUT_CSV}\n")

    # ── Parse file ───────────────────────────────────────
    flat_data = {}          # oid → value
    skipped = 0

    with INPUT_FILE.open(encoding='utf-8', errors='replace') as f:
        for line in f:
            result = parse_line(line)
            if result:
                oid, value = result
                flat_data[oid] = value
            else:
                skipped += 1

    print(f"Parsed {len(flat_data):,} OIDs  (skipped {skipped:,} lines)\n")

    # ── 1. Nested JSON tree ──────────────────────────────
    tree = build_nested_tree(flat_data)

    with OUTPUT_JSON.open('w', encoding='utf-8') as f:
        json.dump(tree, f, indent=2, ensure_ascii=False)

    print(f"→ Nested tree saved: {OUTPUT_JSON}")

    # ── 2. Flat DataFrame + CSV ──────────────────────────
    df = pd.DataFrame.from_dict(flat_data, orient='index', columns=['value'])
    df.index.name = 'oid'
    df = df.reset_index()

    df.to_csv(OUTPUT_CSV, index=False, encoding='utf-8')
    print(f"→ Flat table saved:   {OUTPUT_CSV}")

    # ── Quick console summary & examples ─────────────────
    print("\nQuick summary:")
    print(f"Total entries: {len(df):,}")
    print(f"Unique OID prefixes (top 8):")
    df['prefix'] = df['oid'].str.replace(r'\.\d+$', '', regex=True)
    print(df['prefix'].value_counts().head(8))

    print("\nExample: System group (.1.3.6.1.2.1.1)")
    system = df[df['oid'].str.startswith('.1.3.6.1.2.1.1')]
    if not system.empty:
        print(system[['oid', 'value']].to_string(index=False))
    else:
        print("→ No system group entries found")

    print("\nExample: Interface descriptions (.1.3.6.1.2.1.2.2.1.2)")
    ifaces = df[df['oid'].str.contains(r'\.1\.3\.6\.1\.2\.1\.2\.2\.1\.2\b')]
    if not ifaces.empty:
        print(ifaces[['oid', 'value']].to_string(index=False))
    else:
        print("→ No interface descriptions found")

    print("\nDone. Open the .json or .csv file in VS Code / Excel / pandas.")

if __name__ == '__main__':
    main()