crawlo 1.0.6__tar.gz → 1.0.8__tar.gz

{crawlo-1.0.6/crawlo.egg-info → crawlo-1.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlo
-Version: 1.0.6
+Version: 1.0.8
 Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架，支持分布式抓取。
 Home-page: https://github.com/crawl-coder/Crawlo.git
 Author: crawl-coder

crawlo-1.0.8/crawlo/__version__.py

@@ -0,0 +1 @@
+__version__ = "1.0.8"

crawlo-1.0.8/crawlo/commands/check.py

@@ -0,0 +1,107 @@
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-08-31 22:35
+# @Author  :   crawl-coder
+# @Desc    :   命令行入口：crawlo check， 检查所有爬虫定义是否合规。
+"""
+import sys
+import configparser
+
+from crawlo.crawler import CrawlerProcess
+from crawlo.utils.project import get_settings
+from crawlo.utils.log import get_logger
+
+
+logger = get_logger(__name__)
+
+
+def main(args):
+    if args:
+        print("Usage: crawlo check")
+        return 1
+
+    try:
+        project_root = get_settings().get('PROJECT_ROOT')
+        if not project_root:
+            print("❌ Error: Cannot determine project root.")
+            return 1
+
+        if str(project_root) not in sys.path:
+            sys.path.insert(0, str(project_root))
+
+        cfg_file = project_root / 'crawlo.cfg'
+        if not cfg_file.exists():
+            print(f"❌ Error: crawlo.cfg not found in {project_root}")
+            return 1
+
+        config = configparser.ConfigParser()
+        config.read(cfg_file, encoding='utf-8')
+
+        if not config.has_section('settings') or not config.has_option('settings', 'default'):
+            print("❌ Error: Missing [settings] section or 'default' option in crawlo.cfg")
+            return 1
+
+        settings_module = config.get('settings', 'default')
+        project_package = settings_module.split('.')[0]
+
+        # 创建 CrawlerProcess 并发现爬虫
+        process = CrawlerProcess(spider_modules=[f"{project_package}.spiders"])
+        spider_names = process.get_spider_names()
+
+        if not spider_names:
+            print("📭 No spiders found.")
+            return 1
+
+        print(f"🔍 Checking {len(spider_names)} spider(s)...")
+        print("-" * 60)
+
+        issues_found = False
+        for name in sorted(spider_names):
+            cls = process.get_spider_class(name)
+            issues = []
+
+            if not hasattr(cls, 'name') or not cls.name:
+                issues.append("missing or empty 'name' attribute")
+            elif not isinstance(cls.name, str):
+                issues.append("'name' is not a string")
+
+            if not callable(getattr(cls, 'start_requests', None)):
+                issues.append("missing or non-callable 'start_requests' method")
+
+            if hasattr(cls, 'start_urls') and isinstance(cls.start_urls, str):
+                issues.append("'start_urls' is a string, should be list/tuple")
+
+            # 实例化检查（轻量）
+            try:
+                spider = cls.create_instance(None)
+                if not callable(getattr(spider, 'parse', None)):
+                    issues.append("no 'parse' method defined (optional but recommended)")
+            except Exception as e:
+                issues.append(f"failed to create instance: {e}")
+
+            if issues:
+                print(f"❌ {name:<20} {cls.__name__}")
+                for issue in issues:
+                    print(f"     • {issue}")
+                issues_found = True
+            else:
+                print(f"✅ {name:<20} {cls.__name__} (OK)")
+
+        print("-" * 60)
+        if issues_found:
+            print("⚠️  Some spiders have issues. Please fix them.")
+            return 1
+        else:
+            print("🎉 All spiders are compliant!")
+            return 0
+
+    except Exception as e:
+        print(f"❌ Error during check: {e}")
+        import traceback
+        traceback.print_exc()
+        return 1
+
+
+if __name__ == '__main__':
+    sys.exit(main(sys.argv[1:]))

crawlo-1.0.8/crawlo/commands/list.py

@@ -0,0 +1,92 @@
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-08-31 22:33
+# @Author  :   crawl-coder
+# @Desc    :   命令行入口：crawlo list，用于列出所有已注册的爬虫
+"""
+import sys
+import configparser
+
+from crawlo.crawler import CrawlerProcess
+from crawlo.utils.project import get_settings
+from crawlo.utils.log import get_logger
+
+
+logger = get_logger(__name__)
+
+
+def main(args):
+    """
+    列出所有可用爬虫
+    用法: crawlo list
+    """
+    if args:
+        print("Usage: crawlo list")
+        return 1
+
+    try:
+        # 1. 获取项目根目录
+        project_root = get_settings().get('PROJECT_ROOT')
+        if not project_root:
+            print("❌ Error: Cannot determine project root.")
+            return 1
+
+        # 将项目根目录加入 sys.path
+        project_root_str = str(project_root)
+        if project_root_str not in sys.path:
+            sys.path.insert(0, project_root_str)
+
+        # 2. 读取 crawlo.cfg 获取项目包名
+        cfg_file = project_root / 'crawlo.cfg'
+        if not cfg_file.exists():
+            print(f"❌ Error: crawlo.cfg not found in {project_root}")
+            return 1
+
+        config = configparser.ConfigParser()
+        config.read(cfg_file, encoding='utf-8')
+
+        if not config.has_section('settings') or not config.has_option('settings', 'default'):
+            print("❌ Error: Missing [settings] section or 'default' option in crawlo.cfg")
+            return 1
+
+        settings_module = config.get('settings', 'default')
+        project_package = settings_module.split('.')[0]
+
+        # 3. 创建 CrawlerProcess 并自动发现爬虫
+        spider_modules = [f"{project_package}.spiders"]
+        process = CrawlerProcess(spider_modules=spider_modules)
+
+        # 4. 获取所有爬虫信息
+        spider_names = process.get_spider_names()
+        if not spider_names:
+            print("📭 No spiders found.")
+            print("💡 Make sure:")
+            print("   - Your spider classes inherit from `Spider`")
+            print("   - They define a `name` attribute")
+            print("   - The modules are imported (e.g. via __init__.py)")
+            return 1
+
+        # 5. 输出爬虫列表
+        print(f"📋 Found {len(spider_names)} spider(s):")
+        print("-" * 50)
+        for name in sorted(spider_names):
+            cls = process.get_spider_class(name)
+            module = cls.__module__.replace(project_package + ".", "")  # 简化模块名
+            print(f"🕷️  {name:<20} {cls.__name__:<25} ({module})")
+        print("-" * 50)
+        return 0
+
+    except Exception as e:
+        print(f"❌ Error listing spiders: {e}")
+        import traceback
+        traceback.print_exc()
+        return 1
+
+
+if __name__ == '__main__':
+    """
+    允许直接运行：
+        python -m crawlo.commands.list
+    """
+    sys.exit(main(sys.argv[1:]))

crawlo-1.0.8/crawlo/commands/run.py

@@ -0,0 +1,181 @@
+"""
+命令行入口：crawlo run <spider_name>
+用于运行指定名称的爬虫。
+"""
+
+import asyncio
+from pathlib import Path
+import configparser
+
+from crawlo.crawler import CrawlerProcess
+from crawlo.utils.project import get_settings
+from crawlo.utils.log import get_logger
+
+logger = get_logger(__name__)
+
+
+def main(args):
+    """
+    运行指定爬虫的主函数
+    用法:
+        crawlo run <spider_name>
+        crawlo run all
+    """
+    if len(args) < 1:
+        print("Usage: crawlo run <spider_name>|all")
+        print("Examples:")
+        print("  crawlo run baidu")
+        print("  crawlo run all")
+        return 1
+
+    spider_arg = args[0]
+
+    try:
+        # 1. 获取项目根目录
+        project_root = get_settings().get('PROJECT_ROOT')
+        if not project_root:
+            print("❌ Error: Cannot determine project root.")
+            return 1
+
+        if str(project_root) not in sys.path:
+            sys.path.insert(0, str(project_root))
+
+        # 2. 读取 crawlo.cfg 获取项目包名
+        cfg_file = project_root / 'crawlo.cfg'
+        if not cfg_file.exists():
+            print(f"❌ Error: crawlo.cfg not found in {project_root}")
+            return 1
+
+        config = configparser.ConfigParser()
+        config.read(cfg_file, encoding='utf-8')
+
+        if not config.has_section('settings') or not config.has_option('settings', 'default'):
+            print("❌ Error: Missing [settings] section or 'default' option in crawlo.cfg")
+            return 1
+
+        settings_module = config.get('settings', 'default')
+        project_package = settings_module.split('.')[0]
+
+        # 3. 创建 CrawlerProcess 并自动发现爬虫模块
+        spider_modules = [f"{project_package}.spiders"]
+        settings = get_settings()
+        process = CrawlerProcess(settings=settings, spider_modules=spider_modules)
+
+        # === 新增：支持 'all' ===
+        if spider_arg.lower() == "all":
+            spider_names = process.get_spider_names()
+            if not spider_names:
+                print("❌ No spiders found. Make sure spiders are defined and imported.")
+                return 1
+
+            print(f"🚀 Starting ALL {len(spider_names)} spiders:")
+            for name in sorted(spider_names):
+                cls = process.get_spider_class(name)
+                print(f"   🕷️  {name} ({cls.__name__})")
+            print("-" * 50)
+
+            # 启动所有爬虫
+            asyncio.run(process.crawl(spider_names))
+            return 0
+
+        # === 原有：启动单个爬虫 ===
+        spider_name = spider_arg
+        if not process.is_spider_registered(spider_name):
+            print(f"❌ Error: Spider with name '{spider_name}' not found.")
+            available_names = process.get_spider_names()
+            if available_names:
+                print("💡 Available spiders:")
+                for name in sorted(available_names):
+                    cls = process.get_spider_class(name)
+                    print(f"   - {name} (class: {cls.__name__})")
+            else:
+                print("💡 No spiders found. Make sure your spider classes are defined and imported.")
+            return 1
+
+        spider_class = process.get_spider_class(spider_name)
+
+        # 打印启动信息
+        print(f"🚀 Starting spider: {spider_name}")
+        print(f"📁 Project: {project_package}")
+        print(f"🕷️  Class: {spider_class.__name__}")
+        print("-" * 50)
+
+        # 启动爬虫
+        asyncio.run(process.crawl(spider_name))
+
+        print("-" * 50)
+        print("✅ Spider completed successfully!")
+        return 0
+
+    except KeyboardInterrupt:
+        print("\n⚠️  Spider interrupted by user.")
+        return 1
+    except Exception as e:
+        print(f"❌ Error running spider: {e}")
+        import traceback
+        traceback.print_exc()
+        return 1
+
+
+def list_available_spiders(project_package: str):
+    """
+    列出指定项目包中所有可用的爬虫（用于调试或命令行扩展）
+    """
+    try:
+        # 临时创建一个 CrawlerProcess 来发现爬虫
+        process = CrawlerProcess(spider_modules=[f"{project_package}.spiders"])
+        available_names = process.get_spider_names()
+
+        if not available_names:
+            print("   No spiders found. Make sure:")
+            print("   - spiders/ 目录存在")
+            print("   - 爬虫类继承 Spider 且定义了 name")
+            print("   - 模块被导入（可通过 __init__.py 触发）")
+            return
+
+        print(f"Found {len(available_names)} spider(s):")
+        for name in sorted(available_names):
+            cls = process.get_spider_class(name)
+            module = cls.__module__.replace(project_package + ".", "")
+            print(f"   - {name} ({cls.__name__} @ {module})")
+    except Exception as e:
+        print(f"❌ Failed to list spiders: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+def run_spider_by_name(spider_name: str, project_package: str = None):
+    """
+    在代码中直接运行某个爬虫（需提供 project_package）
+    """
+    if project_package is None:
+        # 尝试从配置读取
+        cfg_file = Path('crawlo.cfg')
+        if cfg_file.exists():
+            config = configparser.ConfigParser()
+            config.read(cfg_file, encoding='utf-8')
+            if config.has_option('settings', 'default'):
+                project_package = config.get('settings', 'default').split('.')[0]
+
+    if not project_package:
+        print("❌ Error: project_package is required.")
+        return 1
+
+    # 添加项目路径
+    project_root = get_settings().get('PROJECT_ROOT')
+    if project_root and str(project_root) not in sys.path:
+        sys.path.insert(0, str(project_root))
+
+    # 复用 main 函数逻辑
+    args = [spider_name]
+    return main(args)
+
+
+if __name__ == '__main__':
+    """
+    允许直接运行：
+        python -m crawlo.commands.run <spider_name>
+    """
+    import sys
+
+    sys.exit(main(sys.argv[1:]))

crawlo-1.0.8/crawlo/commands/stats.py

@@ -0,0 +1,59 @@
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-08-31 22:36
+# @Author  :   crawl-coder
+# @Desc    :   命令行入口：crawlo stats，查看最近运行的爬虫统计信息。
+"""
+import sys
+from crawlo.utils.log import get_logger
+
+
+logger = get_logger(__name__)
+
+# 保存最近运行的爬虫的统计（示例）
+_LAST_RUN_STATS = {}
+
+
+def record_stats(crawler):
+    """在爬虫关闭后记录统计（需在 close 中调用）"""
+    if crawler.stats and crawler.spider:
+        _LAST_RUN_STATS[crawler.spider.name] = crawler.stats.get_stats()
+
+
+def main(args):
+    if len(args) == 0:
+        # 显示所有历史统计
+        if not _LAST_RUN_STATS:
+            print("📊 No stats available. Run a spider first.")
+            return 0
+
+        print("📊 Recent Spider Statistics:")
+        print("-" * 60)
+        for spider_name, stats in _LAST_RUN_STATS.items():
+            print(f"🕷️  {spider_name}")
+            for k, v in stats.items():
+                print(f"    {k:<30} {v}")
+            print()
+        return 0
+
+    elif len(args) == 1:
+        spider_name = args[0]
+        if spider_name not in _LAST_RUN_STATS:
+            print(f"📊 No stats found for spider '{spider_name}'")
+            return 1
+
+        stats = _LAST_RUN_STATS[spider_name]
+        print(f"📊 Stats for '{spider_name}':")
+        print("-" * 60)
+        for k, v in stats.items():
+            print(f"    {k:<30} {v}")
+        return 0
+
+    else:
+        print("Usage: crawlo stats [spider_name]")
+        return 1
+
+
+if __name__ == '__main__':
+    sys.exit(main(sys.argv[1:]))