以下是针对爬虫新手的Python语法教程，结合基础语法与爬虫开发实践，帮助快速入门：一、Python基础语法要点变量与数据类型变量无需声明类型，直接赋值即可（如url = "https://example.com"）常用数据类型：title = "爬虫教程" # 字符串count = 10 # 整数price = 9.99 # 浮点数tags = ["Python", "爬虫"] # 列表控制流条件判断：if response.status_code == 200: print("请求成功")else: print("请求失败")循环结构：for item in items: print(item.text)函数封装def parse_content(html): soup = BeautifulSoup(html, 'html.parser') return soup.find_all('article')类与对象（进阶）class WebScraper: def __init__(self, base_url): self.base_url = base_url def fetch_data(self): return requests.get(self.base_url)二、核心爬虫库使用requests库import requestsheaders = {'User-Agent': 'Mozilla/5.0'}response = requests.get(url, headers=headers)response.encoding = 'utf-8' # 解决中文编码BeautifulSoup解析from bs4 import BeautifulSoupsoup = BeautifulSoup(response.text, 'html.parser')# CSS选择器示例titles = soup.select('div.news-item > h3 > a')lxml加速解析from lxml import etreehtml = etree.HTML(response.text)results = html.xpath('//div[@class="content"]/text()')三、完整爬虫开发流程目标分析三步法浏览器开发者工具（F12）查看：网络请求（Network标签）数据接口（XHR类型请求）HTML结构（Elements标签）反爬策略应对# 添加请求头headers = { 'User-Agent': 'Mozilla/5.0', 'Referer': 'https://example.com'}# 设置会话保持session = requests.Session()数据存储方案# 存储为CSVimport csvwith open('data.csv', 'w', encoding='utf-8') as f: writer = csv.writer(f) writer.writerow(['标题', '链接']) writer.writerows(data_list)# 存储到SQLiteimport sqlite3conn = sqlite3.connect('data.db')cursor = conn.cursor()cursor.execute('CREATE TABLE IF NOT EXISTS news (title TEXT, url TEXT)')四、实战示例：爬取新闻标题import requestsfrom bs4 import BeautifulSoupdef scrape_news(url): try: response = requests.get(url, timeout=5) response.raise_for_status() soup = BeautifulSoup(response.text, 'html.parser') articles = soup.find_all('article', class_='news-item') results = [] for article in articles[:5]: # 限制获取前5条 title = article.find('h2').get_text(strip=True) link = article.find('a')['href'] results.append({'title': title, 'url': link}) return results except Exception as e: print(f"爬取失败: {e}") return []if __name__ == '__main__': data = scrape_news("https://news.example.com") for idx, item in enumerate(data, 1): print(f"{idx}. {item['title']} ({item['url']})")五、新手避坑指南法律与道德规范遵守目标网站的robots.txt协议设置合理的请求间隔（建议1-3秒/次）避免爬取用户隐私数据常见错误处理# 网络请求重试机制from time import sleepfor _ in range(3): try: response = requests.get(url) break except: sleep(2)性能优化建议使用Session()对象复用连接对大规模数据采用多线程（需控制并发量）考虑使用缓存（如requests-cache库）六、学习资源推荐官方文档：Requests文档BeautifulSoup文档实践平台：Scrapy官方教程Python练习网站建议从静态页面爬取开始练习，逐步尝试JavaScript渲染页面（可用Selenium或Playwright），最后学习分布式爬虫框架如Scrapy。