crawlo 1.3.3__py3-none-any.whl → 1.3.4__py3-none-any.whl

tests/scrapy_comparison/ofweek_scrapy.py

@@ -0,0 +1,139 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from urllib.parse import urljoin
+
+
+class NewsItem(scrapy.Item):
+    title = scrapy.Field()
+    publish_time = scrapy.Field()
+    url = scrapy.Field()
+    source = scrapy.Field()
+    content = scrapy.Field()
+
+
+class OfweekScrapySpider(scrapy.Spider):
+    name = 'ofweek_scrapy'
+    allowed_domains = ['ee.ofweek.com']
+    
+    def start_requests(self):
+        headers = {
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Pragma": "no-cache",
+            "Referer": "https://ee.ofweek.com/CATList-2800-8100-ee-2.html",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-Fetch-User": "?1",
+            "Upgrade-Insecure-Requests": "1",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
+            "sec-ch-ua": "\"Not;A=Brand\";v=\"99\", \"Google Chrome\";v=\"139\", \"Chromium\";v=\"139\"",
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": "\"Windows\""
+        }
+        cookies = {
+            "__utmz": "57425525.1730117117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)",
+            "Hm_lvt_abe9900db162c6d089cdbfd107db0f03": "1739244841",
+            "Hm_lvt_af50e2fc51af73da7720fb324b88a975": "1740100727",
+            "JSESSIONID": "FEA96D3B5FC31350B2285E711BF2A541",
+            "Hm_lvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477622",
+            "HMACCOUNT": "08DF0D235A291EAA",
+            "__utma": "57425525.2080994505.1730117117.1747970718.1757477622.50",
+            "__utmc": "57425525",
+            "__utmt": "1",
+            "__utmb": "57425525.2.10.1757477622",
+            "Hm_lpvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477628",
+            "index_burying_point": "c64d6c31e69d560efe319cc9f8be279f"
+        }
+
+        # 使用较少的页数进行测试
+        max_page = 50
+        for page in range(1, max_page + 1):
+            url = f'https://ee.ofweek.com/CATList-2800-8100-ee-{page}.html'
+            yield scrapy.Request(
+                url=url,
+                callback=self.parse,
+                headers=headers,
+                cookies=cookies
+            )
+
+    def parse(self, response):
+        self.logger.info(f'正在解析页面: {response.url}')
+
+        rows = response.xpath(
+            '//div[@class="main_left"]/div[@class="list_model"]/div[@class="model_right model_right2"]')
+        self.logger.info(f"在页面 {response.url} 中找到 {len(rows)} 个条目")
+
+        for row in rows:
+            try:
+                # 提取URL和标题
+                url = row.xpath('./h3/a/@href').extract_first()
+                title = row.xpath('./h3/a/text()').extract_first()
+
+                # 容错处理
+                if not url:
+                    self.logger.warning(f"条目缺少URL，跳过")
+                    continue
+
+                if not title:
+                    self.logger.warning(f"条目缺少标题，跳过")
+                    continue
+
+                # 确保 URL 是绝对路径
+                absolute_url = urljoin(response.url, url)
+
+                # 验证URL格式
+                if not absolute_url.startswith(('http://', 'https://')):
+                    self.logger.warning(f"无效的URL格式，跳过: {absolute_url}")
+                    continue
+
+                self.logger.info(f"提取到详情页链接: {absolute_url}, 标题: {title}")
+                yield scrapy.Request(
+                    url=absolute_url,
+                    meta={
+                        "title": title.strip() if title else '',
+                        "parent_url": response.url
+                    },
+                    callback=self.parse_detail
+                )
+            except Exception as e:
+                self.logger.error(f"处理条目时出错: {e}")
+                continue
+
+    def parse_detail(self, response):
+        self.logger.info(f'正在解析详情页: {response.url}')
+
+        try:
+            title = response.meta.get('title', '')
+
+            # 提取内容，增加容错处理
+            content_elements = response.xpath('//div[@class="TRS_Editor"]|//*[@id="articleC"]')
+            if content_elements:
+                content = content_elements.xpath('.//text()').extract()
+                content = '\n'.join([text.strip() for text in content if text.strip()])
+            else:
+                content = ''
+                self.logger.warning(f"未找到内容区域: {response.url}")
+
+            # 提取发布时间
+            publish_time = response.xpath('//div[@class="time fl"]/text()').extract_first()
+            if publish_time:
+                publish_time = publish_time.strip()
+
+            source = response.xpath('//div[@class="source-name"]/text()').extract_first()
+
+            # 创建数据项
+            item = NewsItem()
+            item['title'] = title.strip() if title else ''
+            item['publish_time'] = publish_time if publish_time else ''
+            item['url'] = response.url
+            item['source'] = source if source else ''
+            item['content'] = content
+
+            self.logger.info(f"成功提取详情页数据: {item['title']}")
+            yield item
+
+        except Exception as e:
+            self.logger.error(f"解析详情页 {response.url} 时出错: {e}")

tests/scrapy_comparison/scrapy_test.py

@@ -0,0 +1,134 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from urllib.parse import urljoin
+
+class NewsItem(scrapy.Item):
+    title = scrapy.Field()
+    publish_time = scrapy.Field()
+    url = scrapy.Field()
+    source = scrapy.Field()
+    content = scrapy.Field()
+
+class OfweekScrapyTestSpider(scrapy.Spider):
+    name = 'ofweek_scrapy_test'
+    allowed_domains = ['ee.ofweek.com']
+    
+    def start_requests(self):
+        headers = {
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Pragma": "no-cache",
+            "Referer": "https://ee.ofweek.com/CATList-2800-8100-ee-2.html",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-Fetch-User": "?1",
+            "Upgrade-Insecure-Requests": "1",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
+        }
+        cookies = {
+            "__utmz": "57425525.1730117117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)",
+            "Hm_lvt_abe9900db162c6d089cdbfd107db0f03": "1739244841",
+            "Hm_lvt_af50e2fc51af73da7720fb324b88a975": "1740100727",
+            "JSESSIONID": "FEA96D3B5FC31350B2285E711BF2A541",
+            "Hm_lvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477622",
+            "HMACCOUNT": "08DF0D235A291EAA",
+            "__utma": "57425525.2080994505.1730117117.1747970718.1757477622.50",
+            "__utmc": "57425525",
+            "__utmt": "1",
+            "__utmb": "57425525.2.10.1757477622",
+            "Hm_lpvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477628",
+            "index_burying_point": "c64d6c31e69d560efe319cc9f8be279f"
+        }
+
+        # 使用较少的页数进行测试
+        max_page = 5
+        for page in range(1, max_page + 1):
+            url = f'https://ee.ofweek.com/CATList-2800-8100-ee-{page}.html'
+            yield scrapy.Request(
+                url=url,
+                callback=self.parse,
+                headers=headers,
+                cookies=cookies
+            )
+
+    def parse(self, response):
+        self.logger.info(f'正在解析页面: {response.url}')
+
+        rows = response.xpath(
+            '//div[@class="main_left"]/div[@class="list_model"]/div[@class="model_right model_right2"]')
+        self.logger.info(f"在页面 {response.url} 中找到 {len(rows)} 个条目")
+
+        for row in rows:
+            try:
+                # 提取URL和标题
+                url = row.xpath('./h3/a/@href').extract_first()
+                title = row.xpath('./h3/a/text()').extract_first()
+
+                # 容错处理
+                if not url:
+                    self.logger.warning(f"条目缺少URL，跳过")
+                    continue
+
+                if not title:
+                    self.logger.warning(f"条目缺少标题，跳过")
+                    continue
+
+                # 确保 URL 是绝对路径
+                absolute_url = urljoin(response.url, url)
+
+                # 验证URL格式
+                if not absolute_url.startswith(('http://', 'https://')):
+                    self.logger.warning(f"无效的URL格式，跳过: {absolute_url}")
+                    continue
+
+                self.logger.info(f"提取到详情页链接: {absolute_url}, 标题: {title}")
+                yield scrapy.Request(
+                    url=absolute_url,
+                    meta={
+                        "title": title.strip() if title else '',
+                        "parent_url": response.url
+                    },
+                    callback=self.parse_detail
+                )
+            except Exception as e:
+                self.logger.error(f"处理条目时出错: {e}")
+                continue
+
+    def parse_detail(self, response):
+        self.logger.info(f'正在解析详情页: {response.url}')
+
+        try:
+            title = response.meta.get('title', '')
+
+            # 提取内容，增加容错处理
+            content_elements = response.xpath('//div[@class="TRS_Editor"]|//*[@id="articleC"]')
+            if content_elements:
+                content = content_elements.xpath('.//text()').extract()
+                content = '\n'.join([text.strip() for text in content if text.strip()])
+            else:
+                content = ''
+                self.logger.warning(f"未找到内容区域: {response.url}")
+
+            # 提取发布时间
+            publish_time = response.xpath('//div[@class="time fl"]/text()').extract_first()
+            if publish_time:
+                publish_time = publish_time.strip()
+
+            source = response.xpath('//div[@class="source-name"]/text()').extract_first()
+
+            # 创建数据项
+            item = NewsItem()
+            item['title'] = title.strip() if title else ''
+            item['publish_time'] = publish_time if publish_time else ''
+            item['url'] = response.url
+            item['source'] = source if source else ''
+            item['content'] = content
+
+            self.logger.info(f"成功提取详情页数据: {item['title']}")
+            yield item
+
+        except Exception as e:
+            self.logger.error(f"解析详情页 {response.url} 时出错: {e}")

tests/simple_command_test.py

@@ -0,0 +1,120 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+简单测试所有 crawlo 命令
+"""
+
+import sys
+import os
+import subprocess
+
+# 添加项目根目录到Python路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+def run_command(cmd, cwd=None):
+    """运行命令并返回结果"""
+    try:
+        result = subprocess.run(
+            cmd, 
+            shell=True, 
+            cwd=cwd, 
+            capture_output=True, 
+            text=True, 
+            timeout=30
+        )
+        return result.returncode, result.stdout, result.stderr
+    except subprocess.TimeoutExpired:
+        return -1, "", "Command timed out"
+    except Exception as e:
+        return -1, "", str(e)
+
+def test_help_command():
+    """测试 help 命令"""
+    print("测试 help 命令...")
+    
+    # 测试 -h 参数
+    code, stdout, stderr = run_command("python -m crawlo.cli -h")
+    assert code == 0, f"help 命令失败: {stderr}"
+    assert "Crawlo" in stdout, "help 输出不包含框架名称"
+    
+    # 测试 --help 参数
+    code, stdout, stderr = run_command("python -m crawlo.cli --help")
+    assert code == 0, f"help 命令失败: {stderr}"
+    assert "Crawlo" in stdout, "help 输出不包含框架名称"
+    
+    print("✅ help 命令测试通过")
+
+def test_version_command():
+    """测试 version 命令"""
+    print("测试 version 命令...")
+    
+    # 测试 -v 参数
+    code, stdout, stderr = run_command("python -m crawlo.cli -v")
+    assert code == 0, f"version 命令失败: {stderr}"
+    assert "Crawlo" in stdout, "version 输出不包含框架名称"
+    
+    # 测试 --version 参数
+    code, stdout, stderr = run_command("python -m crawlo.cli --version")
+    assert code == 0, f"version 命令失败: {stderr}"
+    assert "Crawlo" in stdout, "version 输出不包含框架名称"
+    
+    print("✅ version 命令测试通过")
+
+def test_command_help():
+    """测试各命令的帮助信息"""
+    print("测试各命令的帮助信息...")
+    
+    commands = ["startproject", "genspider", "run", "check", "list", "stats"]
+    
+    for command in commands:
+        code, stdout, stderr = run_command(f"python -m crawlo.cli {command} --help")
+        # 命令帮助通常返回非0状态码，但我们检查输出
+        assert len(stdout) > 0 or len(stderr) > 0, f"{command} 命令帮助无输出"
+        print(f"✅ {command} 命令帮助测试通过")
+
+def test_invalid_command():
+    """测试无效命令"""
+    print("测试无效命令...")
+    
+    code, stdout, stderr = run_command("python -m crawlo.cli invalid_command")
+    assert code != 0, "无效命令应该返回非0状态码"
+    assert "Unknown command" in stderr or "Unknown command" in stdout, "应该提示未知命令"
+    
+    print("✅ 无效命令测试通过")
+
+def main():
+    """主函数"""
+    print("开始简单测试所有 crawlo 命令...")
+    print("=" * 50)
+    
+    try:
+        # 测试 help 命令
+        test_help_command()
+        print()
+        
+        # 测试 version 命令
+        test_version_command()
+        print()
+        
+        # 测试各命令的帮助信息
+        test_command_help()
+        print()
+        
+        # 测试无效命令
+        test_invalid_command()
+        print()
+        
+        print("=" * 50)
+        print("所有命令简单测试通过！")
+        
+    except Exception as e:
+        print("=" * 50)
+        print(f"测试失败: {e}")
+        import traceback
+        traceback.print_exc()
+        return 1
+    
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())

tests/simple_crawlo_test.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+简单的Crawlo性能测试
+"""
+import asyncio
+import time
+import sys
+import os
+
+# 添加项目根目录到Python路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo import Spider, Request
+from crawlo.crawler import CrawlerProcess
+from crawlo.items import Item, Field
+
+class NewsItem(Item):
+    title = Field()
+    publish_time = Field()
+    url = Field()
+    source = Field()
+    content = Field()
+
+class OfweekSimpleSpider(Spider):
+    name = "ofweek_simple"
+    
+    def start_requests(self):
+        headers = {
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Pragma": "no-cache",
+            "Referer": "https://ee.ofweek.com/CATList-2800-8100-ee-2.html",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-Fetch-User": "?1",
+            "Upgrade-Insecure-Requests": "1",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
+        }
+        cookies = {
+            "__utmz": "57425525.1730117117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)",
+            "Hm_lvt_abe9900db162c6d089cdbfd107db0f03": "1739244841",
+            "Hm_lvt_af50e2fc51af73da7720fb324b88a975": "1740100727",
+            "JSESSIONID": "FEA96D3B5FC31350B2285E711BF2A541",
+            "Hm_lvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477622",
+            "HMACCOUNT": "08DF0D235A291EAA",
+            "__utma": "57425525.2080994505.1730117117.1747970718.1757477622.50",
+            "__utmc": "57425525",
+            "__utmt": "1",
+            "__utmb": "57425525.2.10.1757477622",
+            "Hm_lpvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477628",
+            "index_burying_point": "c64d6c31e69d560efe319cc9f8be279f"
+        }
+
+        # 使用较少的页数进行测试
+        max_page = 5
+        for page in range(1, max_page + 1):
+            url = f"https://ee.ofweek.com/CATList-2800-8100-ee-{page}.html"
+            yield Request(url=url, callback=self.parse, headers=headers, cookies=cookies)
+
+    def parse(self, response):
+        from urllib.parse import urljoin
+        rows = response.xpath("//div[@class=\"main_left\"]/div[@class=\"list_model\"]/div[@class=\"model_right model_right2\"]")
+        
+        for row in rows:
+            try:
+                url = row.xpath("./h3/a/@href").extract_first()
+                title = row.xpath("./h3/a/text()").extract_first()
+
+                if not url or not title:
+                    continue
+
+                absolute_url = urljoin(response.url, url)
+                if not absolute_url.startswith(("http://", "https://")):
+                    continue
+
+                yield Request(
+                    url=absolute_url,
+                    meta={"title": title.strip() if title else "", "parent_url": response.url},
+                    callback=self.parse_detail
+                )
+            except Exception:
+                continue
+
+    def parse_detail(self, response):
+        title = response.meta.get("title", "")
+        content_elements = response.xpath("//div[@class=\"TRS_Editor\"]|//*[@id=\"articleC\"]")
+        if content_elements:
+            content = content_elements.xpath(".//text()").extract()
+            content = "\n".join([text.strip() for text in content if text.strip()])
+        else:
+            content = ""
+
+        publish_time = response.xpath("//div[@class=\"time fl\"]/text()").extract_first()
+        if publish_time:
+            publish_time = publish_time.strip()
+
+        source = response.xpath("//div[@class=\"source-name\"]/text()").extract_first()
+
+        item = NewsItem()
+        item["title"] = title.strip() if title else ""
+        item["publish_time"] = publish_time if publish_time else ""
+        item["url"] = response.url
+        item["source"] = source if source else ""
+        item["content"] = content
+
+        yield item
+
+async def main():
+    start_time = time.time()
+    
+    process = CrawlerProcess(settings={
+        "CONCURRENCY": 8,
+        "DOWNLOAD_DELAY": 0.1,
+        "LOG_LEVEL": "ERROR",  # 减少日志输出以提高性能
+    })
+    await process.crawl(OfweekSimpleSpider)
+    
+    end_time = time.time()
+    execution_time = end_time - start_time
+    
+    print(f"Crawlo执行时间: {execution_time:.2f}秒")
+
+if __name__ == "__main__":
+    asyncio.run(main())

tests/simple_log_test.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+简单的日志系统测试
+"""
+import sys
+import os
+sys.path.insert(0, '/')
+
+# 确保日志目录存在
+os.makedirs('/examples/ofweek_standalone/logs', exist_ok=True)
+
+# 测试日志系统
+from crawlo.utils.log import LoggerManager, get_logger
+
+print("=== 简单日志系统测试 ===")
+
+# 1. 直接配置日志系统
+print("1. 配置日志系统...")
+LoggerManager.configure(
+    LOG_LEVEL='INFO',
+    LOG_FILE='/Users/oscar/projects/Crawlo/examples/ofweek_standalone/logs/simple_test.log'
+)
+
+# 2. 创建logger
+print("2. 创建logger...")
+logger = get_logger('test.logger')
+print(f"   Logger: {logger}")
+print(f"   Handlers: {len(logger.handlers)}")
+
+for i, handler in enumerate(logger.handlers):
+    handler_type = type(handler).__name__
+    print(f"     Handler {i}: {handler_type}")
+    if hasattr(handler, 'baseFilename'):
+        print(f"       File: {handler.baseFilename}")
+
+# 3. 测试日志输出
+print("3. 测试日志输出...")
+logger.info("这是一条测试INFO日志")
+logger.debug("这是一条测试DEBUG日志")
+logger.warning("这是一条测试WARNING日志")
+
+print("4. 检查日志文件...")
+log_file = '/Users/oscar/projects/Crawlo/examples/ofweek_standalone/logs/simple_test.log'
+if os.path.exists(log_file):
+    print(f"   日志文件存在: {log_file}")
+    with open(log_file, 'r', encoding='utf-8') as f:
+        content = f.read()
+        print(f"   文件内容长度: {len(content)} 字符")
+        if content:
+            print("   文件内容:")
+            print(content)
+        else:
+            print("   文件为空")
+else:
+    print(f"   日志文件不存在: {log_file}")
+
+print("=== 测试完成 ===")