计算机毕业设计：都市供求信息网源代码解析

标签 p_tags = soup.find_all('p') for p_tag in p_tags: # 提取ID talk_id = p_tag.find_previous(string=lambda text: isinstance(text, str) and '[talkid:' in text) talk_id = talk_id.strip('[talkid:]') # 提取时间 timestamp = p_tag.find_previous('body').find_previous('head').find('meta', {'http-equiv': 'Content=-Type'})[ 'content'] # 提取发送号码 send_number = p_tag.find('span', {'class': 'hint-success'}).text # 提取接收号码 receive_number = p_tag.find_all('span', {'class': 'hint-success'})[1].text # 提取信息内容 message = p_tag.previous_sibling.strip() # 遍历文件夹及子文件夹，提取HTML文件信息 for root, dirs, files in os.walk(folder_path): for file in files: if file.endswith('.html'): file_path = os.path.join(root, file) extract_html_info(file_path) # 判断是否是音频 if '音频' in message: file_url = p_tag.find('a')['href'] print( f"ID: {talk_id}, 时间: {timestamp}, 发送号码: {send_number}, 接收号码: {receive_number}, 音频文件地址: {file_url}") else: print( f"ID: {talk_id}, 时间: {timestamp}, 发送号码: {send_number}, 接收号码: {receive_number}, 信息内容: {message}")