爬虫用xpath爬取豆瓣电影top100电影评分代码

XPath是一种用于XML文档和类似结构的选择语言，常用于网页爬虫中选择和提取数据。以下是一个基本的例子，展示如何使用Python的`lxml`库（结合`requests`获取网页内容）来爬取豆瓣电影Top250页面上电影的评分：

import requests
from lxml import etree

def get_douban_ratings():
    # 请求豆瓣电影Top250页面
    url = "https://movie.douban.com/top250"
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
    }
    response = requests.get(url, headers=headers)

    # 检查请求是否成功，设置解析树
    if response.status_code == 200:
        html_content = response.text
        tree = etree.HTML(html_content)
        
        # 使用XPath表达式找到电影评分节点
        rating_nodes = tree.xpath('//div[@class="rating_num"]')
        
        ratings = []
        for node in rating_nodes:
            rating_text = node.text.strip()  # 提取文本
            ratings.append(float(rating_text))  # 将字符串转为浮点数

        return ratings
    else:
        print(f"Failed to fetch the page. Status code: {response.status_code}")
        return []

# 打印并处理结果
top_100_ratings = get_douban_ratings()
for i, rating in enumerate(top_100_ratings[:10], start=1):
    print(f"{i}. 电影{str(i)}的评分: {rating}")