Python爬虫保存数据到CSV教程

import csv
import requests
from bs4 import BeautifulSoup
<h1>模拟请求网页</h1><p>url = "<a target='_blank'  href='https://www.17golang.com/gourl/?redirect=MDAwMDAwMDAwML57hpSHp6VpkrqbYLx2eayza4KafaOkbLS3zqSBrJvPsa5_0Ia6sWuR4Juaq6t9nq5roGCUgXuytMyero6Kn83GjHPXkraZo5qYYKbFenqqv4GOmpSBhqKu3LOifWSJ0bJ4mNuGqrluhq2Bqa-GlJ2-s4Flf32kbL-3s2uNrITfvoiHzobQsW4' rel='nofollow'>https://example.com/products</a>"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')</p><h1>提取数据（示例）</h1><p>products = []
for item in soup.find<em>all('div', class</em>='product'):
name = item.find('h2').text.strip()
price = item.find('span', class_='price').text.strip()
link = item.find('a')['href']
products.append([name, price, link])</p><h1>写入CSV文件</h1><p>with open('products.csv', 'w', newline='', encoding='utf-8') as f:
writer = csv.writer(f)</p><h1>写入标题</h1><pre class="brush:python;toolbar:false;">writer.writerow(['Name', 'Price', 'Link'])
# 写入每条数据
writer.writerows(products)

import pandas as pd
<h1>假设数据是字典列表</h1><p>data = [
{'Name': '手机', 'Price': '¥2999', 'Link': '<a target='_blank'  href='https://www.17golang.com/gourl/?redirect=MDAwMDAwMDAwML57hpSHp6VpkrqbYLx2eayza4KafaOkbLS3zqSBrJvPsa5_0Ia6sWuR4Juaq6t9nq5roGCUgXuytMyerpl6n5mwoX_amracsYHffZqrq36fv42JZH19i6S0t7ijgZx8mL2hft2Ht8tuh62FqrBkfa6ya41hibOTorS0o3U' rel='nofollow'>https://xxx.com/1</a>'},
{'Name': '耳机', 'Price': '¥199', 'Link': '<a target='_blank'  href='https://www.17golang.com/gourl/?redirect=MDAwMDAwMDAwML57hpSHp6VpkrqbYLx2eayza4KafaOkbLS3zqSBrJvPsa5_0Ia6sWuR4Juaq6t9nq5roGCUgXuytMyerpl6n5mwoX_amracsoHffZqrq36fv42JZH19i6S0t7ijgZx8mL2hft2Ht8tuh62FqrBkfa6ya41hibOTorS0o3U' rel='nofollow'>https://xxx.com/2</a>'}
]</p><h1>转为DataFrame并保存</h1><p>df = pd.DataFrame(data)
df.to_csv('products_pandas.csv', index=False, encoding='utf-8-sig')</p>

try:
    with open('data.csv', 'w', newline='', encoding='utf-8') as f:
        writer = csv.writer(f)
        writer.writerow(['Title', 'URL'])
        for item in items:
            title = item.get('title', '未知')
            url = item.get('url', '')
            writer.writerow([title, url])
except Exception as e:
    print(f"保存文件出错: {e}")