diff --git a/kb-zhihu-metadata/zhihu_extractor.py b/kb-zhihu-metadata/zhihu_extractor.py index f917f79..2ff509b 100644 --- a/kb-zhihu-metadata/zhihu_extractor.py +++ b/kb-zhihu-metadata/zhihu_extractor.py @@ -80,6 +80,8 @@ class ZhihuPlaywrightExtractor: URL_PATTERNS = { 'zvideo': r'zhihu\.com/zvideo/(\d+)', 'zhuanlan': r'zhuanlan\.zhihu\.com/p/(\d+)', + 'answer': r'zhihu\.com/question/\d+/answer/(\d+)', + 'question': r'zhihu\.com/question/(\d+)', } def __init__(self, headless: bool = True, timeout: int = 30): @@ -242,6 +244,115 @@ class ZhihuPlaywrightExtractor: return result + def _extract_answer_content(self) -> Dict[str, Any]: + """提取知乎回答内容""" + result = { + 'type': 'answer', + 'title': '', # 问题标题 + 'question_id': '', + 'answer_id': '', + 'author': '', + 'content': '', + 'content_markdown': '', + 'publish_time': '', + 'vote_up': 0, + } + + # 打印页面标题用于调试 + page_title = self.browser.page.title() + print(f"页面标题: {page_title}") + + # 提取问题标题 + question_title_elem = self.browser.query_selector('.QuestionHeader-title') + if not question_title_elem: + question_title_elem = self.browser.query_selector('.QuestionHeader-content h1') + if question_title_elem: + result['title'] = self._extract_text_content(question_title_elem) + + # 提取回答内容 + content_elem = self.browser.query_selector('.RichText') + if not content_elem: + content_elem = self.browser.query_selector('.AnswerItem-richText') + if not content_elem: + content_elem = self.browser.query_selector('[class*="RichText"]') + if content_elem: + html_content = self._extract_html_content(content_elem) + result['content'] = html_content + result['content_markdown'] = self.markdown_converter.convert(html_content) + + # 提取作者信息 + author_elem = self.browser.query_selector('.AuthorInfo-name') + if author_elem: + result['author'] = self._extract_text_content(author_elem) + + # 提取发布时间 + time_elem = self.browser.query_selector('.AnswerItem-time') + if not time_elem: + time_elem = self.browser.query_selector('.ContentItem-time') + if time_elem: + result['publish_time'] = time_elem.get_attribute('data-tooltip') or self._extract_text_content(time_elem) + + # 提取点赞数 + vote_elem = self.browser.query_selector('.VoteButton--up .VoteButton-label') + if not vote_elem: + vote_elem = self.browser.query_selector('.VoteButton .Count') + if vote_elem: + vote_text = self._extract_text_content(vote_elem) + try: + result['vote_up'] = int(vote_text.replace(',', '')) + except (ValueError, AttributeError): + pass + + return result + + def _extract_question_content(self) -> Dict[str, Any]: + """提取知乎问题内容（包含所有回答）""" + result = { + 'type': 'question', + 'title': '', + 'question_id': '', + 'author': '', + 'content': '', + 'content_markdown': '', + 'publish_time': '', + 'answer_count': 0, + } + + # 打印页面标题用于调试 + page_title = self.browser.page.title() + print(f"页面标题: {page_title}") + + # 提取问题标题 + title_elem = self.browser.query_selector('.QuestionHeader-title') + if not title_elem: + title_elem = self.browser.query_selector('.QuestionHeader-content h1') + if title_elem: + result['title'] = self._extract_text_content(title_elem) + + # 提取问题描述 + desc_elem = self.browser.query_selector('.QuestionHeader-detail') + if not desc_elem: + desc_elem = self.browser.query_selector('.QuestionRichText') + if desc_elem: + html_content = self._extract_html_content(desc_elem) + result['content'] = html_content + result['content_markdown'] = self.markdown_converter.convert(html_content) + + # 提取回答数量 + answer_count_elem = self.browser.query_selector('.List-headerText span') + if answer_count_elem: + count_text = self._extract_text_content(answer_count_elem) + try: + # 提取数字 + import re + match = re.search(r'(\d+)', count_text) + if match: + result['answer_count'] = int(match.group(1)) + except (ValueError, AttributeError): + pass + + return result + def extract(self, url: str) -> Optional[Dict[str, Any]]: """ 从 URL 提取知乎内容 @@ -288,6 +399,10 @@ class ZhihuPlaywrightExtractor: result = self._extract_zvideo_content() elif url_type == 'zhuanlan': result = self._extract_zhuanlan_content() + elif url_type == 'answer': + result = self._extract_answer_content() + elif url_type == 'question': + result = self._extract_question_content() else: print(f"不支持的类型: {url_type}") return None diff --git a/kb-zhihu-metadata/zhihu_metadata.py b/kb-zhihu-metadata/zhihu_metadata.py index fcff2b1..8963aa9 100644 --- a/kb-zhihu-metadata/zhihu_metadata.py +++ b/kb-zhihu-metadata/zhihu_metadata.py @@ -2,9 +2,11 @@ """ 知乎元数据获取工具 -仅支持两种内容类型： +支持以下内容类型： - zvideo: 知乎视频 (https://www.zhihu.com/zvideo/xxx) - zhuanlan: 知乎专栏文章 (https://zhuanlan.zhihu.com/p/xxx) +- answer: 知乎回答 (https://www.zhihu.com/question/xxx/answer/yyy) +- question: 知乎问题 (https://www.zhihu.com/question/xxx) """ import argparse @@ -51,6 +53,38 @@ def extract_zhuanlan(article_id: str, headless: bool = True) -> Dict[str, Any]: return _extract_metadata(url, "zhuanlan", headless) +def extract_answer(answer_id: str, headless: bool = True) -> Dict[str, Any]: + """ + 获取知乎回答元数据 + + Args: + answer_id: 回答 ID (数字字符串) + headless: 是否使用无头浏览器 + + Returns: + 回答元数据字典 + """ + # 回答需要构建包含问题ID的URL，但answer_id本身足以识别 + # 使用一个占位符问题ID，因为提取器会从URL中提取answer_id + url = f"https://www.zhihu.com/question/0/answer/{answer_id}" + return _extract_metadata(url, "answer", headless) + + +def extract_question(question_id: str, headless: bool = True) -> Dict[str, Any]: + """ + 获取知乎问题元数据 + + Args: + question_id: 问题 ID (数字字符串) + headless: 是否使用无头浏览器 + + Returns: + 问题元数据字典 + """ + url = f"https://www.zhihu.com/question/{question_id}" + return _extract_metadata(url, "question", headless) + + def _extract_metadata(url: str, content_type: str, headless: bool) -> Dict[str, Any]: """ 内部函数：提取元数据 @@ -97,24 +131,28 @@ def main(): 支持的类型: zvideo - 知乎视频 (https://www.zhihu.com/zvideo/123456) zhuanlan - 知乎专栏文章 (https://zhuanlan.zhihu.com/p/123456) + answer - 知乎回答 (https://www.zhihu.com/question/xxx/answer/yyy) + question - 知乎问题 (https://www.zhihu.com/question/xxx) 示例: python zhihu_metadata.py --id "123456" --type zvideo python zhihu_metadata.py --id "123456" --type zhuanlan + python zhihu_metadata.py --id "123456" --type answer + python zhihu_metadata.py --id "123456" --type question """ ) parser.add_argument( "--id", "-i", required=True, - help="知乎内容 ID (视频ID或文章ID)" + help="知乎内容 ID (视频ID/文章ID/回答ID/问题ID)" ) parser.add_argument( "--type", "-t", required=True, - choices=["zvideo", "zhuanlan"], - help="内容类型: zvideo=视频, zhuanlan=专栏文章" + choices=["zvideo", "zhuanlan", "answer", "question"], + help="内容类型: zvideo=视频, zhuanlan=专栏文章, answer=回答, question=问题" ) parser.add_argument( @@ -135,8 +173,15 @@ def main(): # 提取元数据 if args.type == "zvideo": result = extract_zvideo(args.id, headless=args.headless) - else: # zhuanlan + elif args.type == "zhuanlan": result = extract_zhuanlan(args.id, headless=args.headless) + elif args.type == "answer": + result = extract_answer(args.id, headless=args.headless) + elif args.type == "question": + result = extract_question(args.id, headless=args.headless) + else: + print(f"不支持的类型: {args.type}") + sys.exit(1) # 输出结果 json_output = json.dumps(result, ensure_ascii=False, indent=2)