Regex: Character Classes, Groups and Lookarounds Reference Guide

import re

# Find / match
re.search(r"\bfoo\b", text)           # first match, anywhere
re.match (r"foo",      text)          # only at the start
re.fullmatch(r"\d{4}", "2026")        # the whole string must match
re.findall(r"\d+",     text)          # list of all non-overlapping
list(re.finditer(r"\d+", text))       # list of Match objects (with .span())

# Replace
re.sub(r"\s+",  " ",   text)          # collapse whitespace
re.sub(r"(\w+)@(\w+)", r"\1 at \2", t)  # backrefs in replacement

# Groups
m = re.search(r"(?P\d{3})-(?P\d{4})", "415-1234")
m.group("area"), m["num"], m.groupdict()

# Compile + flags for hot loops
pat = re.compile(r"^error:", re.MULTILINE | re.IGNORECASE)
for line in pat.finditer(log):
    ...

// Test / match
/foo/.test("foobar")                   // boolean
"foobar".match(/o+/g)                  // ["oo"]  (all matches with /g)
"foobar".search(/b/)                   // index of first match

// Iterate with capture groups
const re = /(\d{4})-(\d{2})-(\d{2})/g;
for (const m of "2026-05-17 and 2026-01-02".matchAll(re)) {
  const [, y, mo, d] = m;
  console.log(y, mo, d);
}

// Named groups (ES2018+)
const pat = /(?\d{3})-(?\d{4})/;
const { groups } = "415-1234".match(pat);
groups.area;                            // "415"

// Replace with a function
"x = 1 + 2".replaceAll(/\d+/g, n => String(Number(n) * 10));

// Common flags
//   g  global       i  ignore case     m  multiline (^/$)
//   s  dotAll       u  unicode         y  sticky

# Email (good-enough, not RFC-perfect)
[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}

# IPv4 (with bounds — each octet 0–255)
\b(?:(?:25[0-5]|2[0-4]\d|1?\d?\d)\.){3}(?:25[0-5]|2[0-4]\d|1?\d?\d)\b

# URL (http/https, no creds, optional path/query)
https?://[^\s/$.?#].[^\s]*

# ISO 8601 date (yyyy-mm-dd)
\b\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])\b

# UUID v4
\b[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-4[0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}\b

# Semver
\bv?(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)(?:-[\w.\-]+)?(?:\+[\w.\-]+)?\b

# Markdown link  →  [text](url)
\[([^\]]+)\]\(([^)]+)\)

# Trim trailing whitespace on every line
[ \t]+$    →  ""    (multiline)

import re
from pathlib import Path

# Parse "2026-05-17 12:34:56 ERROR [orders] failed: ConnectTimeout"
LINE = re.compile(
    r"""
    ^(?P\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2})  # timestamp
    \s+(?PDEBUG|INFO|WARN|ERROR)             # level
    \s+\[(?P[\w.\-]+)\]                        # service
    \s+(?P.+?)                                 # message (lazy)
    (?::\s+(?P\w+))?$                          # optional exception
    """,
    re.VERBOSE,
)

errors_by_service: dict[str, int] = {}

for line in Path("app.log").read_text().splitlines():
    m = LINE.match(line)
    if not m or m["level"] != "ERROR":
        continue
    errors_by_service[m["svc"]] = errors_by_service.get(m["svc"], 0) + 1

for svc, n in sorted(errors_by_service.items(), key=lambda kv: -kv[1]):
    print(f"{n:5d}  {svc}")