Files & Data

with open("notes.txt", "w", encoding="utf-8") as f:
    f.write("first line\n")
    f.write("second line\n")

with open("notes.txt", "a", encoding="utf-8") as f:   # append
    print("third line", file=f)                        # print works on files too

with open("notes.txt", encoding="utf-8") as f:
    content = f.read()                                  # whole file as one str
print(repr(content))

with open("notes.txt", encoding="utf-8") as f:
    for n, line in enumerate(f, 1):                     # line by line — memory-safe for huge files
        print(n, line.rstrip())

with open("notes.txt", encoding="utf-8") as f:
    print(f.readlines())

from pathlib import Path

root = Path("project")
(root / "logs").mkdir(parents=True, exist_ok=True)
(root / "logs" / "app.log").write_text("boot ok\n", encoding="utf-8")
(root / "logs" / "db.log").write_text("connected\n", encoding="utf-8")
(root / "README.md").write_text("# Project\n", encoding="utf-8")

p = root / "logs" / "app.log"
print(p, "|", p.name, "|", p.stem, "|", p.suffix, "|", p.parent)
print(p.exists(), p.is_file(), (root / "nope").exists())

for log in sorted(root.glob("**/*.log")):          # recursive search
    print(log, "→", log.read_text(encoding="utf-8").strip())

print([child.name for child in sorted(root.iterdir())])
print(p.with_suffix(".txt"))                          # rename the extension
print(Path("a/b/../c").resolve().name)                # normalise

import csv

rows = [
    {"id": 1, "customer": "Ada, Inc.", "total": 19.99},   # note the comma in the name
    {"id": 2, "customer": "Linus", "total": 5.00},
]

# write
with open("orders.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.DictWriter(f, fieldnames=["id", "customer", "total"])
    writer.writeheader()
    writer.writerows(rows)

print(open("orders.csv", encoding="utf-8").read())   # see the quoting

# read — every value comes back as a STRING
with open("orders.csv", newline="", encoding="utf-8") as f:
    total = 0
    for row in csv.DictReader(f):
        print(row)
        total += float(row["total"])          # convert!
print("sum:", total)

import json
from datetime import date

user = {"name": "Ada", "langs": ("python", "sql"), "active": True, "manager": None, 42: "int key"}

text = json.dumps(user, indent=2)
print(text)

back = json.loads(text)
print(back["langs"], type(back["langs"]).__name__)   # tuple → list
print(list(back.keys())[-1], "is now a", type(list(back.keys())[-1]).__name__)

# to / from a file
with open("user.json", "w", encoding="utf-8") as f:
    json.dump(user, f)
with open("user.json", encoding="utf-8") as f:
    print(json.load(f)["name"])

# things JSON cannot represent need a default
print(json.dumps({"when": date(2026, 1, 1)}, default=str))

s = "café €5"
b = s.encode("utf-8")
print(b, len(s), len(b))             # 7 characters, 10 bytes
print(b.decode("utf-8"))
print(s.encode("latin-1", errors="replace"))   # € has no Latin-1 code point

# The crash, reproduced: bytes written as Latin-1, read as UTF-8
with open("legacy.txt", "wb") as f:
    f.write("résumé".encode("latin-1"))
try:
    print(open("legacy.txt", encoding="utf-8").read())
except UnicodeDecodeError as e:
    print("UnicodeDecodeError:", e.reason, "at byte", e.start)
print(open("legacy.txt", encoding="latin-1").read())      # the right key opens it