Python Code
Samples
Easy snippets you can copy, study, and run in the browser editor.
Automatically Detect Corrupted Files Using SHA-256 Checksums in Python
Compute SHA-256 checksums of files and compare them to detect corruption in Python.
import hashlib
import os
def compute_sha256(filepath: str) -> str:
"""Compute SHA-256 checksum of a file."""
sha256 = hashlib.sha256()
with open(filepath, 'rb') as f:
for chunk in iter(lambda: f.read(4096), b''):
sha256.update(chunk)
return sha256.hexdigest()
def validate_file_int…Build a File Index by Relative Path Hash Map in Python
Recursively walk a directory and map normalized relative paths to absolute file paths using a defaultdict hash map.
import os
from collections import defaultdict
def build_file_index(root_dir):
index = defaultdict(list)
for dirpath, dirnames, filenames in os.walk(root_dir):
for filename in filenames:
full_path = os.path.join(dirpath, filename)
relative_path = os.path.relpath(full_path, roo…How to Compute File SHA256 Hash with hashlib in Python
Compute the SHA256 hash of a file by reading it in chunks with hashlib and Path.open.
import hashlib
from pathlib import Path
def sha256_file(file_path: Path) -> str:
sha256_hash = hashlib.sha256()
with file_path.open("rb") as f:
for chunk in iter(lambda: f.read(4096), b""):
sha256_hash.update(chunk)
return sha256_hash.hexdigest()
if __name__ == "__main__":
demo_fi…Sync only changed files between two folders in Python
This code compares two folders and copies only the new or modified files from source to destination, skipping unchanged ones by comparing SHA-256 hashes.
import hashlib
from pathlib import Path
import shutil
def file_hash(path: Path, chunk_size: int = 8192) -> str:
hasher = hashlib.sha256()
with path.open("rb") as f:
for chunk in iter(lambda: f.read(chunk_size), b""):
hasher.update(chunk)
return hasher.hexdigest()
def sync_files(src: s…How to Use a Frozenset as a Dict Key in Python
Demonstrates using an immutable frozenset as a hashable dictionary key, including equality and lookup with differently-ordered elements.
frozen = frozenset({"a", "b", "c"})
mapping = {frozen: "set as hashable key"}
other_frozen = frozenset(["c", "b", "a"])
print(f"Are keys equal? {frozen == other_frozen}")
print(f"Lookup with different order: {mapping[other_frozen]}")
print(f"Hash matches: {hash(frozen) == hash(other_frozen)}")How to Make a Python Class Hashable with __eq__ and __hash__
Define __eq__ and __hash__ together on a Python class so equal instances share the same hash and work correctly in sets and dictionary keys.
class Point:
def __init__(self, x, y):
self.x = x
self.y = y
def __eq__(self, other):
if not isinstance(other, Point):
return NotImplemented
return self.x == other.x and self.y == other.y
def __hash__(self):
return hash((self.x, self.y))
def __repr…Python object equality: id vs value comparison
Demonstrates the difference between default identity comparison and custom equality, with a value-based class implementing __eq__ and __hash__.
import copy
class IdOnly:
def __init__(self, name):
self.name = name
class ValueId:
def __init__(self, name):
self.name = name
def __eq__(self, other):
return isinstance(other, ValueId) and self.name == other.name
def __hash__(self):
return hash(self.name)
def…Find Maximum Distance Between Identical Elements in Python
Compute the maximum index distance between any two identical elements in a list using a dictionary to track first occurrences.
from collections import defaultdict
def max_distance_between_identical(nums):
first_occurrence = {}
max_dist = 0
for i, num in enumerate(nums):
if num in first_occurrence:
dist = i - first_occurrence[num]
max_dist = max(max_dist, dist)
else:
first_occur…Cache LLM Completions by Hashing the Prompt in Python
A simple in-memory cache that stores LLM completions keyed by a SHA-256 hash of the prompt to avoid recomputing identical requests.
import hashlib
import json
class PromptCache:
def __init__(self):
self.cache = {}
def _hash_prompt(self, prompt: str) -> str:
return hashlib.sha256(prompt.encode("utf-8")).hexdigest()
def get(self, prompt: str) -> str | None:
key = self._hash_prompt(prompt)
return self.ca…How to Create a Mock Text Embedding with Hash in Python
Generate deterministic mock text embeddings using SHA-256 hashing and numpy, producing normalized vectors for similarity testing without an LLM.
import hashlib
import numpy as np
def mock_embed(text: str, dim: int = 10, seed: int = 42) -> np.ndarray:
"""Generate a deterministic mock embedding using a hash function.
Args:
text: Input text to embed
dim: Dimension of the output vector
seed: Seed for reproducibility
R…How to hash a prompt with SHA-256 in Python
Create a SHA-256 hex fingerprint of a prompt string, with a short-prefix variant for quick references.
import hashlib
def prompt_hash_fingerprint(prompt: str) -> str:
"""Return the full SHA-256 hex digest of the prompt."""
return hashlib.sha256(prompt.encode("utf-8")).hexdigest()
def short_fingerprint(prompt: str, length: int = 12) -> str:
"""Return a short prefix of the SHA-256 digest for quick reference…How to Hash Duplicate Photos and Delete Copies in Python
This script hashes image files in a directory using SHA-256 and deletes duplicate copies while keeping the first occurrence, ideal for cleaning up photo libraries.
from pathlib import Path
import hashlib
def file_hash(path, chunk_size=8192):
hasher = hashlib.sha256()
with open(path, "rb") as f:
for chunk in iter(lambda: f.read(chunk_size), b""):
hasher.update(chunk)
return hasher.hexdigest()
def delete_duplicate_photos(directory):
directory …How to Scan Files Against a Malware Hash List in Python
Compare a file's SHA-256 hash against a known malware hash set and report whether it's clean or infected.
import hashlib
from pathlib import Path
# Mock file content (in real usage, read from disk)
MOCK_FILE_CONTENT = b"print('hello world')"
KNOWN_MALWARE_HASHES = {
"8d969eef6ecad3c29a3a629280e686cf0c3f5d5a86aff3ca12020c923adc6c92",
"5e884898da28047151d0e56f8dc6292773603d0d6aabbdd62a11ef721d1542d8",
}
def sha25…How to generate an htpasswd bcrypt entry in Python
Create a mock htpasswd file entry with a bcrypt-hashed password for a given username using a simple Python script.
import bcrypt
def mock_htpasswd_entry(username, password):
salt = bcrypt.gensalt(rounds=12)
hashed = bcrypt.hashpw(password.encode(), salt).decode()
return f"{username}:{hashed}"
if __name__ == "__main__":
entry = mock_htpasswd_entry("demo_user", "s3cretP@ss")
print(entry)Generate a Deterministic Hash for Deduplication in Python
Create a stable SHA-256 fingerprint from nested data and file contents to deduplicate records in a data pipeline.
import hashlib
import json
from pathlib import Path
def natural_key_hash(data, salt=""):
"""
Generate a deterministic fingerprint from raw data (dict/list/str).
Uses JSON canonical-ish serialization with sorted keys and SHA-256.
"""
canonical = json.dumps(data, sort_keys=True, separators=(",", ":"…How to Hash Email Addresses in a PII Masking Pipeline in Python
Replaces every email address in a text string with its SHA-256 hash to protect personally identifiable information (PII).
import hashlib
import re
def hash_email(email: str) -> str:
"""Mask an email address by hashing it with SHA-256."""
normalized = email.strip().lower()
return hashlib.sha256(normalized.encode("utf-8")).hexdigest()
def mask_pii_emails(text: str) -> str:
"""Replace all email addresses in text with their…How to shard output by primary key hash mod N in Python
This code computes a consistent shard index for any primary key string using an MD5 hash mod the number of shards, enabling stable key-based data distribution.
import hashlib
def shard_id(primary_key: str, num_shards: int) -> int:
"""Return the shard index for a primary key using MD5 hash mod N."""
digest = hashlib.md5(primary_key.encode("utf-8")).hexdigest()
hash_int = int(digest, 16)
return hash_int % num_shards
if __name__ == "__main__":
keys = ["use…How to Partition and Order Kafka-Style Messages by Key in Python
Group messages with the same key into ordered buckets using hashing and a defaultdict, mimicking Kafka partition ordering.
from dataclasses import dataclass
from collections import defaultdict
@dataclass
class Message:
key: str
content: str
def partition_and_order(messages, num_partitions=3):
partitions = defaultdict(list)
for msg in messages:
partition_id = hash(msg.key) % num_partitions
partitions[parti…How to Use Redis HSET and HGET in Python
This code demonstrates how to store and retrieve hash data in Redis using Python's redis library with HSET, HGET, HGETALL, and HDEL commands.
import redis
# Connect to Redis (adjust host/port as needed)
r = redis.Redis(host='localhost', port=6379, db=0, decode_responses=True)
# Clear any existing data for demonstration
r.delete('user:1')
# HSET - Store a hash
r.hset('user:1', mapping={'name': 'Alice', 'age': 30, 'city': 'New York'})
# HGET - Retrieve a …How to cache filtered data in Redis with Python
This code caches filtered list results in Redis using an MD5 hash key, returning cached results when available.
import redis
import json
import hashlib
import time
cache = redis.Redis(host='localhost', port=6379, db=0, decode_responses=True)
def filter_data(data, predicate_key, predicate_value):
"""Filter a list of dicts by key-value pair, with Redis caching."""
cache_key = hashlib.md5(
f"{predicate_key}:{pred…How to create a stable cache key from function arguments in Python
Generate a stable SHA-256 cache key from normalized function arguments, with keyword order normalized and tests using mocks.
import hashlib
import json
from unittest.mock import Mock
def make_cache_key(*args, **kwargs):
"""Normalize args/kwargs into a stable hash key for caching."""
normalized = {
"args": [repr(arg) for arg in args],
"kwargs": {key: repr(value) for key, value in sorted(kwargs.items())}
}
pa…How to Deduplicate Events in Python with SHA256 Hashing
Build an event deduplicator that identifies duplicate inbox messages using SHA256 hashes and tracks duplicate counts per event type.
```python
import hashlib
import json
from collections import defaultdict
class EventDeduplicator:
def __init__(self):
self.seen_hashes = set()
self.duplicate_counts = defaultdict(int)
def process_event(self, event):
event_key = f"{event['event_id']}:{event['timestamp']}"
even…How to Mock a Hash Join on Large and Small Tables in Python
This code efficiently joins a large dataset (1000 rows) with a small lookup table (20 rows) by building a dictionary hash lookup, mimicking a hash join strategy used in big data systems.
import random
from pprint import pprint
# Large table: 1000 rows (id, group_id, value)
large = [{"id": i, "group_id": random.randint(1, 20), "value": random.random() * 100} for i in range(1000)]
# Small table: 20 rows (group_id, label)
small = [{"group_id": g, "label": f"Group-{g}"} for g in range(1, 21)]
# Mock a …Partition Data by Hash Key Mod N in Python
Returns a partition index for a string key by hashing it with MD5 and taking modulo N, then groups sample keys into partitions.
import hashlib
def partition_key(key: str, num_partitions: int) -> int:
"""Return partition index for key using MD5 hash mod N."""
digest = hashlib.md5(key.encode()).hexdigest()
return int(digest, 16) % num_partitions
if __name__ == "__main__":
keys = ["alice", "bob", "carol", "dave", "eve"]
nu…Browse by section
Each section groups closely related Python snippets.
Guide: free Python code samples library
Copy-ready Python snippets for learners and developers
PythonSkillset code samples are short, focused examples organised by topic and difficulty. Every snippet is server-rendered HTML — readable by search engines and easy to copy. Open any sample, read the notes, copy the code, then press Try in editor to run it in the browser with Pyodide.
How to use this library
- Pick a topic section — strings, lists, files, functions, and more
- Open a sample, read How it works, and copy the code block
- Run it in the IDE, tweak values, then take a related quiz or tutorial lesson
Samples vs tutorials and challenges
Samples are quick reference — one concept per page. For step-by-step teaching, use our Python tutorials. To test yourself, try quizzes or coding challenges. Clean up style with the Python formatter.