Merge pull request #637 from realpython/python-bytes

Python Bytes Materials

Author: brendaweles

python-bytes/README.md

@@ -0,0 +1,17 @@
+# Bytes Objects: Handling Binary Data in Python
+
+This folder contains code associated with the Real Python tutorial [Bytes Objects: Handling Binary Data in Python](https://realpython.com/python-bytes/).
+
+## Prerequisites
+
+Install the requirements into your virtual environment:
+
+```shell
+(venv) $ python -m pip install -r requirements.txt
+```
+
+Start the Redis server in a Docker container:
+
+```sh
+$ docker run --rm -d -p 6379:6379 redis
+```

python-bytes/checksum.py

@@ -0,0 +1,11 @@
+import hashlib
+import sys
+from pathlib import Path
+
+python_path = Path(sys.executable)
+checksum_path = python_path.with_suffix(".md5")
+
+machine_code = python_path.read_bytes()
+checksum_path.write_bytes(hashlib.md5(machine_code).digest())
+
+print("Saved", checksum_path)

python-bytes/checksum_incremental.py

@@ -0,0 +1,15 @@
+import hashlib
+import sys
+from pathlib import Path
+
+
+def calculate_checksum(path: Path, chunk_size: int = 4096) -> bytes:
+    checksum = hashlib.md5()
+    with path.open(mode="rb") as file:
+        while chunk := file.read(chunk_size):
+            checksum.update(chunk)
+    return checksum.digest()
+
+
+if __name__ == "__main__":
+    print(calculate_checksum(Path(sys.executable)))

python-bytes/embed.py

@@ -0,0 +1,15 @@
+from base64 import b64encode
+from pathlib import Path
+
+
+def embed_image(path: Path, label: str = "") -> str:
+    ascii_string = b64encode(path.read_bytes()).decode("ascii")
+    print(len(path.read_bytes()))
+    print(len(ascii_string))
+    return f"![{label}](data:image/jpeg;base64,{ascii_string})"
+
+
+if __name__ == "__main__":
+    output_path = Path("picture.md")
+    output_path.write_text(embed_image(Path("picture.jpg")))
+    print("Saved", output_path)

python-bytes/find_timestamps.py

@@ -0,0 +1,8 @@
+import re
+from pathlib import Path
+
+binary_data = Path("picture.jpg").read_bytes()
+pattern = rb"\d{4}:\d{2}:\d{2} \d{2}:\d{2}:\d{2}"
+
+for match in re.finditer(pattern, binary_data):
+    print(match)

python-bytes/generate_image.py

@@ -0,0 +1,6 @@
+import numpy as np
+from PIL import Image
+
+pixels = np.random.default_rng().random((1080, 1920, 3)) * 255
+image = Image.fromarray(pixels.astype("uint8"))
+image.save("image.png")

python-bytes/image.png

@@ -0,0 +1,28 @@
+from mmap import ACCESS_READ, mmap
+from pathlib import Path
+from typing import Iterator, Self
+
+
+class OpenStreetMap:
+    def __init__(self, path: Path) -> None:
+        self.file = path.open(mode="rb")
+        self.stream = mmap(self.file.fileno(), 0, access=ACCESS_READ)
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        self.stream.close()
+        self.file.close()
+
+    def __iter__(self) -> Iterator[bytes]:
+        end = 0
+        while (begin := self.stream.find(b"<way", end)) != -1:
+            end = self.stream.find(b"</way>", begin)
+            yield self.stream[begin : end + len(b"</way>")]
+
+
+if __name__ == "__main__":
+    with OpenStreetMap(Path("map.osm")) as osm:
+        for way_tag in osm:
+            print(way_tag)