7~10주차 — 웹 스크래핑 · NumPy / Pandas 입문 · 패키징과 배포 · 고급 종합 실습

import requests

r = requests.get("https://httpbin.org/get", params={"q": "python"}, timeout=10)
print(r.status_code)
print(r.json()["args"])

200
{'q': 'python'}

from bs4 import BeautifulSoup

html = """<html><body>
<h1>제목</h1>
<ul>
  <li class="item">A</li>
  <li class="item">B</li>
  <li class="item">C</li>
</ul>
</body></html>"""

soup = BeautifulSoup(html, "html.parser")
print(soup.h1.text)
print([li.text for li in soup.select("li.item")])

제목
['A', 'B', 'C']

import requests

s = requests.Session()
s.headers.update({"User-Agent": "study/1.0"})

# httpbin이 보낸 쿠키를 받아서 그대로 사용
s.get("https://httpbin.org/cookies/set/sessionid/abc123")
r = s.get("https://httpbin.org/cookies")
print(r.json())

{'cookies': {'sessionid': 'abc123'}}

import requests
from bs4 import BeautifulSoup

r = requests.get("https://httpbin.org/html", timeout=10)
r.raise_for_status()
soup = BeautifulSoup(r.text, "html.parser")
print("h1:", soup.h1.get_text(strip=True))
print("p 개수:", len(soup.find_all("p")))

h1: Herman Melville - Moby-Dick
p 개수: 1

import numpy as np

a = np.array([1, 2, 3, 4, 5])
print("평균:", a.mean())
print("표준편차:", round(a.std(), 4))
print("합계:", a.sum())
print("배수:", a * 2)
print("불리언:", a > 2)

평균: 3.0
표준편차: 1.4142
합계: 15
배수: [ 2  4  6  8 10]
불리언: [False False False  True  True]

import numpy as np

m = np.arange(12).reshape(3, 4)
print(m)
print("m[1, 2] =", m[1, 2])
print("m[:, 1] =", m[:, 1])
print("m[1, :] =", m[1, :])
print("axis=0 합:", m.sum(axis=0))
print("axis=1 합:", m.sum(axis=1))

[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]]
m[1, 2] = 6
m[:, 1] = [1 5 9]
m[1, :] = [4 5 6 7]
axis=0 합: [12 15 18 21]
axis=1 합: [ 6 22 38]

import pandas as pd

df = pd.DataFrame({
    "name": ["Alice", "Bob", "Charlie"],
    "score": [92, 78, 85],
})
print(df)
print("---")
print("평균:", df["score"].mean())
print("최대:", df["score"].max())

      name  score
0    Alice     92
1      Bob     78
2  Charlie     85
---
평균: 85.0
최대: 92

import pandas as pd

df = pd.DataFrame({
    "name": ["Alice", "Bob", "Charlie", "Dave"],
    "score": [92, 78, 85, 67],
    "dept": ["A", "B", "A", "B"],
})

print(df[df.score >= 80])
print("---")
print(df.groupby("dept")["score"].mean())

      name  score dept
0    Alice     92    A
2  Charlie     85    A
---
dept
A    88.5
B    72.5
Name: score, dtype: float64

[project]
name = "mytool"
version = "0.1.0"
description = "내 멋진 CLI 도구"
authors = [{name = "홍길동", email = "hong@example.com"}]
requires-python = ">=3.10"
dependencies = ["requests>=2.28"]

[project.scripts]
mytool = "mytool.cli:main"

[build-system]
requires = ["setuptools>=61"]
build-backend = "setuptools.build_meta"

(설정 파일 — 직접 출력은 없음)

__version__ = "0.1.0"

(import 시 활성화)

import argparse

def main():
    parser = argparse.ArgumentParser(prog="mytool")
    parser.add_argument("name", help="이름")
    parser.add_argument("--upper", action="store_true")
    args = parser.parse_args()
    msg = f"Hello, {args.name}!"
    print(msg.upper() if args.upper else msg)

if __name__ == "__main__":
    main()

$ mytool 홍길동
Hello, 홍길동!
$ mytool 홍길동 --upper
HELLO, 홍길동!

# 가상환경
python -m venv .venv
source .venv/bin/activate

# 개발 설치
pip install -e .

# 실행
mytool 세상

# 빌드
pip install build
python -m build

Hello, 세상!
Successfully built mytool-0.1.0.tar.gz mytool-0.1.0-py3-none-any.whl

from dataclasses import dataclass, field

@dataclass
class Article:
    title: str
    url: str
    score: int = 0
    tags: list[str] = field(default_factory=list)

a = Article("파이썬 비동기", "https://x", score=120, tags=["python", "async"])
print(a)

Article(title='파이썬 비동기', url='https://x', score=120, tags=['python', 'async'])

import asyncio
import httpx

async def fetch_one(client, url):
    r = await client.get(url, timeout=10)
    return r.status_code, len(r.text)

async def fetch_all(urls):
    async with httpx.AsyncClient() as client:
        return await asyncio.gather(*(fetch_one(client, u) for u in urls))

if __name__ == "__main__":
    urls = ["https://example.com"] * 3
    print(asyncio.run(fetch_all(urls)))

[(200, 1256), (200, 1256), (200, 1256)]

import pandas as pd

def by_dept(df: pd.DataFrame) -> pd.Series:
    return df.groupby("dept")["score"].mean()

if __name__ == "__main__":
    df = pd.DataFrame({"name": ["A", "B", "C", "D"], "score": [90, 70, 80, 60], "dept": ["X", "Y", "X", "Y"]})
    print(by_dept(df))

dept
X    85.0
Y    65.0
Name: score, dtype: float64

import argparse

def main():
    p = argparse.ArgumentParser(prog="myapp")
    sub = p.add_subparsers(dest="cmd", required=True)
    sub.add_parser("crawl")
    a = sub.add_parser("analyze")
    a.add_argument("path")
    args = p.parse_args()

    if args.cmd == "crawl":
        print("크롤 시작")
    elif args.cmd == "analyze":
        print(f"분석: {args.path}")

if __name__ == "__main__":
    main()

$ myapp crawl
크롤 시작
$ myapp analyze data.csv
분석: data.csv