Master 4.0 (#2210)

* stage academic conversation

* stage document conversation

* fix buggy gradio version

* file dynamic load

* merge more academic plugins

* accelerate nltk

* feat: 为predict函数添加文件和URL读取功能
- 添加URL检测和网页内容提取功能，支持自动提取网页文本
- 添加文件路径识别和文件内容读取功能，支持private_upload路径格式
- 集成WebTextExtractor处理网页内容提取
- 集成TextContentLoader处理本地文件读取
- 支持文件路径与问题组合的智能处理

* back

* block unstable

---------

Co-authored-by: XiaoBoAI <liuboyin2019@ia.ac.cn>

crazy_functions/paper_fns/auto_git/handlers/base_handler.py

@@ -0,0 +1,386 @@
+from abc import ABC, abstractmethod
+from typing import List, Dict, Any
+from ..query_analyzer import SearchCriteria
+from ..sources.github_source import GitHubSource
+import asyncio
+import re
+from datetime import datetime
+
+class BaseHandler(ABC):
+    """处理器基类"""
+
+    def __init__(self, github: GitHubSource, llm_kwargs: Dict = None):
+        self.github = github
+        self.llm_kwargs = llm_kwargs or {}
+        self.ranked_repos = []  # 存储排序后的仓库列表
+
+    def _get_search_params(self, plugin_kwargs: Dict) -> Dict:
+        """获取搜索参数"""
+        return {
+            'max_repos': plugin_kwargs.get('max_repos', 150),  # 最大仓库数量，从30改为150
+            'max_details': plugin_kwargs.get('max_details', 80),  # 最多展示详情的仓库数量，新增参数
+            'search_multiplier': plugin_kwargs.get('search_multiplier', 3),  # 检索倍数
+            'min_stars': plugin_kwargs.get('min_stars', 0),  # 最少星标数
+        }
+
+    @abstractmethod
+    async def handle(
+            self,
+            criteria: SearchCriteria,
+            chatbot: List[List[str]],
+            history: List[List[str]],
+            system_prompt: str,
+            llm_kwargs: Dict[str, Any],
+            plugin_kwargs: Dict[str, Any],
+    ) -> str:
+        """处理查询"""
+        pass
+
+    async def _search_repositories(self, query: str, language: str = None, min_stars: int = 0,
+                                sort: str = "stars", per_page: int = 30) -> List[Dict]:
+        """搜索仓库"""
+        try:
+            # 构建查询字符串
+            if min_stars > 0 and "stars:>" not in query:
+                query += f" stars:>{min_stars}"
+                
+            if language and "language:" not in query:
+                query += f" language:{language}"
+                
+            # 执行搜索
+            result = await self.github.search_repositories(
+                query=query,
+                sort=sort,
+                per_page=per_page
+            )
+            
+            if result and "items" in result:
+                return result["items"]
+            return []
+        except Exception as e:
+            print(f"仓库搜索出错: {str(e)}")
+            return []
+
+    async def _search_bilingual_repositories(self, english_query: str, chinese_query: str, language: str = None, min_stars: int = 0,
+                                sort: str = "stars", per_page: int = 30) -> List[Dict]:
+        """同时搜索中英文仓库并合并结果"""
+        try:
+            # 搜索英文仓库
+            english_results = await self._search_repositories(
+                query=english_query,
+                language=language,
+                min_stars=min_stars,
+                sort=sort,
+                per_page=per_page
+            )
+            
+            # 搜索中文仓库
+            chinese_results = await self._search_repositories(
+                query=chinese_query,
+                language=language,
+                min_stars=min_stars,
+                sort=sort,
+                per_page=per_page
+            )
+            
+            # 合并结果，去除重复项
+            merged_results = []
+            seen_repos = set()
+            
+            # 优先添加英文结果
+            for repo in english_results:
+                repo_id = repo.get('id')
+                if repo_id and repo_id not in seen_repos:
+                    seen_repos.add(repo_id)
+                    merged_results.append(repo)
+            
+            # 添加中文结果（排除重复）
+            for repo in chinese_results:
+                repo_id = repo.get('id')
+                if repo_id and repo_id not in seen_repos:
+                    seen_repos.add(repo_id)
+                    merged_results.append(repo)
+            
+            # 按星标数重新排序
+            merged_results.sort(key=lambda x: x.get('stargazers_count', 0), reverse=True)
+            
+            return merged_results[:per_page]  # 返回合并后的前per_page个结果
+        except Exception as e:
+            print(f"双语仓库搜索出错: {str(e)}")
+            return []
+
+    async def _search_code(self, query: str, language: str = None, per_page: int = 30) -> List[Dict]:
+        """搜索代码"""
+        try:
+            # 构建查询字符串
+            if language and "language:" not in query:
+                query += f" language:{language}"
+                
+            # 执行搜索
+            result = await self.github.search_code(
+                query=query,
+                per_page=per_page
+            )
+            
+            if result and "items" in result:
+                return result["items"]
+            return []
+        except Exception as e:
+            print(f"代码搜索出错: {str(e)}")
+            return []
+
+    async def _search_bilingual_code(self, english_query: str, chinese_query: str, language: str = None, per_page: int = 30) -> List[Dict]:
+        """同时搜索中英文代码并合并结果"""
+        try:
+            # 搜索英文代码
+            english_results = await self._search_code(
+                query=english_query,
+                language=language,
+                per_page=per_page
+            )
+            
+            # 搜索中文代码
+            chinese_results = await self._search_code(
+                query=chinese_query,
+                language=language,
+                per_page=per_page
+            )
+            
+            # 合并结果，去除重复项
+            merged_results = []
+            seen_files = set()
+            
+            # 优先添加英文结果
+            for item in english_results:
+                # 使用文件URL作为唯一标识
+                file_url = item.get('html_url', '')
+                if file_url and file_url not in seen_files:
+                    seen_files.add(file_url)
+                    merged_results.append(item)
+            
+            # 添加中文结果（排除重复）
+            for item in chinese_results:
+                file_url = item.get('html_url', '')
+                if file_url and file_url not in seen_files:
+                    seen_files.add(file_url)
+                    merged_results.append(item)
+            
+            # 对结果进行排序，优先显示匹配度高的结果
+            # 由于无法直接获取匹配度，这里使用仓库的星标数作为替代指标
+            merged_results.sort(key=lambda x: x.get('repository', {}).get('stargazers_count', 0), reverse=True)
+            
+            return merged_results[:per_page]  # 返回合并后的前per_page个结果
+        except Exception as e:
+            print(f"双语代码搜索出错: {str(e)}")
+            return []
+
+    async def _search_users(self, query: str, per_page: int = 30) -> List[Dict]:
+        """搜索用户"""
+        try:
+            result = await self.github.search_users(
+                query=query,
+                per_page=per_page
+            )
+            
+            if result and "items" in result:
+                return result["items"]
+            return []
+        except Exception as e:
+            print(f"用户搜索出错: {str(e)}")
+            return []
+
+    async def _search_bilingual_users(self, english_query: str, chinese_query: str, per_page: int = 30) -> List[Dict]:
+        """同时搜索中英文用户并合并结果"""
+        try:
+            # 搜索英文用户
+            english_results = await self._search_users(
+                query=english_query,
+                per_page=per_page
+            )
+            
+            # 搜索中文用户
+            chinese_results = await self._search_users(
+                query=chinese_query,
+                per_page=per_page
+            )
+            
+            # 合并结果，去除重复项
+            merged_results = []
+            seen_users = set()
+            
+            # 优先添加英文结果
+            for user in english_results:
+                user_id = user.get('id')
+                if user_id and user_id not in seen_users:
+                    seen_users.add(user_id)
+                    merged_results.append(user)
+            
+            # 添加中文结果（排除重复）
+            for user in chinese_results:
+                user_id = user.get('id')
+                if user_id and user_id not in seen_users:
+                    seen_users.add(user_id)
+                    merged_results.append(user)
+            
+            # 按关注者数量进行排序
+            merged_results.sort(key=lambda x: x.get('followers', 0), reverse=True)
+            
+            return merged_results[:per_page]  # 返回合并后的前per_page个结果
+        except Exception as e:
+            print(f"双语用户搜索出错: {str(e)}")
+            return []
+
+    async def _search_topics(self, query: str, per_page: int = 30) -> List[Dict]:
+        """搜索主题"""
+        try:
+            result = await self.github.search_topics(
+                query=query,
+                per_page=per_page
+            )
+            
+            if result and "items" in result:
+                return result["items"]
+            return []
+        except Exception as e:
+            print(f"主题搜索出错: {str(e)}")
+            return []
+
+    async def _search_bilingual_topics(self, english_query: str, chinese_query: str, per_page: int = 30) -> List[Dict]:
+        """同时搜索中英文主题并合并结果"""
+        try:
+            # 搜索英文主题
+            english_results = await self._search_topics(
+                query=english_query,
+                per_page=per_page
+            )
+            
+            # 搜索中文主题
+            chinese_results = await self._search_topics(
+                query=chinese_query,
+                per_page=per_page
+            )
+            
+            # 合并结果，去除重复项
+            merged_results = []
+            seen_topics = set()
+            
+            # 优先添加英文结果
+            for topic in english_results:
+                topic_name = topic.get('name')
+                if topic_name and topic_name not in seen_topics:
+                    seen_topics.add(topic_name)
+                    merged_results.append(topic)
+            
+            # 添加中文结果（排除重复）
+            for topic in chinese_results:
+                topic_name = topic.get('name')
+                if topic_name and topic_name not in seen_topics:
+                    seen_topics.add(topic_name)
+                    merged_results.append(topic)
+            
+            # 可以按流行度进行排序（如果有）
+            if merged_results and 'featured' in merged_results[0]:
+                merged_results.sort(key=lambda x: x.get('featured', False), reverse=True)
+            
+            return merged_results[:per_page]  # 返回合并后的前per_page个结果
+        except Exception as e:
+            print(f"双语主题搜索出错: {str(e)}")
+            return []
+
+    async def _get_repo_details(self, repos: List[Dict]) -> List[Dict]:
+        """获取仓库详细信息"""
+        enhanced_repos = []
+        
+        for repo in repos:
+            try:
+                # 获取README信息
+                owner = repo.get('owner', {}).get('login') if repo.get('owner') is not None else None
+                repo_name = repo.get('name')
+                
+                if owner and repo_name:
+                    readme = await self.github.get_repo_readme(owner, repo_name)
+                    if readme and "decoded_content" in readme:
+                        # 提取README的前1000个字符作为摘要
+                        repo['readme_excerpt'] = readme["decoded_content"][:1000] + "..."
+                    
+                    # 获取语言使用情况
+                    languages = await self.github.get_repository_languages(owner, repo_name)
+                    if languages:
+                        repo['languages_detail'] = languages
+                    
+                    # 获取最新发布版本
+                    releases = await self.github.get_repo_releases(owner, repo_name, per_page=1)
+                    if releases and len(releases) > 0:
+                        repo['latest_release'] = releases[0]
+                    
+                    # 获取主题标签
+                    topics = await self.github.get_repo_topics(owner, repo_name)
+                    if topics and "names" in topics:
+                        repo['topics'] = topics["names"]
+                
+                enhanced_repos.append(repo)
+            except Exception as e:
+                print(f"获取仓库 {repo.get('full_name')} 详情时出错: {str(e)}")
+                enhanced_repos.append(repo)  # 添加原始仓库信息
+                
+        return enhanced_repos
+
+    def _format_repos(self, repos: List[Dict]) -> str:
+        """格式化仓库列表"""
+        formatted = []
+        
+        for i, repo in enumerate(repos, 1):
+            # 构建仓库URL
+            repo_url = repo.get('html_url', '')
+            
+            # 构建完整的引用
+            reference = (
+                f"{i}. **{repo.get('full_name', '')}**\n"
+                f"   - 描述: {repo.get('description', 'N/A')}\n"
+                f"   - 语言: {repo.get('language', 'N/A')}\n"
+                f"   - 星标: {repo.get('stargazers_count', 0)}\n"
+                f"   - Fork数: {repo.get('forks_count', 0)}\n"
+                f"   - 更新时间: {repo.get('updated_at', 'N/A')[:10]}\n"
+                f"   - 创建时间: {repo.get('created_at', 'N/A')[:10]}\n"
+                f"   - URL: <a href='{repo_url}' target='_blank'>{repo_url}</a>\n"
+            )
+            
+            # 添加主题标签(如果有)
+            if repo.get('topics'):
+                topics_str = ", ".join(repo.get('topics'))
+                reference += f"   - 主题标签: {topics_str}\n"
+                
+            # 添加最新发布版本(如果有)
+            if repo.get('latest_release'):
+                release = repo.get('latest_release')
+                reference += f"   - 最新版本: {release.get('tag_name', 'N/A')} ({release.get('published_at', 'N/A')[:10]})\n"
+                
+            # 添加README摘要(如果有)
+            if repo.get('readme_excerpt'):
+                # 截断README，只取前300个字符
+                readme_short = repo.get('readme_excerpt')[:300].replace('\n', ' ')
+                reference += f"   - README摘要: {readme_short}...\n"
+                
+            formatted.append(reference)
+            
+        return "\n".join(formatted)
+
+    def _generate_apology_prompt(self, criteria: SearchCriteria) -> str:
+        """生成道歉提示"""
+        return f"""很抱歉，我们未能找到与"{criteria.main_topic}"相关的GitHub项目。
+
+可能的原因：
+1. 搜索词过于具体或冷门
+2. 星标数要求过高
+3. 编程语言限制过于严格
+
+建议解决方案：
+   1. 尝试使用更通用的关键词
+   2. 降低最低星标数要求
+   3. 移除或更改编程语言限制
+请根据以上建议调整后重试。"""
+
+    def _get_current_time(self) -> str:
+        """获取当前时间信息"""
+        now = datetime.now()
+        return now.strftime("%Y年%m月%d日") 

crazy_functions/paper_fns/auto_git/handlers/code_handler.py

@@ -0,0 +1,156 @@
+from typing import List, Dict, Any
+from .base_handler import BaseHandler
+from ..query_analyzer import SearchCriteria
+import asyncio
+
+class CodeSearchHandler(BaseHandler):
+    """代码搜索处理器"""
+    
+    def __init__(self, github, llm_kwargs=None):
+        super().__init__(github, llm_kwargs)
+    
+    async def handle(
+        self,
+        criteria: SearchCriteria,
+        chatbot: List[List[str]],
+        history: List[List[str]],
+        system_prompt: str,
+        llm_kwargs: Dict[str, Any],
+        plugin_kwargs: Dict[str, Any],
+    ) -> str:
+        """处理代码搜索请求，返回最终的prompt"""
+        
+        search_params = self._get_search_params(plugin_kwargs)
+        
+        # 搜索代码
+        code_results = await self._search_bilingual_code(
+            english_query=criteria.github_params["query"],
+            chinese_query=criteria.github_params["chinese_query"],
+            language=criteria.language,
+            per_page=search_params['max_repos']
+        )
+        
+        if not code_results:
+            return self._generate_apology_prompt(criteria)
+            
+        # 获取代码文件内容
+        enhanced_code_results = await self._get_code_details(code_results[:search_params['max_details']])
+        self.ranked_repos = [item["repository"] for item in enhanced_code_results if "repository" in item]
+        
+        if not enhanced_code_results:
+            return self._generate_apology_prompt(criteria)
+        
+        # 构建最终的prompt
+        current_time = self._get_current_time()
+        final_prompt = f"""当前时间: {current_time}
+
+基于用户对{criteria.main_topic}的查询，我找到了以下代码示例。
+
+代码搜索结果:
+{self._format_code_results(enhanced_code_results)}
+
+请提供:
+
+1. 对于搜索的"{criteria.main_topic}"主题的综合解释:
+   - 概念和原理介绍
+   - 常见实现方法和技术
+   - 最佳实践和注意事项
+
+2. 对每个代码示例:
+   - 解释代码的主要功能和实现方式
+   - 分析代码质量、可读性和效率
+   - 指出代码中的亮点和潜在改进空间
+   - 说明代码的适用场景
+
+3. 代码实现比较:
+   - 不同实现方法的优缺点
+   - 性能和可维护性分析
+   - 适用不同场景的实现建议
+
+4. 学习建议:
+   - 理解和使用这些代码需要的背景知识
+   - 如何扩展或改进所展示的代码
+   - 进一步学习相关技术的资源
+
+重要提示:
+- 深入解释代码的核心逻辑和实现思路
+- 提供专业、技术性的分析
+- 优先关注代码的实现质量和技术价值
+- 当代码实现有问题时，指出并提供改进建议
+- 对于复杂代码，分解解释其组成部分
+- 根据用户查询的具体问题提供针对性答案
+- 所有链接请使用<a href='链接地址' target='_blank'>链接文本</a>格式，确保链接在新窗口打开
+
+使用markdown格式提供清晰的分节回复。
+"""
+        
+        return final_prompt
+
+    async def _get_code_details(self, code_results: List[Dict]) -> List[Dict]:
+        """获取代码详情"""
+        enhanced_results = []
+        
+        for item in code_results:
+            try:
+                repo = item.get('repository', {})
+                file_path = item.get('path', '')
+                repo_name = repo.get('full_name', '')
+                
+                if repo_name and file_path:
+                    owner, repo_name = repo_name.split('/')
+                    
+                    # 获取文件内容
+                    file_content = await self.github.get_file_content(owner, repo_name, file_path)
+                    if file_content and "decoded_content" in file_content:
+                        item['code_content'] = file_content["decoded_content"]
+                        
+                        # 获取仓库基本信息
+                        repo_details = await self.github.get_repo(owner, repo_name)
+                        if repo_details:
+                            item['repository'] = repo_details
+                
+                enhanced_results.append(item)
+            except Exception as e:
+                print(f"获取代码详情时出错: {str(e)}")
+                enhanced_results.append(item)  # 添加原始信息
+                
+        return enhanced_results
+
+    def _format_code_results(self, code_results: List[Dict]) -> str:
+        """格式化代码搜索结果"""
+        formatted = []
+        
+        for i, item in enumerate(code_results, 1):
+            # 构建仓库信息
+            repo = item.get('repository', {})
+            repo_name = repo.get('full_name', 'N/A')
+            repo_url = repo.get('html_url', '')
+            stars = repo.get('stargazers_count', 0)
+            language = repo.get('language', 'N/A')
+            
+            # 构建文件信息
+            file_path = item.get('path', 'N/A')
+            file_url = item.get('html_url', '')
+            
+            # 构建代码内容
+            code_content = item.get('code_content', '')
+            if code_content:
+                # 只显示前30行代码
+                code_lines = code_content.split("\n")
+                if len(code_lines) > 30:
+                    displayed_code = "\n".join(code_lines[:30]) + "\n... (代码太长已截断) ..."
+                else:
+                    displayed_code = code_content
+            else:
+                displayed_code = "(代码内容获取失败)"
+            
+            reference = (
+                f"### {i}. {file_path} (在 {repo_name} 中)\n\n"
+                f"- **仓库**: <a href='{repo_url}' target='_blank'>{repo_name}</a> (⭐ {stars}, 语言: {language})\n"
+                f"- **文件路径**: <a href='{file_url}' target='_blank'>{file_path}</a>\n\n"
+                f"```{language.lower()}\n{displayed_code}\n```\n\n"
+            )
+            
+            formatted.append(reference)
+            
+        return "\n".join(formatted) 

crazy_functions/paper_fns/auto_git/handlers/repo_handler.py

@@ -0,0 +1,192 @@
+from typing import List, Dict, Any
+from .base_handler import BaseHandler
+from ..query_analyzer import SearchCriteria
+import asyncio
+
+class RepositoryHandler(BaseHandler):
+    """仓库搜索处理器"""
+    
+    def __init__(self, github, llm_kwargs=None):
+        super().__init__(github, llm_kwargs)
+    
+    async def handle(
+        self,
+        criteria: SearchCriteria,
+        chatbot: List[List[str]],
+        history: List[List[str]],
+        system_prompt: str,
+        llm_kwargs: Dict[str, Any],
+        plugin_kwargs: Dict[str, Any],
+    ) -> str:
+        """处理仓库搜索请求，返回最终的prompt"""
+        
+        search_params = self._get_search_params(plugin_kwargs)
+        
+        # 如果是特定仓库查询
+        if criteria.repo_id:
+            try:
+                owner, repo = criteria.repo_id.split('/')
+                repo_details = await self.github.get_repo(owner, repo)
+                if repo_details:
+                    # 获取推荐的相似仓库
+                    similar_repos = await self.github.get_repo_recommendations(criteria.repo_id, limit=5)
+                    
+                    # 添加详细信息
+                    all_repos = [repo_details] + similar_repos
+                    enhanced_repos = await self._get_repo_details(all_repos)
+                    
+                    self.ranked_repos = enhanced_repos
+                    
+                    # 构建最终的prompt
+                    current_time = self._get_current_time()
+                    final_prompt = self._build_repo_detail_prompt(enhanced_repos[0], enhanced_repos[1:], current_time)
+                    return final_prompt
+                else:
+                    return self._generate_apology_prompt(criteria)
+            except Exception as e:
+                print(f"处理特定仓库时出错: {str(e)}")
+                return self._generate_apology_prompt(criteria)
+        
+        # 一般仓库搜索
+        repos = await self._search_bilingual_repositories(
+            english_query=criteria.github_params["query"],
+            chinese_query=criteria.github_params["chinese_query"],
+            language=criteria.language,
+            min_stars=criteria.min_stars,
+            per_page=search_params['max_repos']
+        )
+        
+        if not repos:
+            return self._generate_apology_prompt(criteria)
+        
+        # 获取仓库详情
+        enhanced_repos = await self._get_repo_details(repos[:search_params['max_details']])  # 使用max_details参数
+        self.ranked_repos = enhanced_repos
+        
+        if not enhanced_repos:
+            return self._generate_apology_prompt(criteria)
+        
+        # 构建最终的prompt
+        current_time = self._get_current_time()
+        final_prompt = f"""当前时间: {current_time}
+
+基于用户对{criteria.main_topic}的兴趣，以下是相关的GitHub仓库。
+
+可供推荐的GitHub仓库:
+{self._format_repos(enhanced_repos)}
+
+请提供:
+1. 按功能、用途或成熟度对仓库进行分组
+
+2. 对每个仓库：
+   - 简要描述其主要功能和用途
+   - 分析其技术特点和优势
+   - 说明其适用场景和使用难度
+   - 指出其与同类产品相比的独特优势
+   - 解释其星标数量和活跃度代表的意义
+
+3. 使用建议：
+   - 新手最适合入门的仓库
+   - 生产环境中最稳定可靠的选择
+   - 最新技术栈或创新方案的代表
+   - 学习特定技术的最佳资源
+
+4. 相关资源：
+   - 学习这些项目需要的前置知识
+   - 项目间的关联和技术栈兼容性
+   - 可能的使用组合方案
+
+重要提示:
+- 重点解释为什么每个仓库值得关注
+- 突出项目间的关联性和差异性
+- 考虑用户不同水平的需求(初学者vs专业人士)
+- 在介绍项目时，使用<a href='链接' target='_blank'>文本</a>格式，确保链接在新窗口打开
+- 根据仓库的活跃度、更新频率、维护状态提供使用建议
+- 仅基于提供的信息，不要做无根据的猜测
+- 在信息缺失或不明确时，坦诚说明
+
+使用markdown格式提供清晰的分节回复。
+"""
+        
+        return final_prompt
+
+    def _build_repo_detail_prompt(self, main_repo: Dict, similar_repos: List[Dict], current_time: str) -> str:
+        """构建仓库详情prompt"""
+        
+        # 提取README摘要
+        readme_content = "未提供"
+        if main_repo.get('readme_excerpt'):
+            readme_content = main_repo.get('readme_excerpt')
+            
+        # 构建语言分布
+        languages = main_repo.get('languages_detail', {})
+        lang_distribution = []
+        if languages:
+            total = sum(languages.values())
+            for lang, bytes_val in languages.items():
+                percentage = (bytes_val / total) * 100
+                lang_distribution.append(f"{lang}: {percentage:.1f}%")
+        
+        lang_str = "未知"
+        if lang_distribution:
+            lang_str = ", ".join(lang_distribution)
+            
+        # 构建最终prompt
+        prompt = f"""当前时间: {current_time}
+
+## 主要仓库信息
+
+### {main_repo.get('full_name')}
+
+- **描述**: {main_repo.get('description', '未提供')}
+- **星标数**: {main_repo.get('stargazers_count', 0)}
+- **Fork数**: {main_repo.get('forks_count', 0)}
+- **Watch数**: {main_repo.get('watchers_count', 0)}
+- **Issues数**: {main_repo.get('open_issues_count', 0)}
+- **语言分布**: {lang_str}
+- **许可证**: {main_repo.get('license', {}).get('name', '未指定') if main_repo.get('license') is not None else '未指定'}
+- **创建时间**: {main_repo.get('created_at', '')[:10]}
+- **最近更新**: {main_repo.get('updated_at', '')[:10]}
+- **主题标签**: {', '.join(main_repo.get('topics', ['无']))}
+- **GitHub链接**: <a href='{main_repo.get('html_url')}' target='_blank'>链接</a>
+
+### README摘要:
+{readme_content}
+
+## 类似仓库:
+{self._format_repos(similar_repos)}
+
+请提供以下内容:
+
+1. **项目概述**
+   - 详细解释{main_repo.get('name', '')}项目的主要功能和用途
+   - 分析其技术特点、架构和实现原理
+   - 讨论其在所属领域的地位和影响力
+   - 评估项目成熟度和稳定性
+
+2. **优势与特点**
+   - 与同类项目相比的独特优势
+   - 显著的技术创新或设计模式
+   - 值得学习或借鉴的代码实践
+
+3. **使用场景**
+   - 最适合的应用场景
+   - 潜在的使用限制和注意事项
+   - 入门门槛和学习曲线评估
+   - 产品级应用的可行性分析
+
+4. **资源与生态**
+   - 相关学习资源推荐
+   - 配套工具和库的建议
+   - 社区支持和活跃度评估
+
+5. **类似项目对比**
+   - 与列出的类似项目的详细对比
+   - 不同场景下的最佳选择建议
+   - 潜在的互补使用方案
+
+提示：所有链接请使用<a href='链接地址' target='_blank'>链接文本</a>格式，确保链接在新窗口打开。
+
+请以专业、客观的技术分析角度回答，使用markdown格式提供结构化信息。
+"""
+        return prompt 

crazy_functions/paper_fns/auto_git/handlers/topic_handler.py

@@ -0,0 +1,217 @@
+from typing import List, Dict, Any
+from .base_handler import BaseHandler
+from ..query_analyzer import SearchCriteria
+import asyncio
+
+class TopicHandler(BaseHandler):
+    """主题搜索处理器"""
+    
+    def __init__(self, github, llm_kwargs=None):
+        super().__init__(github, llm_kwargs)
+    
+    async def handle(
+        self,
+        criteria: SearchCriteria,
+        chatbot: List[List[str]],
+        history: List[List[str]],
+        system_prompt: str,
+        llm_kwargs: Dict[str, Any],
+        plugin_kwargs: Dict[str, Any],
+    ) -> str:
+        """处理主题搜索请求，返回最终的prompt"""
+        
+        search_params = self._get_search_params(plugin_kwargs)
+        
+        # 搜索主题
+        topics = await self._search_bilingual_topics(
+            english_query=criteria.github_params["query"],
+            chinese_query=criteria.github_params["chinese_query"],
+            per_page=search_params['max_repos']
+        )
+        
+        if not topics:
+            # 尝试用主题搜索仓库
+            search_query = criteria.github_params["query"]
+            chinese_search_query = criteria.github_params["chinese_query"]
+            if "topic:" not in search_query:
+                search_query += " topic:" + criteria.main_topic.replace(" ", "-")
+            if "topic:" not in chinese_search_query:
+                chinese_search_query += " topic:" + criteria.main_topic.replace(" ", "-")
+            
+            repos = await self._search_bilingual_repositories(
+                english_query=search_query,
+                chinese_query=chinese_search_query,
+                language=criteria.language,
+                min_stars=criteria.min_stars,
+                per_page=search_params['max_repos']
+            )
+            
+            if not repos:
+                return self._generate_apology_prompt(criteria)
+                
+            # 获取仓库详情
+            enhanced_repos = await self._get_repo_details(repos[:10])
+            self.ranked_repos = enhanced_repos
+            
+            if not enhanced_repos:
+                return self._generate_apology_prompt(criteria)
+                
+            # 构建基于主题的仓库列表prompt
+            current_time = self._get_current_time()
+            final_prompt = f"""当前时间: {current_time}
+
+基于用户对主题"{criteria.main_topic}"的查询，我找到了以下相关GitHub仓库。
+
+主题相关仓库:
+{self._format_repos(enhanced_repos)}
+
+请提供:
+
+1. 主题综述:
+   - "{criteria.main_topic}"主题的概述和重要性
+   - 该主题在技术领域中的应用和发展趋势
+   - 主题相关的主要技术栈和知识体系
+
+2. 仓库分析:
+   - 按功能、技术栈或应用场景对仓库进行分类
+   - 每个仓库在该主题领域的定位和贡献
+   - 不同仓库间的技术路线对比
+
+3. 学习路径建议:
+   - 初学者入门该主题的推荐仓库和学习顺序
+   - 进阶学习的关键仓库和技术要点
+   - 实际应用中的最佳实践选择
+
+4. 技术生态分析:
+   - 该主题下的主流工具和库
+   - 社区活跃度和维护状况
+   - 与其他相关技术的集成方案
+
+重要提示:
+- 主题"{criteria.main_topic}"是用户查询的核心，请围绕此主题展开分析
+- 注重仓库质量评估和使用建议
+- 提供基于事实的客观技术分析
+- 在介绍仓库时使用<a href='链接地址' target='_blank'>链接文本</a>格式，确保链接在新窗口打开
+- 考虑不同技术水平用户的需求
+
+使用markdown格式提供清晰的分节回复。
+"""
+            return final_prompt
+            
+        # 如果找到了主题，则获取主题下的热门仓库
+        topic_repos = []
+        for topic in topics[:5]:  # 增加到5个主题
+            topic_name = topic.get('name', '')
+            if topic_name:
+                # 搜索该主题下的仓库
+                repos = await self._search_repositories(
+                    query=f"topic:{topic_name}",
+                    language=criteria.language,
+                    min_stars=criteria.min_stars,
+                    per_page=20  # 每个主题最多20个仓库
+                )
+                
+                if repos:
+                    for repo in repos:
+                        repo['topic_source'] = topic_name
+                        topic_repos.append(repo)
+        
+        if not topic_repos:
+            return self._generate_apology_prompt(criteria)
+            
+        # 获取前N个仓库的详情
+        enhanced_repos = await self._get_repo_details(topic_repos[:search_params['max_details']])
+        self.ranked_repos = enhanced_repos
+        
+        if not enhanced_repos:
+            return self._generate_apology_prompt(criteria)
+            
+        # 构建最终的prompt
+        current_time = self._get_current_time()
+        final_prompt = f"""当前时间: {current_time}
+
+基于用户对"{criteria.main_topic}"主题的查询，我找到了以下相关GitHub主题和仓库。
+
+主题相关仓库:
+{self._format_topic_repos(enhanced_repos)}
+
+请提供:
+
+1. 主题概述:
+   - 对"{criteria.main_topic}"相关主题的介绍和技术背景
+   - 这些主题在软件开发中的重要性和应用范围
+   - 主题间的关联性和技术演进路径
+
+2. 精选仓库分析:
+   - 每个主题下最具代表性的仓库详解
+   - 仓库的技术亮点和创新点
+   - 使用场景和技术成熟度评估
+
+3. 技术趋势分析:
+   - 基于主题和仓库活跃度的技术发展趋势
+   - 新兴解决方案和传统方案的对比
+   - 未来可能的技术方向预测
+
+4. 实践建议:
+   - 不同应用场景下的最佳仓库选择
+   - 学习路径和资源推荐
+   - 实际项目中的应用策略
+
+重要提示:
+- 将分析重点放在主题的技术内涵和价值上
+- 突出主题间的关联性和技术演进脉络
+- 提供基于数据(星标数、更新频率等)的客观分析
+- 考虑不同技术背景用户的需求
+- 所有链接请使用<a href='链接地址' target='_blank'>链接文本</a>格式，确保链接在新窗口打开
+
+使用markdown格式提供清晰的分节回复。
+"""
+        
+        return final_prompt
+        
+    def _format_topic_repos(self, repos: List[Dict]) -> str:
+        """按主题格式化仓库列表"""
+        # 按主题分组
+        topics_dict = {}
+        for repo in repos:
+            topic = repo.get('topic_source', '其他')
+            if topic not in topics_dict:
+                topics_dict[topic] = []
+            topics_dict[topic].append(repo)
+        
+        # 格式化输出
+        formatted = []
+        for topic, topic_repos in topics_dict.items():
+            formatted.append(f"## 主题: {topic}\n")
+            
+            for i, repo in enumerate(topic_repos, 1):
+                # 构建仓库URL
+                repo_url = repo.get('html_url', '')
+                
+                # 构建引用
+                reference = (
+                    f"{i}. **{repo.get('full_name', '')}**\n"
+                    f"   - 描述: {repo.get('description', 'N/A')}\n"
+                    f"   - 语言: {repo.get('language', 'N/A')}\n"
+                    f"   - 星标: {repo.get('stargazers_count', 0)}\n"
+                    f"   - Fork数: {repo.get('forks_count', 0)}\n"
+                    f"   - 更新时间: {repo.get('updated_at', 'N/A')[:10]}\n"
+                    f"   - URL: <a href='{repo_url}' target='_blank'>{repo_url}</a>\n"
+                )
+                
+                # 添加主题标签(如果有)
+                if repo.get('topics'):
+                    topics_str = ", ".join(repo.get('topics'))
+                    reference += f"   - 主题标签: {topics_str}\n"
+                
+                # 添加README摘要(如果有)
+                if repo.get('readme_excerpt'):
+                    # 截断README，只取前200个字符
+                    readme_short = repo.get('readme_excerpt')[:200].replace('\n', ' ')
+                    reference += f"   - README摘要: {readme_short}...\n"
+                
+                formatted.append(reference)
+            
+            formatted.append("\n")  # 主题之间添加空行
+            
+        return "\n".join(formatted) 

crazy_functions/paper_fns/auto_git/handlers/user_handler.py

@@ -0,0 +1,164 @@
+from typing import List, Dict, Any
+from .base_handler import BaseHandler
+from ..query_analyzer import SearchCriteria
+import asyncio
+
+class UserSearchHandler(BaseHandler):
+    """用户搜索处理器"""
+    
+    def __init__(self, github, llm_kwargs=None):
+        super().__init__(github, llm_kwargs)
+    
+    async def handle(
+        self,
+        criteria: SearchCriteria,
+        chatbot: List[List[str]],
+        history: List[List[str]],
+        system_prompt: str,
+        llm_kwargs: Dict[str, Any],
+        plugin_kwargs: Dict[str, Any],
+    ) -> str:
+        """处理用户搜索请求，返回最终的prompt"""
+        
+        search_params = self._get_search_params(plugin_kwargs)
+        
+        # 搜索用户
+        users = await self._search_bilingual_users(
+            english_query=criteria.github_params["query"],
+            chinese_query=criteria.github_params["chinese_query"],
+            per_page=search_params['max_repos']
+        )
+        
+        if not users:
+            return self._generate_apology_prompt(criteria)
+            
+        # 获取用户详情和仓库
+        enhanced_users = await self._get_user_details(users[:search_params['max_details']])
+        self.ranked_repos = []  # 添加用户top仓库进行展示
+        
+        for user in enhanced_users:
+            if user.get('top_repos'):
+                self.ranked_repos.extend(user.get('top_repos'))
+        
+        if not enhanced_users:
+            return self._generate_apology_prompt(criteria)
+        
+        # 构建最终的prompt
+        current_time = self._get_current_time()
+        final_prompt = f"""当前时间: {current_time}
+
+基于用户对{criteria.main_topic}的查询，我找到了以下GitHub用户。
+
+GitHub用户搜索结果:
+{self._format_users(enhanced_users)}
+
+请提供:
+
+1. 用户综合分析:
+   - 各开发者的专业领域和技术专长
+   - 他们在GitHub开源社区的影响力
+   - 技术实力和项目质量评估
+
+2. 对每位开发者:
+   - 其主要贡献领域和技术栈
+   - 代表性项目及其价值
+   - 编程风格和技术特点
+   - 在相关领域的影响力
+
+3. 项目推荐:
+   - 针对用户查询的最有价值项目
+   - 值得学习和借鉴的代码实践
+   - 不同用户项目的相互补充关系
+
+4. 如何学习和使用:
+   - 如何从这些开发者项目中学习
+   - 最适合入门学习的项目
+   - 进阶学习的路径建议
+
+重要提示:
+- 关注开发者的技术专长和核心贡献
+- 分析其开源项目的技术价值
+- 根据用户的原始查询提供相关建议
+- 避免过度赞美或主观评价
+- 基于事实数据(项目数、星标数等)进行客观分析
+- 所有链接请使用<a href='链接地址' target='_blank'>链接文本</a>格式，确保链接在新窗口打开
+
+使用markdown格式提供清晰的分节回复。
+"""
+        
+        return final_prompt
+
+    async def _get_user_details(self, users: List[Dict]) -> List[Dict]:
+        """获取用户详情和仓库"""
+        enhanced_users = []
+        
+        for user in users:
+            try:
+                username = user.get('login')
+                
+                if username:
+                    # 获取用户详情
+                    user_details = await self.github.get_user(username)
+                    if user_details:
+                        user.update(user_details)
+                    
+                    # 获取用户仓库
+                    repos = await self.github.get_user_repos(
+                        username,
+                        sort="stars",
+                        per_page=10  # 增加到10个仓库
+                    )
+                    if repos:
+                        user['top_repos'] = repos
+                
+                enhanced_users.append(user)
+            except Exception as e:
+                print(f"获取用户 {user.get('login')} 详情时出错: {str(e)}")
+                enhanced_users.append(user)  # 添加原始信息
+                
+        return enhanced_users
+
+    def _format_users(self, users: List[Dict]) -> str:
+        """格式化用户列表"""
+        formatted = []
+        
+        for i, user in enumerate(users, 1):
+            # 构建用户信息
+            username = user.get('login', 'N/A')
+            name = user.get('name', username)
+            profile_url = user.get('html_url', '')
+            bio = user.get('bio', '无简介')
+            followers = user.get('followers', 0)
+            public_repos = user.get('public_repos', 0)
+            company = user.get('company', '未指定')
+            location = user.get('location', '未指定')
+            blog = user.get('blog', '')
+            
+            user_info = (
+                f"### {i}. {name} (@{username})\n\n"
+                f"- **简介**: {bio}\n"
+                f"- **关注者**: {followers} | **公开仓库**: {public_repos}\n"
+                f"- **公司**: {company} | **地点**: {location}\n"
+                f"- **个人网站**: {blog}\n"
+                f"- **GitHub**: <a href='{profile_url}' target='_blank'>{username}</a>\n\n"
+            )
+            
+            # 添加用户的热门仓库
+            top_repos = user.get('top_repos', [])
+            if top_repos:
+                user_info += "**热门仓库**:\n\n"
+                for repo in top_repos:
+                    repo_name = repo.get('name', '')
+                    repo_url = repo.get('html_url', '')
+                    repo_desc = repo.get('description', '无描述')
+                    repo_stars = repo.get('stargazers_count', 0)
+                    repo_language = repo.get('language', '未指定')
+                    
+                    user_info += (
+                        f"- <a href='{repo_url}' target='_blank'>{repo_name}</a> - ⭐ {repo_stars}, {repo_language}\n"
+                        f"  {repo_desc}\n\n"
+                    )
+            
+            formatted.append(user_info)
+            
+        return "\n".join(formatted) 

crazy_functions/paper_fns/auto_git/query_analyzer.py

@@ -0,0 +1,356 @@
+from typing import Dict, List
+from dataclasses import dataclass
+import re
+
+@dataclass
+class SearchCriteria:
+    """搜索条件"""
+    query_type: str  # 查询类型: repo/code/user/topic
+    main_topic: str  # 主题
+    sub_topics: List[str]  # 子主题列表
+    language: str  # 编程语言
+    min_stars: int  # 最少星标数
+    github_params: Dict  # GitHub搜索参数
+    original_query: str = ""  # 原始查询字符串
+    repo_id: str = ""  # 特定仓库ID或名称
+
+class QueryAnalyzer:
+    """查询分析器"""
+
+    # 响应索引常量
+    BASIC_QUERY_INDEX = 0
+    GITHUB_QUERY_INDEX = 1
+    
+    def __init__(self):
+        self.valid_types = {
+            "repo": ["repository", "project", "library", "framework", "tool"],
+            "code": ["code", "snippet", "implementation", "function", "class", "algorithm"],
+            "user": ["user", "developer", "organization", "contributor", "maintainer"],
+            "topic": ["topic", "category", "tag", "field", "area", "domain"]
+        }
+
+    def analyze_query(self, query: str, chatbot: List, llm_kwargs: Dict):
+        """分析查询意图"""
+        from crazy_functions.crazy_utils import \
+            request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency as request_gpt
+        
+        # 1. 基本查询分析
+        type_prompt = f"""请分析这个与GitHub相关的查询，并严格按照以下XML格式回答：
+
+查询: {query}
+
+说明:
+1. 你的回答必须使用下面显示的XML标签，不要有任何标签外的文本
+2. 从以下选项中选择查询类型: repo/code/user/topic
+   - repo: 用于查找仓库、项目、框架或库
+   - code: 用于查找代码片段、函数实现或算法
+   - user: 用于查找用户、开发者或组织
+   - topic: 用于查找主题、类别或领域相关项目
+3. 识别主题和子主题
+4. 识别首选编程语言(如果有)
+5. 确定最低星标数(如果适用)
+
+必需格式:
+<query_type>此处回答</query_type>
+<main_topic>此处回答</main_topic>
+<sub_topics>子主题1, 子主题2, ...</sub_topics>
+<language>此处回答</language>
+<min_stars>此处回答</min_stars>
+
+示例回答:
+
+1. 仓库查询:
+查询: "查找有至少1000颗星的Python web框架"
+<query_type>repo</query_type>
+<main_topic>web框架</main_topic>
+<sub_topics>后端开发, HTTP服务器, ORM</sub_topics>
+<language>Python</language>
+<min_stars>1000</min_stars>
+
+2. 代码查询:
+查询: "如何用JavaScript实现防抖函数"
+<query_type>code</query_type>
+<main_topic>防抖函数</main_topic>
+<sub_topics>事件处理, 性能优化, 函数节流</sub_topics>
+<language>JavaScript</language>
+<min_stars>0</min_stars>"""
+
+        # 2. 生成英文搜索条件
+        github_prompt = f"""Optimize the following GitHub search query:
+
+Query: {query}
+
+Task: Convert the natural language query into an optimized GitHub search query.
+Please use English, regardless of the language of the input query.
+
+Available search fields and filters:
+1. Basic fields:
+   - in:name - Search in repository names
+   - in:description - Search in repository descriptions
+   - in:readme - Search in README files
+   - in:topic - Search in topics
+   - language:X - Filter by programming language
+   - user:X - Repositories from a specific user
+   - org:X - Repositories from a specific organization
+
+2. Code search fields:
+   - extension:X - Filter by file extension
+   - path:X - Filter by path
+   - filename:X - Filter by filename
+
+3. Metric filters:
+   - stars:>X - Has more than X stars
+   - forks:>X - Has more than X forks
+   - size:>X - Size greater than X KB
+   - created:>YYYY-MM-DD - Created after a specific date
+   - pushed:>YYYY-MM-DD - Updated after a specific date
+
+4. Other filters:
+   - is:public/private - Public or private repositories
+   - archived:true/false - Archived or not archived
+   - license:X - Specific license
+   - topic:X - Contains specific topic tag
+
+Examples:
+
+1. Query: "Find Python machine learning libraries with at least 1000 stars"
+<query>machine learning in:description language:python stars:>1000</query>
+
+2. Query: "Recently updated React UI component libraries"
+<query>UI components library in:readme in:description language:javascript topic:react pushed:>2023-01-01</query>
+
+3. Query: "Open source projects developed by Facebook"
+<query>org:facebook is:public</query>
+
+4. Query: "Depth-first search implementation in JavaScript"
+<query>depth first search in:file language:javascript</query>
+
+Please analyze the query and answer using only the XML tag:
+<query>Provide the optimized GitHub search query, using appropriate fields and operators</query>"""
+
+        # 3. 生成中文搜索条件
+        chinese_github_prompt = f"""优化以下GitHub搜索查询:
+
+查询: {query}
+
+任务: 将自然语言查询转换为优化的GitHub搜索查询语句。
+为了搜索中文内容，请提取原始查询的关键词并使用中文形式，同时保留GitHub特定的搜索语法为英文。
+
+可用的搜索字段和过滤器:
+1. 基本字段:
+   - in:name - 在仓库名称中搜索
+   - in:description - 在仓库描述中搜索
+   - in:readme - 在README文件中搜索
+   - in:topic - 在主题中搜索
+   - language:X - 按编程语言筛选
+   - user:X - 特定用户的仓库
+   - org:X - 特定组织的仓库
+
+2. 代码搜索字段:
+   - extension:X - 按文件扩展名筛选
+   - path:X - 按路径筛选
+   - filename:X - 按文件名筛选
+
+3. 指标过滤器:
+   - stars:>X - 有超过X颗星
+   - forks:>X - 有超过X个分支
+   - size:>X - 大小超过X KB
+   - created:>YYYY-MM-DD - 在特定日期后创建
+   - pushed:>YYYY-MM-DD - 在特定日期后更新
+
+4. 其他过滤器:
+   - is:public/private - 公开或私有仓库
+   - archived:true/false - 已归档或未归档
+   - license:X - 特定许可证
+   - topic:X - 含特定主题标签
+
+示例:
+
+1. 查询: "找有关机器学习的Python库，至少1000颗星"
+<query>机器学习 in:description language:python stars:>1000</query>
+
+2. 查询: "最近更新的React UI组件库"
+<query>UI 组件库 in:readme in:description language:javascript topic:react pushed:>2023-01-01</query>
+
+3. 查询: "微信小程序开发框架"
+<query>微信小程序 开发框架 in:name in:description in:readme</query>
+
+请分析查询并仅使用XML标签回答:
+<query>提供优化的GitHub搜索查询，使用适当的字段和运算符，保留中文关键词</query>"""
+
+        try:
+            # 构建提示数组
+            prompts = [
+                type_prompt,
+                github_prompt,
+                chinese_github_prompt,
+            ]
+
+            show_messages = [
+                "分析查询类型...",
+                "优化英文GitHub搜索参数...",
+                "优化中文GitHub搜索参数...",
+            ]
+
+            sys_prompts = [
+                "你是一个精通GitHub生态系统的专家，擅长分析与GitHub相关的查询。",
+                "You are a GitHub search expert, specialized in converting natural language queries into optimized GitHub search queries in English.",
+                "你是一个GitHub搜索专家，擅长处理查询并保留中文关键词进行搜索。",
+            ]
+            
+            # 使用同步方式调用LLM
+            responses = yield from request_gpt(
+                inputs_array=prompts,
+                inputs_show_user_array=show_messages,
+                llm_kwargs=llm_kwargs,
+                chatbot=chatbot,
+                history_array=[[] for _ in prompts],
+                sys_prompt_array=sys_prompts,
+                max_workers=3
+            )
+
+            # 从收集的响应中提取我们需要的内容
+            extracted_responses = []
+            for i in range(len(prompts)):
+                if (i * 2 + 1) < len(responses):
+                    response = responses[i * 2 + 1]
+                    if response is None:
+                        raise Exception(f"Response {i} is None")
+                    if not isinstance(response, str):
+                        try:
+                            response = str(response)
+                        except:
+                            raise Exception(f"Cannot convert response {i} to string")
+                    extracted_responses.append(response)
+                else:
+                    raise Exception(f"未收到第 {i + 1} 个响应")
+
+            # 解析基本信息
+            query_type = self._extract_tag(extracted_responses[self.BASIC_QUERY_INDEX], "query_type")
+            if not query_type:
+                print(
+                    f"Debug - Failed to extract query_type. Response was: {extracted_responses[self.BASIC_QUERY_INDEX]}")
+                raise Exception("无法提取query_type标签内容")
+            query_type = query_type.lower()
+
+            main_topic = self._extract_tag(extracted_responses[self.BASIC_QUERY_INDEX], "main_topic")
+            if not main_topic:
+                print(f"Debug - Failed to extract main_topic. Using query as fallback.")
+                main_topic = query
+
+            query_type = self._normalize_query_type(query_type, query)
+
+            # 提取子主题
+            sub_topics = []
+            sub_topics_text = self._extract_tag(extracted_responses[self.BASIC_QUERY_INDEX], "sub_topics")
+            if sub_topics_text:
+                sub_topics = [topic.strip() for topic in sub_topics_text.split(",")]
+
+            # 提取语言
+            language = self._extract_tag(extracted_responses[self.BASIC_QUERY_INDEX], "language")
+            
+            # 提取最低星标数
+            min_stars = 0
+            min_stars_text = self._extract_tag(extracted_responses[self.BASIC_QUERY_INDEX], "min_stars")
+            if min_stars_text and min_stars_text.isdigit():
+                min_stars = int(min_stars_text)
+
+            # 解析GitHub搜索参数 - 英文
+            english_github_query = self._extract_tag(extracted_responses[self.GITHUB_QUERY_INDEX], "query")
+            
+            # 解析GitHub搜索参数 - 中文
+            chinese_github_query = self._extract_tag(extracted_responses[2], "query")
+            
+            # 构建GitHub参数
+            github_params = {
+                "query": english_github_query,
+                "chinese_query": chinese_github_query,
+                "sort": "stars",  # 默认按星标排序
+                "order": "desc",  # 默认降序
+                "per_page": 30,   # 默认每页30条
+                "page": 1         # 默认第1页
+            }
+            
+            # 检查是否为特定仓库查询
+            repo_id = ""
+            if "repo:" in english_github_query or "repository:" in english_github_query:
+                repo_match = re.search(r'(repo|repository):([a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+)', english_github_query)
+                if repo_match:
+                    repo_id = repo_match.group(2)
+            
+            print(f"Debug - 提取的信息:")
+            print(f"查询类型: {query_type}")
+            print(f"主题: {main_topic}")
+            print(f"子主题: {sub_topics}")
+            print(f"语言: {language}")
+            print(f"最低星标数: {min_stars}")
+            print(f"英文GitHub参数: {english_github_query}")
+            print(f"中文GitHub参数: {chinese_github_query}")
+            print(f"特定仓库: {repo_id}")
+
+            # 更新返回的 SearchCriteria，包含中英文查询
+            return SearchCriteria(
+                query_type=query_type,
+                main_topic=main_topic,
+                sub_topics=sub_topics,
+                language=language,
+                min_stars=min_stars,
+                github_params=github_params,
+                original_query=query,
+                repo_id=repo_id
+            )
+
+        except Exception as e:
+            raise Exception(f"分析查询失败: {str(e)}")
+
+    def _normalize_query_type(self, query_type: str, query: str) -> str:
+        """规范化查询类型"""
+        if query_type in ["repo", "code", "user", "topic"]:
+            return query_type
+
+        query_lower = query.lower()
+        for type_name, keywords in self.valid_types.items():
+            for keyword in keywords:
+                if keyword in query_lower:
+                    return type_name
+
+        query_type_lower = query_type.lower()
+        for type_name, keywords in self.valid_types.items():
+            for keyword in keywords:
+                if keyword in query_type_lower:
+                    return type_name
+
+        return "repo"  # 默认返回repo类型
+
+    def _extract_tag(self, text: str, tag: str) -> str:
+        """提取标记内容"""
+        if not text:
+            return ""
+
+        # 标准XML格式（处理多行和特殊字符）
+        pattern = f"<{tag}>(.*?)</{tag}>"
+        match = re.search(pattern, text, re.DOTALL | re.IGNORECASE)
+        if match:
+            content = match.group(1).strip()
+            if content:
+                return content
+
+        # 备用模式
+        patterns = [
+            rf"<{tag}>\s*([\s\S]*?)\s*</{tag}>",  # 标准XML格式
+            rf"<{tag}>([\s\S]*?)(?:</{tag}>|$)",  # 未闭合的标签
+            rf"[{tag}]([\s\S]*?)[/{tag}]",  # 方括号格式
+            rf"{tag}:\s*(.*?)(?=\n\w|$)",  # 冒号格式
+            rf"<{tag}>\s*(.*?)(?=<|$)"  # 部分闭合
+        ]
+
+        # 尝试所有模式
+        for pattern in patterns:
+            match = re.search(pattern, text, re.IGNORECASE | re.DOTALL)
+            if match:
+                content = match.group(1).strip()
+                if content:  # 确保提取的内容不为空
+                    return content
+
+        # 如果所有模式都失败，返回空字符串
+        return "" 

crazy_functions/paper_fns/auto_git/sources/github_source.py

@@ -0,0 +1,701 @@
+import aiohttp
+import asyncio
+import base64
+import json
+import random
+from datetime import datetime
+from typing import List, Dict, Optional, Union, Any
+
+class GitHubSource:
+    """GitHub API实现"""
+
+    # 默认API密钥列表 - 可以放置多个GitHub令牌
+    API_KEYS = [
+        "github_pat_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+        "github_pat_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+        # "your_github_token_1",
+        # "your_github_token_2",
+        # "your_github_token_3"
+    ]
+
+    def __init__(self, api_key: Optional[Union[str, List[str]]] = None):
+        """初始化GitHub API客户端
+
+        Args:
+            api_key: GitHub个人访问令牌或令牌列表
+        """
+        if api_key is None:
+            self.api_keys = self.API_KEYS
+        elif isinstance(api_key, str):
+            self.api_keys = [api_key]
+        else:
+            self.api_keys = api_key
+
+        self._initialize()
+
+    def _initialize(self) -> None:
+        """初始化客户端，设置默认参数"""
+        self.base_url = "https://api.github.com"
+        self.headers = {
+            "Accept": "application/vnd.github+json",
+            "X-GitHub-Api-Version": "2022-11-28",
+            "User-Agent": "GitHub-API-Python-Client"
+        }
+
+        # 如果有可用的API密钥，随机选择一个
+        if self.api_keys:
+            selected_key = random.choice(self.api_keys)
+            self.headers["Authorization"] = f"Bearer {selected_key}"
+            print(f"已随机选择API密钥进行认证")
+        else:
+            print("警告: 未提供API密钥，将受到GitHub API请求限制")
+
+    async def _request(self, method: str, endpoint: str, params: Dict = None, data: Dict = None) -> Any:
+        """发送API请求
+
+        Args:
+            method: HTTP方法 (GET, POST, PUT, DELETE等)
+            endpoint: API端点
+            params: URL参数
+            data: 请求体数据
+
+        Returns:
+            解析后的响应JSON
+        """
+        async with aiohttp.ClientSession(headers=self.headers) as session:
+            url = f"{self.base_url}{endpoint}"
+
+            # 为调试目的打印请求信息
+            print(f"请求: {method} {url}")
+            if params:
+                print(f"参数: {params}")
+
+            # 发送请求
+            request_kwargs = {}
+            if params:
+                request_kwargs["params"] = params
+            if data:
+                request_kwargs["json"] = data
+
+            async with session.request(method, url, **request_kwargs) as response:
+                response_text = await response.text()
+
+                # 检查HTTP状态码
+                if response.status >= 400:
+                    print(f"API请求失败: HTTP {response.status}")
+                    print(f"响应内容: {response_text}")
+                    return None
+
+                # 解析JSON响应
+                try:
+                    return json.loads(response_text)
+                except json.JSONDecodeError:
+                    print(f"JSON解析错误: {response_text}")
+                    return None
+
+    # ===== 用户相关方法 =====
+
+    async def get_user(self, username: Optional[str] = None) -> Dict:
+        """获取用户信息
+
+        Args:
+            username: 指定用户名，不指定则获取当前授权用户
+
+        Returns:
+            用户信息字典
+        """
+        endpoint = "/user" if username is None else f"/users/{username}"
+        return await self._request("GET", endpoint)
+
+    async def get_user_repos(self, username: Optional[str] = None, sort: str = "updated",
+                            direction: str = "desc", per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取用户的仓库列表
+
+        Args:
+            username: 指定用户名，不指定则获取当前授权用户
+            sort: 排序方式 (created, updated, pushed, full_name)
+            direction: 排序方向 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            仓库列表
+        """
+        endpoint = "/user/repos" if username is None else f"/users/{username}/repos"
+        params = {
+            "sort": sort,
+            "direction": direction,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def get_user_starred(self, username: Optional[str] = None,
+                              per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取用户星标的仓库
+
+        Args:
+            username: 指定用户名，不指定则获取当前授权用户
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            星标仓库列表
+        """
+        endpoint = "/user/starred" if username is None else f"/users/{username}/starred"
+        params = {
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    # ===== 仓库相关方法 =====
+
+    async def get_repo(self, owner: str, repo: str) -> Dict:
+        """获取仓库信息
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+
+        Returns:
+            仓库信息
+        """
+        endpoint = f"/repos/{owner}/{repo}"
+        return await self._request("GET", endpoint)
+
+    async def get_repo_branches(self, owner: str, repo: str, per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取仓库的分支列表
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            分支列表
+        """
+        endpoint = f"/repos/{owner}/{repo}/branches"
+        params = {
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def get_repo_commits(self, owner: str, repo: str, sha: Optional[str] = None,
+                              path: Optional[str] = None, per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取仓库的提交历史
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            sha: 特定提交SHA或分支名
+            path: 文件路径筛选
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            提交列表
+        """
+        endpoint = f"/repos/{owner}/{repo}/commits"
+        params = {
+            "per_page": per_page,
+            "page": page
+        }
+        if sha:
+            params["sha"] = sha
+        if path:
+            params["path"] = path
+
+        return await self._request("GET", endpoint, params=params)
+
+    async def get_commit_details(self, owner: str, repo: str, commit_sha: str) -> Dict:
+        """获取特定提交的详情
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            commit_sha: 提交SHA
+
+        Returns:
+            提交详情
+        """
+        endpoint = f"/repos/{owner}/{repo}/commits/{commit_sha}"
+        return await self._request("GET", endpoint)
+
+    # ===== 内容相关方法 =====
+
+    async def get_file_content(self, owner: str, repo: str, path: str, ref: Optional[str] = None) -> Dict:
+        """获取文件内容
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            path: 文件路径
+            ref: 分支名、标签名或提交SHA
+
+        Returns:
+            文件内容信息
+        """
+        endpoint = f"/repos/{owner}/{repo}/contents/{path}"
+        params = {}
+        if ref:
+            params["ref"] = ref
+
+        response = await self._request("GET", endpoint, params=params)
+        if response and isinstance(response, dict) and "content" in response:
+            try:
+                # 解码Base64编码的文件内容
+                content = base64.b64decode(response["content"].encode()).decode()
+                response["decoded_content"] = content
+            except Exception as e:
+                print(f"解码文件内容时出错: {str(e)}")
+
+        return response
+
+    async def get_directory_content(self, owner: str, repo: str, path: str, ref: Optional[str] = None) -> List[Dict]:
+        """获取目录内容
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            path: 目录路径
+            ref: 分支名、标签名或提交SHA
+
+        Returns:
+            目录内容列表
+        """
+        # 注意：此方法与get_file_content使用相同的端点，但对于目录会返回列表
+        endpoint = f"/repos/{owner}/{repo}/contents/{path}"
+        params = {}
+        if ref:
+            params["ref"] = ref
+
+        return await self._request("GET", endpoint, params=params)
+
+    # ===== Issues相关方法 =====
+
+    async def get_issues(self, owner: str, repo: str, state: str = "open",
+                        sort: str = "created", direction: str = "desc",
+                        per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取仓库的Issues列表
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            state: Issue状态 (open, closed, all)
+            sort: 排序方式 (created, updated, comments)
+            direction: 排序方向 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            Issues列表
+        """
+        endpoint = f"/repos/{owner}/{repo}/issues"
+        params = {
+            "state": state,
+            "sort": sort,
+            "direction": direction,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def get_issue(self, owner: str, repo: str, issue_number: int) -> Dict:
+        """获取特定Issue的详情
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            issue_number: Issue编号
+
+        Returns:
+            Issue详情
+        """
+        endpoint = f"/repos/{owner}/{repo}/issues/{issue_number}"
+        return await self._request("GET", endpoint)
+
+    async def get_issue_comments(self, owner: str, repo: str, issue_number: int) -> List[Dict]:
+        """获取Issue的评论
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            issue_number: Issue编号
+
+        Returns:
+            评论列表
+        """
+        endpoint = f"/repos/{owner}/{repo}/issues/{issue_number}/comments"
+        return await self._request("GET", endpoint)
+
+    # ===== Pull Requests相关方法 =====
+
+    async def get_pull_requests(self, owner: str, repo: str, state: str = "open",
+                               sort: str = "created", direction: str = "desc",
+                               per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取仓库的Pull Request列表
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            state: PR状态 (open, closed, all)
+            sort: 排序方式 (created, updated, popularity, long-running)
+            direction: 排序方向 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            Pull Request列表
+        """
+        endpoint = f"/repos/{owner}/{repo}/pulls"
+        params = {
+            "state": state,
+            "sort": sort,
+            "direction": direction,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def get_pull_request(self, owner: str, repo: str, pr_number: int) -> Dict:
+        """获取特定Pull Request的详情
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            pr_number: Pull Request编号
+
+        Returns:
+            Pull Request详情
+        """
+        endpoint = f"/repos/{owner}/{repo}/pulls/{pr_number}"
+        return await self._request("GET", endpoint)
+
+    async def get_pull_request_files(self, owner: str, repo: str, pr_number: int) -> List[Dict]:
+        """获取Pull Request中修改的文件
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+            pr_number: Pull Request编号
+
+        Returns:
+            修改文件列表
+        """
+        endpoint = f"/repos/{owner}/{repo}/pulls/{pr_number}/files"
+        return await self._request("GET", endpoint)
+
+    # ===== 搜索相关方法 =====
+
+    async def search_repositories(self, query: str, sort: str = "stars",
+                                 order: str = "desc", per_page: int = 30, page: int = 1) -> Dict:
+        """搜索仓库
+
+        Args:
+            query: 搜索关键词
+            sort: 排序方式 (stars, forks, updated)
+            order: 排序顺序 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            搜索结果
+        """
+        endpoint = "/search/repositories"
+        params = {
+            "q": query,
+            "sort": sort,
+            "order": order,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def search_code(self, query: str, sort: str = "indexed",
+                         order: str = "desc", per_page: int = 30, page: int = 1) -> Dict:
+        """搜索代码
+
+        Args:
+            query: 搜索关键词
+            sort: 排序方式 (indexed)
+            order: 排序顺序 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            搜索结果
+        """
+        endpoint = "/search/code"
+        params = {
+            "q": query,
+            "sort": sort,
+            "order": order,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def search_issues(self, query: str, sort: str = "created",
+                           order: str = "desc", per_page: int = 30, page: int = 1) -> Dict:
+        """搜索Issues和Pull Requests
+
+        Args:
+            query: 搜索关键词
+            sort: 排序方式 (created, updated, comments)
+            order: 排序顺序 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            搜索结果
+        """
+        endpoint = "/search/issues"
+        params = {
+            "q": query,
+            "sort": sort,
+            "order": order,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def search_users(self, query: str, sort: str = "followers",
+                          order: str = "desc", per_page: int = 30, page: int = 1) -> Dict:
+        """搜索用户
+
+        Args:
+            query: 搜索关键词
+            sort: 排序方式 (followers, repositories, joined)
+            order: 排序顺序 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            搜索结果
+        """
+        endpoint = "/search/users"
+        params = {
+            "q": query,
+            "sort": sort,
+            "order": order,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    # ===== 组织相关方法 =====
+
+    async def get_organization(self, org: str) -> Dict:
+        """获取组织信息
+
+        Args:
+            org: 组织名称
+
+        Returns:
+            组织信息
+        """
+        endpoint = f"/orgs/{org}"
+        return await self._request("GET", endpoint)
+
+    async def get_organization_repos(self, org: str, type: str = "all",
+                                    sort: str = "created", direction: str = "desc",
+                                    per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取组织的仓库列表
+
+        Args:
+            org: 组织名称
+            type: 仓库类型 (all, public, private, forks, sources, member, internal)
+            sort: 排序方式 (created, updated, pushed, full_name)
+            direction: 排序方向 (asc, desc)
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            仓库列表
+        """
+        endpoint = f"/orgs/{org}/repos"
+        params = {
+            "type": type,
+            "sort": sort,
+            "direction": direction,
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    async def get_organization_members(self, org: str, per_page: int = 30, page: int = 1) -> List[Dict]:
+        """获取组织成员列表
+
+        Args:
+            org: 组织名称
+            per_page: 每页结果数量
+            page: 页码
+
+        Returns:
+            成员列表
+        """
+        endpoint = f"/orgs/{org}/members"
+        params = {
+            "per_page": per_page,
+            "page": page
+        }
+        return await self._request("GET", endpoint, params=params)
+
+    # ===== 更复杂的操作 =====
+
+    async def get_repository_languages(self, owner: str, repo: str) -> Dict:
+        """获取仓库使用的编程语言及其比例
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+
+        Returns:
+            语言使用情况
+        """
+        endpoint = f"/repos/{owner}/{repo}/languages"
+        return await self._request("GET", endpoint)
+
+    async def get_repository_stats_contributors(self, owner: str, repo: str) -> List[Dict]:
+        """获取仓库的贡献者统计
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+
+        Returns:
+            贡献者统计信息
+        """
+        endpoint = f"/repos/{owner}/{repo}/stats/contributors"
+        return await self._request("GET", endpoint)
+
+    async def get_repository_stats_commit_activity(self, owner: str, repo: str) -> List[Dict]:
+        """获取仓库的提交活动
+
+        Args:
+            owner: 仓库所有者
+            repo: 仓库名
+
+        Returns:
+            提交活动统计
+        """
+        endpoint = f"/repos/{owner}/{repo}/stats/commit_activity"
+        return await self._request("GET", endpoint)
+
+async def example_usage():
+    """GitHubSource使用示例"""
+    # 创建客户端实例（可选传入API令牌）
+    # github = GitHubSource(api_key="your_github_token")
+    github = GitHubSource()
+
+    try:
+        # 示例1：搜索热门Python仓库
+        print("\n=== 示例1：搜索热门Python仓库 ===")
+        repos = await github.search_repositories(
+            query="language:python stars:>1000",
+            sort="stars",
+            order="desc",
+            per_page=5
+        )
+
+        if repos and "items" in repos:
+            for i, repo in enumerate(repos["items"], 1):
+                print(f"\n--- 仓库 {i} ---")
+                print(f"名称: {repo['full_name']}")
+                print(f"描述: {repo['description']}")
+                print(f"星标数: {repo['stargazers_count']}")
+                print(f"Fork数: {repo['forks_count']}")
+                print(f"最近更新: {repo['updated_at']}")
+                print(f"URL: {repo['html_url']}")
+
+        # 示例2：获取特定仓库的详情
+        print("\n=== 示例2：获取特定仓库的详情 ===")
+        repo_details = await github.get_repo("microsoft", "vscode")
+        if repo_details:
+            print(f"名称: {repo_details['full_name']}")
+            print(f"描述: {repo_details['description']}")
+            print(f"星标数: {repo_details['stargazers_count']}")
+            print(f"Fork数: {repo_details['forks_count']}")
+            print(f"默认分支: {repo_details['default_branch']}")
+            print(f"开源许可: {repo_details.get('license', {}).get('name', '无')}")
+            print(f"语言: {repo_details['language']}")
+            print(f"Open Issues数: {repo_details['open_issues_count']}")
+
+        # 示例3：获取仓库的提交历史
+        print("\n=== 示例3：获取仓库的最近提交 ===")
+        commits = await github.get_repo_commits("tensorflow", "tensorflow", per_page=5)
+        if commits:
+            for i, commit in enumerate(commits, 1):
+                print(f"\n--- 提交 {i} ---")
+                print(f"SHA: {commit['sha'][:7]}")
+                print(f"作者: {commit['commit']['author']['name']}")
+                print(f"日期: {commit['commit']['author']['date']}")
+                print(f"消息: {commit['commit']['message'].splitlines()[0]}")
+
+        # 示例4：搜索代码
+        print("\n=== 示例4：搜索代码 ===")
+        code_results = await github.search_code(
+            query="filename:README.md language:markdown pytorch in:file",
+            per_page=3
+        )
+        if code_results and "items" in code_results:
+            print(f"共找到: {code_results['total_count']} 个结果")
+            for i, item in enumerate(code_results["items"], 1):
+                print(f"\n--- 代码 {i} ---")
+                print(f"仓库: {item['repository']['full_name']}")
+                print(f"文件: {item['path']}")
+                print(f"URL: {item['html_url']}")
+
+        # 示例5：获取文件内容
+        print("\n=== 示例5：获取文件内容 ===")
+        file_content = await github.get_file_content("python", "cpython", "README.rst")
+        if file_content and "decoded_content" in file_content:
+            content = file_content["decoded_content"]
+            print(f"文件名: {file_content['name']}")
+            print(f"大小: {file_content['size']} 字节")
+            print(f"内容预览: {content[:200]}...")
+
+        # 示例6：获取仓库使用的编程语言
+        print("\n=== 示例6：获取仓库使用的编程语言 ===")
+        languages = await github.get_repository_languages("facebook", "react")
+        if languages:
+            print(f"React仓库使用的编程语言:")
+            for lang, bytes_of_code in languages.items():
+                print(f"- {lang}: {bytes_of_code} 字节")
+
+        # 示例7：获取组织信息
+        print("\n=== 示例7：获取组织信息 ===")
+        org_info = await github.get_organization("google")
+        if org_info:
+            print(f"名称: {org_info['name']}")
+            print(f"描述: {org_info.get('description', '无')}")
+            print(f"位置: {org_info.get('location', '未指定')}")
+            print(f"公共仓库数: {org_info['public_repos']}")
+            print(f"成员数: {org_info.get('public_members', 0)}")
+            print(f"URL: {org_info['html_url']}")
+
+        # 示例8：获取用户信息
+        print("\n=== 示例8：获取用户信息 ===")
+        user_info = await github.get_user("torvalds")
+        if user_info:
+            print(f"名称: {user_info['name']}")
+            print(f"公司: {user_info.get('company', '无')}")
+            print(f"博客: {user_info.get('blog', '无')}")
+            print(f"位置: {user_info.get('location', '未指定')}")
+            print(f"公共仓库数: {user_info['public_repos']}")
+            print(f"关注者数: {user_info['followers']}")
+            print(f"URL: {user_info['html_url']}")
+
+    except Exception as e:
+        print(f"发生错误: {str(e)}")
+        import traceback
+        print(traceback.format_exc())
+
+if __name__ == "__main__":
+    import asyncio
+
+    # 运行示例
+    asyncio.run(example_usage())