Python爬虫怎样使用XPath解析_Python爬虫利用XPath提取网页元素的技巧

from lxml import html
<h1>示例HTML</h1><p>html_content = '''
<div class="product">
<h3 class="title">手机</h3>
<span class="price">¥2999</span>
</div>
<div class="product">
<h3 class="title">笔记本电脑</h3>
<span class="price">¥5999</span>
</div>
'''</p><h1>解析HTML</h1><p>tree = html.fromstring(html_content)</p>
                    <div class="aritcle_card">
                        <a class="aritcle_card_img" href="/ai/1883">
                            <img src="https://img.php.cn/upload/ai_manual/000/969/633/68b6c393d79ee246.jpeg" alt="Magic Write">
                        </a>
                        <div class="aritcle_card_info">
                            <a href="/ai/1883">Magic Write</a>
                            <p>Canva旗下AI文案生成器</p>
                            <div class="">
                                <img src="/static/images/card_xiazai.png" alt="Magic Write">
                                <span>75</span>
                            </div>
                        </div>
                        <a href="/ai/1883" class="aritcle_card_btn">
                            <span>查看详情</span>
                            <img src="/static/images/cardxiayige-3.png" alt="Magic Write">
                        </a>
                    </div>
                <h1>使用XPath提取标题</h1><p>titles = tree.xpath('//h3[@class="title"]/text()')
prices = tree.xpath('//span[@class="price"]/text()')</p><p>print(titles)   # ['手机', '笔记本电脑']
print(prices)   # ['¥2999', '¥5999']</p>

def parse(self, response):
    for product in response.xpath('//div[@class="product"]'):
        yield {
            'name': product.xpath('.//h3/text()').get(),
            'price': product.xpath('.//span[@class="price"]/text()').get(),
        }