Chapter 12: Practical Projects

Project 1: Simple Web Scraper

A web scraper is a "robot that automatically browses web pages." Let's use requests + BeautifulSoup to fetch web content.

# Install dependencies first
# pip install requests beautifulsoup4

import requests
from bs4 import BeautifulSoup

def fetch_news(url):
    """Fetch page titles and links"""
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
    }

    response = requests.get(url, headers=headers, timeout=10)
    response.encoding = response.apparent_encoding

    soup = BeautifulSoup(response.text, "html.parser")
    title = soup.title.string if soup.title else "No Title"
    links = soup.find_all("a", limit=10)

    print(f"📄 Page Title: {title}")
    print(f"🔗 First 10 links:")
    for link in links:
        href = link.get("href", "")
        text = link.get_text(strip=True)[:30]
        if href and text:
            print(f"  [{text}] → {href[:60]}")

# Usage example (replace with an actual accessible URL)
fetch_news("https://example.com")

📄 Page Title: Example Domain
🔗 First 10 links:
  [More information...] → https://www.iana.org/domains/example

⚠️ Note: ⚠️ Web scraping guidelines: Follow the website's robots.txt rulesSet request intervals to avoid putting pressure on serversUse for learning purposes only; obtain authorization for commercial use

Project 2: Batch File Renaming

import os
from datetime import datetime

def batch_rename(directory, prefix="file", start_num=1):
    """Batch rename files in a directory"""
    renamed_count = 0

    for filename in sorted(os.listdir(directory)):
        old_path = os.path.join(directory, filename)

        # Skip subdirectories
        if not os.path.isfile(old_path):
            continue

        # Get file extension
        _, ext = os.path.splitext(filename)

        # Generate new filename: prefix_number.ext
        new_name = f"{prefix}_{start_num:04d}{ext}"
        new_path = os.path.join(directory, new_name)

        # Avoid overwriting existing files
        if os.path.exists(new_path):
            print(f"  ⚠️ Skipped: {new_name} already exists")
            continue

        os.rename(old_path, new_path)
        print(f"  ✅ {filename} → {new_name}")
        renamed_count += 1
        start_num += 1

    return renamed_count

# Usage example
count = batch_rename("./photos", prefix="vacation", start_num=1)
print(f"\nRenamed {count} files in total")

✅ IMG_20240101.jpg → vacation_0001.jpg
  ✅ IMG_20240102.jpg → vacation_0002.jpg
  ✅ IMG_20240103.png → vacation_0003.png

Renamed 3 files in total

Project 3: Calling a Weather API

# pip install requests

import requests

def get_weather(city):
    """Query weather information (using wttr.in free API)"""
    url = f"https://wttr.in/{city}?format=j1"

    try:
        response = requests.get(url, timeout=10)
        data = response.json()

        current = data["current_condition"][0]
        location = data["nearest_area"][0]

        city_name = location["areaName"][0]["value"]
        temp = current["temp_C"]
        feels_like = current["FeelsLikeC"]
        humidity = current["humidity"]
        desc = current["weatherDesc"][0]["value"]
        wind = current["windspeedKmph"]

        print(f"🌍 {city_name} Weather")
        print(f"  🌡️ Temperature: {temp}°C (Feels like {feels_like}°C)")
        print(f"  💧 Humidity: {humidity}%")
        print(f"  🌤️ Conditions: {desc}")
        print(f"  💨 Wind Speed: {wind} km/h")

    except requests.RequestException as e:
        print(f"❌ Failed to get weather: {e}")

# Usage example
get_weather("Beijing")

🌍 Beijing Weather
  🌡️ Temperature: 32°C (Feels like 35°C)
  💧 Humidity: 45%
  🌤️ Conditions: Sunny
  💨 Wind Speed: 12 km/h