要在指定的当当网畅销书排行榜页面中抓取所需信息，并使用XPath提取数据，可以参考下面的Python代码示例： ```python import requests from lxml import etree # 目标URL url = "http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-24hours-0-0-1-" def fetch_book_info(page_number): # 构造完整请求 URL full_url = url + str(page_number) headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36' } response = requests.get(full_url, headers=headers) if response.status_code == 200: html_content = response.text # 解析HTML内容 tree = etree.HTML(html_content) books = [] for i in range(1, 51): # 每页最多有50本书籍的信息 try: book_info = {} # 排名 XPath ranking_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/div[1]' rank_text = ''.join(tree.xpath(ranking_xpath)).strip() book_info['rank'] = int(''.join(filter(str.isdigit, rank_text))) # 标题 XPath title_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/div[2]/p[1]/a/@title' book_info['title'] = tree.xpath(title_xpath)[0].strip() # 作者 XPath author_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/div[2]/p[2]' author_text = ''.join(tree.xpath(author_xpath)) book_info['author'] = ''.join([s.strip() for s in author_text.split('\n')]).replace("著", "").strip() # 出版社 XPath publisher_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/div[2]/p[3]' pub_text = ''.join(tree.xpath(publisher_xpath)) book_info['publisher'] = ''.join([s.strip() for s in pub_text.split('\n')]) # 时间 XPath date_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/div[2]/p[3]' date_parts = [s.replace("/", "") for s in tree.xpath(date_xpath)] book_info['date'] = ''.join([part for part in date_parts if len(part)==4 or len(part)<3])[:8] # 图片链接 XPath image_link_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/a/img/@src' book_info['image_link'] = tree.xpath(image_link_xpath)[0] # 当前价格 XPath price_xpath = f'//*[@id="bestsell"]/ul/li[{i}]/div[3]/p[1]/span[1]' book_info['price'] = float(tree.xpath(price_xpath)[0].text) books.append(book_info) except Exception as e: print(f"Error parsing book {i}: {e}") return books else: print(f"Failed to retrieve page: HTTP Status Code {response.status_code}") # 获取所有书籍信息并存储到列表中 all_books = [] for page_num in range(1, 21): # 假设每一页包含50本，共需要爬取20页才能达到500本 all_books.extend(fetch_book_info(page_num)) # 输出结果示例（可以根据需求保存为CSV等） print(all_books) ``` 注意此代码仅为示例，实际运行时可能需调整XPath表达式以适应网站结构变化。