zhang_crawl_bio/tests/mytest/xpath_search.py

from lxml import html  # 使用 lxml.html 模块

# 读取 HTML 文件
save_to_html_path = r'K:\code\upwork\zhang_crawl_bio\output\Acalypha+malabarica+essential+oil\40.html'
with open(save_to_html_path, 'r', encoding='utf-8') as f:
    html_content = f.read()

def is_search_result_empty(html_content: str) -> bool:
    '''
    检查页面是否存在 id="search" 的元素
    并检查其是否有子元素
    如果没有子元素则返回 True 表示搜索结果为空
    '''
    tree = html.fromstring(html_content)
    search_elements = tree.xpath('//*[@id="search"]/*')
    return len(search_elements) == 0


def has_rso_element(html_content: str) -> bool:
    '''检查页面是否存在 id="rso" 的元素'''
    tree = html.fromstring(html_content)
    rso_elements = tree.xpath('//*[@id="rso"]')
    return len(rso_elements) > 0

def main():
    # print("Has rso element:", has_rso_element(html_content))
    print("Is search result empty:", is_search_result_empty(html_content))

if __name__ == "__main__":
    main()