File Handling

Opening Files with open()

The built-in open() function opens a file and returns a file object. The mode determines the operation:

f = open("file.txt", "r")   # read (default)
f = open("file.txt", "w")   # write (overwrites!)
f = open("file.txt", "a")   # append
f = open("file.txt", "x")   # exclusive create (fails if exists)
f = open("file.txt", "rb")  # read binary
f = open("file.txt", "wb")  # write binary

Reading Files

# Read entire file as a string
with open("example.txt", "r") as f:
    content = f.read()

# Read one line at a time
with open("example.txt", "r") as f:
    line = f.readline()
    while line:
        print(line.strip())
        line = f.readline()

# Read all lines into a list
with open("example.txt", "r") as f:
    lines = f.readlines()  # includes \n characters

# Iterate directly (memory-efficient)
with open("example.txt", "r") as f:
    for line in f:
        print(line.strip())

Writing Files

# write() writes a single string
with open("output.txt", "w") as f:
    f.write("Hello, World!\n")
    f.write("Second line\n")

# writelines() writes an iterable of strings
lines = ["Line 1\n", "Line 2\n", "Line 3\n"]
with open("output.txt", "w") as f:
    f.writelines(lines)

The with Context Manager

The with statement automatically closes the file, even if an exception occurs:

# Bad: manual close
f = open("file.txt", "r")
data = f.read()
f.close()

# Good: automatic close
with open("file.txt", "r") as f:
    data = f.read()
# File is closed automatically

File Position: seek() and tell()

with open("example.txt", "r") as f:
    f.read(10)          # read first 10 chars
    pos = f.tell()      # current position (10)
    f.seek(0)           # go back to beginning
    f.seek(5)           # go to byte 5
    f.seek(0, 2)        # seek to end (2 = whence end)

The os Module

import os

os.rename("old.txt", "new.txt")   # rename file
os.remove("file.txt")             # delete file
os.mkdir("newdir")                # create directory
os.rmdir("emptydir")              # remove empty directory
os.listdir(".")                   # list directory contents
os.path.exists("file.txt")        # check existence
os.path.isfile("file.txt")        # is it a file?
os.path.isdir("mydir")            # is it a directory?
os.path.join("dir", "file.txt")   # platform-aware path join

The pathlib Module (Modern)

pathlib provides an object-oriented approach to filesystem paths:

from pathlib import Path

p = Path("data/subdir")
p.mkdir(parents=True, exist_ok=True)  # create dirs recursively

file = p / "notes.txt"               # path join with /
file.write_text("Hello, Path!")      # write text
content = file.read_text()           # read text
file.exists()                        # True
file.is_file()                       # True
file.suffix                          # '.txt'
file.stem                            # 'notes'
file.name                            # 'notes.txt'

# Glob pattern matching
txt_files = Path(".").glob("*.txt")
py_files = Path("src").rglob("*.py")  # recursive

# Delete file
file.unlink()

Practical Example

from pathlib import Path

# Create a log file and append entries
log = Path("app.log")
entries = [
    "[INFO] Starting application",
    "[INFO] Connected to database",
    "[WARN] Memory usage above 80%",
    "[ERROR] Connection timeout",
]

with log.open("a") as f:
    for entry in entries:
        f.write(entry + "\n")

# Read and filter errors
errors = [line for line in log.read_text().splitlines()
          if "ERROR" in line]
print(f"Found {len(errors)} errors:")
for err in errors:
    print(f"  {err}")

# Backup the log
backup = log.parent / "backups" / f"app_{Path('log').stem}.bak"
backup.parent.mkdir(exist_ok=True)
backup.write_text(log.read_text())

# Clean up old backup files
for old in backup.parent.glob("*.bak"):
    if old.stat().st_mtime < (time.time() - 86400 * 7):
        old.unlink()