第十二章：实战项目

项目一：简单网页爬虫

爬虫就是"自动化浏览网页的机器人"。让我们用 requests + BeautifulSoup 抓取网页内容。

# 先安装依赖
# pip install requests beautifulsoup4

import requests
from bs4 import BeautifulSoup

def fetch_news(url):
    """抓取网页标题和链接"""
    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 "无标题"
    links = soup.find_all("a", limit=10)

    print(f"📄 页面标题：{title}")
    print(f"🔗 前 10 个链接：")
    for link in links:
        href = link.get("href", "")
        text = link.get_text(strip=True)[:30]
        if href and text:
            print(f"  [{text}] → {href[:60]}")

# 使用示例（请替换为实际可访问的 URL）
fetch_news("https://example.com")

📄 页面标题：Example Domain
🔗 前 10 个链接：
  [More information...] → https://www.iana.org/domains/example

⚠️ 注意： ⚠️ 爬虫注意事项：遵守网站的robots.txt规则设置请求间隔，不要对服务器造成压力仅用于学习目的，商业用途请获取授权

项目二：文件批量重命名

import os
from datetime import datetime

def batch_rename(directory, prefix="file", start_num=1):
    """批量重命名目录中的文件"""
    renamed_count = 0

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

        # 跳过子目录
        if not os.path.isfile(old_path):
            continue

        # 获取文件扩展名
        _, ext = os.path.splitext(filename)

        # 生成新文件名：前缀_序号.扩展名
        new_name = f"{prefix}_{start_num:04d}{ext}"
        new_path = os.path.join(directory, new_name)

        # 避免覆盖已有文件
        if os.path.exists(new_path):
            print(f"  ⚠️ 跳过：{new_name} 已存在")
            continue

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

    return renamed_count

# 使用示例
count = batch_rename("./photos", prefix="vacation", start_num=1)
print(f"\n共重命名 {count} 个文件")

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

共重命名 3 个文件

项目三：调用天气 API

# pip install requests

import requests

def get_weather(city):
    """查询天气信息（使用 wttr.in 免费 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} 天气")
        print(f"  🌡️ 温度：{temp}°C（体感 {feels_like}°C）")
        print(f"  💧 湿度：{humidity}%")
        print(f"  🌤️ 天气：{desc}")
        print(f"  💨 风速：{wind} km/h")

    except requests.RequestException as e:
        print(f"❌ 获取天气失败：{e}")

# 使用示例
get_weather("Beijing")

🌍 Beijing 天气
  🌡️ 温度：32°C（体感 35°C）
  💧 湿度：45%
  🌤️ 天气：Sunny
  💨 风速：12 km/h