crawlo 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

crawlo/templates/spider/spider.py.tmpl

@@ -1,142 +1,144 @@
-# -*- coding: UTF-8 -*-
-"""
-{{project_name}}.spiders.{{spider_name}}
-=======================================
-由 `crawlo genspider` 命令生成的爬虫。
-基于 Crawlo 框架，支持异步并发、分布式爬取等功能。
-
-使用示例：
-    crawlo crawl {{spider_name}}
-"""
-
-from crawlo.spider import Spider
-from crawlo import Request
-from ..items import ExampleItem
-
-
-class {{class_name}}(Spider):
-    """
-    爬虫：{{spider_name}}
-    
-    功能说明：
-    - 支持并发爬取
-    - 自动去重过滤
-    - 错误重试机制
-    - 数据管道处理
-    """
-    name = '{{spider_name}}'
-    allowed_domains = ['{{domain}}']
-    start_urls = ['https://{{domain}}/']
-    
-    # 高级配置（可选）
-    # custom_settings = {
-    #     'DOWNLOAD_DELAY': 2.0,
-    #     'CONCURRENCY': 4,
-    #     'RETRY_HTTP_CODES': [500, 502, 503, 504, 408, 429],
-    # }
-
-    def start_requests(self):
-        """
-        生成初始请求。
-        
-        支持自定义请求头、代理、优先级等。
-        """
-        headers = {
-            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
-            'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
-        }
-        
-        for url in self.start_urls:
-            yield Request(
-                url=url,
-                callback=self.parse,
-                headers=headers,
-                # meta={'proxy': 'http://proxy.example.com:8080'},  # 自定义代理
-                # priority=10,  # 请求优先级（数字越大优先级越高）
-            )
-
-    def parse(self, response):
-        """
-        解析响应的主方法。
-        
-        Args:
-            response: 响应对象，包含页面内容和元数据
-            
-        Yields:
-            Request: 新的请求对象（用于深度爬取）
-            Item: 数据项对象（用于数据存储）
-        """
-        self.logger.info(f'正在解析页面: {response.url}')
-        
-        # ================== 数据提取示例 ==================
-        
-        # 提取数据并创建 Item
-        # item = {{item_class}}()
-        # item['title'] = response.xpath('//title/text()').get(default='')
-        # item['url'] = response.url
-        # item['content'] = response.xpath('//div[@class="content"]//text()').getall()
-        # yield item
-        
-        # 直接返回字典（简单数据）
-        yield {
-            'title': response.xpath('//title/text()').get(default=''),
-            'url': response.url,
-            'status_code': response.status_code,
-            # 'description': response.xpath('//meta[@name="description"]/@content').get(),
-            # 'keywords': response.xpath('//meta[@name="keywords"]/@content').get(),
-        }
-        
-        # ================== 链接提取示例 ==================
-        
-        # 提取并跟进链接
-        # links = response.xpath('//a/@href').getall()
-        # for link in links:
-        #     # 过滤有效链接
-        #     if link and not link.startswith(('javascript:', 'mailto:', '#')):
-        #         yield response.follow(
-        #             link,
-        #             callback=self.parse_detail,  # 或者 self.parse 继续递归
-        #             meta={'parent_url': response.url}  # 传递父页面信息
-        #         )
-        
-        # 用 CSS 选择器提取链接
-        # for link in response.css('a.item-link::attr(href)').getall():
-        #     yield response.follow(link, callback=self.parse_detail)
-        
-        # ================== 分页处理示例 ==================
-        
-        # 处理分页
-        # next_page = response.xpath('//a[@class="next"]/@href').get()
-        # if next_page:
-        #     yield response.follow(next_page, callback=self.parse)
-        
-        # 数字分页
-        # current_page = int(response.meta.get('page', 1))
-        # max_pages = 100  # 设置最大页数
-        # if current_page < max_pages:
-        #     next_url = f'https://{{domain}}/page/{current_page + 1}'
-        #     yield Request(
-        #         url=next_url,
-        #         callback=self.parse,
-        #         meta={'page': current_page + 1}
-        #     )
-
-    def parse_detail(self, response):
-        """
-        解析详情页面的方法（可选）。
-        
-        用于处理从列表页跳转而来的详情页。
-        """
-        self.logger.info(f'正在解析详情页: {response.url}')
-        
-        # parent_url = response.meta.get('parent_url', '')
-        # 
-        # yield {
-        #     'title': response.xpath('//h1/text()').get(default=''),
-        #     'content': '\n'.join(response.xpath('//div[@class="content"]//text()').getall()),
-        #     'url': response.url,
-        #     'parent_url': parent_url,
-        #     'publish_time': response.xpath('//time/@datetime').get(),
-        # }
-        
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.spiders.{{spider_name}}
+=======================================
+由 `crawlo genspider` 命令生成的爬虫。
+基于 Crawlo 框架，支持异步并发、分布式爬取等功能。
+
+使用示例：
+    crawlo crawl {{spider_name}}
+"""
+
+from crawlo.spider import Spider
+from crawlo import Request
+from ..items import ExampleItem
+
+
+class {{class_name}}(Spider):
+    """
+    爬虫：{{spider_name}}
+    
+    功能说明：
+    - 支持并发爬取
+    - 自动去重过滤
+    - 错误重试机制
+    - 数据管道处理
+    """
+    name = '{{spider_name}}'
+    allowed_domains = ['{{domain}}']
+    start_urls = ['https://{{domain}}/']
+    
+    # 高级配置（可选）
+    # custom_settings = {
+    #     'DOWNLOAD_DELAY': 2.0,
+    #     'CONCURRENCY': 4,
+    #     'RETRY_HTTP_CODES': [500, 502, 503, 504, 408, 429],
+    #     'ALLOWED_RESPONSE_CODES': [200, 301, 302],  # 只允许特定状态码
+    #     'DENIED_RESPONSE_CODES': [403, 404],        # 拒绝特定状态码
+    # }
+
+    def start_requests(self):
+        """
+        生成初始请求。
+        
+        支持自定义请求头、代理、优先级等。
+        """
+        headers = {
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+            'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
+        }
+        
+        for url in self.start_urls:
+            yield Request(
+                url=url,
+                callback=self.parse,
+                headers=headers,
+                # meta={'proxy': 'http://proxy.example.com:8080'},  # 自定义代理
+                # priority=10,  # 请求优先级（数字越大优先级越高）
+            )
+
+    def parse(self, response):
+        """
+        解析响应的主方法。
+        
+        Args:
+            response: 响应对象，包含页面内容和元数据
+            
+        Yields:
+            Request: 新的请求对象（用于深度爬取）
+            Item: 数据项对象（用于数据存储）
+        """
+        self.logger.info(f'正在解析页面: {response.url}')
+        
+        # ================== 数据提取示例 ==================
+        
+        # 提取数据并创建 Item
+        # item = {{item_class}}()
+        # item['title'] = response.xpath('//title/text()').get(default='')
+        # item['url'] = response.url
+        # item['content'] = response.xpath('//div[@class="content"]//text()').getall()
+        # yield item
+        
+        # 直接返回字典（简单数据）
+        yield {
+            'title': response.xpath('//title/text()').get(default=''),
+            'url': response.url,
+            'status_code': response.status_code,
+            # 'description': response.xpath('//meta[@name="description"]/@content').get(),
+            # 'keywords': response.xpath('//meta[@name="keywords"]/@content').get(),
+        }
+        
+        # ================== 链接提取示例 ==================
+        
+        # 提取并跟进链接
+        # links = response.xpath('//a/@href').getall()
+        # for link in links:
+        #     # 过滤有效链接
+        #     if link and not link.startswith(('javascript:', 'mailto:', '#')):
+        #         yield response.follow(
+        #             link,
+        #             callback=self.parse_detail,  # 或者 self.parse 继续递归
+        #             meta={'parent_url': response.url}  # 传递父页面信息
+        #         )
+        
+        # 用 CSS 选择器提取链接
+        # for link in response.css('a.item-link::attr(href)').getall():
+        #     yield response.follow(link, callback=self.parse_detail)
+        
+        # ================== 分页处理示例 ==================
+        
+        # 处理分页
+        # next_page = response.xpath('//a[@class="next"]/@href').get()
+        # if next_page:
+        #     yield response.follow(next_page, callback=self.parse)
+        
+        # 数字分页
+        # current_page = int(response.meta.get('page', 1))
+        # max_pages = 100  # 设置最大页数
+        # if current_page < max_pages:
+        #     next_url = f'https://{{domain}}/page/{current_page + 1}'
+        #     yield Request(
+        #         url=next_url,
+        #         callback=self.parse,
+        #         meta={'page': current_page + 1}
+        #     )
+
+    def parse_detail(self, response):
+        """
+        解析详情页面的方法（可选）。
+        
+        用于处理从列表页跳转而来的详情页。
+        """
+        self.logger.info(f'正在解析详情页: {response.url}')
+        
+        # parent_url = response.meta.get('parent_url', '')
+        # 
+        # yield {
+        #     'title': response.xpath('//h1/text()').get(default=''),
+        #     'content': '\n'.join(response.xpath('//div[@class="content"]//text()').getall()),
+        #     'url': response.url,
+        #     'parent_url': parent_url,
+        #     'publish_time': response.xpath('//time/@datetime').get(),
+        # }
+        
         pass

crawlo/tools/__init__.py

@@ -1,183 +1,183 @@
-#!/usr/bin/python
-# -*- coding: UTF-8 -*-
-"""
-# @Time    : 2025-09-10 22:00
-# @Author  : crawl-coder
-# @Desc    : Crawlo框架工具包集合
-"""
-
-# 日期工具封装
-from .date_tools import (
-    TimeUtils,
-    parse_time,
-    format_time,
-    time_diff,
-    to_timestamp,
-    to_datetime,
-    now,
-    to_timezone,
-    to_utc,
-    to_local,
-    from_timestamp_with_tz
-)
-
-# 数据清洗工具封装
-from ..cleaners import (
-    TextCleaner,
-    DataFormatter,
-    EncodingConverter,
-    remove_html_tags,
-    decode_html_entities,
-    remove_extra_whitespace,
-    remove_special_chars,
-    normalize_unicode,
-    clean_text,
-    extract_numbers,
-    extract_emails,
-    extract_urls,
-    format_number,
-    format_currency,
-    format_percentage,
-    format_phone_number,
-    format_chinese_id_card,
-    capitalize_words,
-    detect_encoding,
-    to_utf8,
-    convert_encoding
-)
-
-# 数据验证工具封装
-from .data_validator import (
-    DataValidator,
-    validate_email,
-    validate_phone,
-    validate_url,
-    validate_chinese_id_card,
-    validate_date,
-    validate_number_range,
-    check_data_integrity
-)
-
-# 重试机制封装
-from .retry_mechanism import (
-    RetryMechanism,
-    retry,
-    should_retry,
-    exponential_backoff
-)
-
-# 反爬虫应对工具
-from .anti_crawler import (
-    ProxyPoolManager,
-    CaptchaHandler,
-    AntiCrawler,
-    get_random_user_agent,
-    rotate_proxy,
-    handle_captcha,
-    detect_rate_limiting
-)
-
-# 带认证代理工具
-from .authenticated_proxy import (
-    AuthenticatedProxy,
-    create_proxy_config,
-    format_proxy_for_request,
-    parse_proxy_url,
-    validate_proxy_url,
-    get_proxy_info
-)
-
-# 分布式协调工具
-from .distributed_coordinator import (
-    TaskDistributor,
-    DeduplicationTool,
-    DistributedCoordinator,
-    generate_task_id,
-    claim_task,
-    report_task_status,
-    get_cluster_info,
-    generate_pagination_tasks,
-    distribute_tasks
-)
-
-__all__ = [
-    # 日期工具
-    "TimeUtils",
-    "parse_time",
-    "format_time",
-    "time_diff",
-    "to_timestamp",
-    "to_datetime",
-    "now",
-    "to_timezone",
-    "to_utc",
-    "to_local",
-    "from_timestamp_with_tz",
-    
-    # 数据清洗工具
-    "TextCleaner",
-    "DataFormatter",
-    "EncodingConverter",
-    "remove_html_tags",
-    "decode_html_entities",
-    "remove_extra_whitespace",
-    "remove_special_chars",
-    "normalize_unicode",
-    "clean_text",
-    "extract_numbers",
-    "extract_emails",
-    "extract_urls",
-    "format_number",
-    "format_currency",
-    "format_percentage",
-    "format_phone_number",
-    "format_chinese_id_card",
-    "capitalize_words",
-    "detect_encoding",
-    "to_utf8",
-    "convert_encoding",
-    
-    # 数据验证工具
-    "DataValidator",
-    "validate_email",
-    "validate_phone",
-    "validate_url",
-    "validate_chinese_id_card",
-    "validate_date",
-    "validate_number_range",
-    "check_data_integrity",
-    
-    # 重试机制封装
-    "RetryMechanism",
-    "retry",
-    "should_retry",
-    "exponential_backoff",
-    
-    # 反爬虫应对工具
-    "ProxyPoolManager",
-    "CaptchaHandler",
-    "AntiCrawler",
-    "get_random_user_agent",
-    "rotate_proxy",
-    "handle_captcha",
-    "detect_rate_limiting",
-    
-    # 带认证代理工具
-    "AuthenticatedProxy",
-    "create_proxy_config",
-    "format_proxy_for_request",
-    "parse_proxy_url",
-    "validate_proxy_url",
-    "get_proxy_info",
-    
-    # 分布式协调工具
-    "TaskDistributor",
-    "DeduplicationTool",
-    "DistributedCoordinator",
-    "generate_task_id",
-    "claim_task",
-    "report_task_status",
-    "get_cluster_info",
-    "generate_pagination_tasks",
-    "distribute_tasks"
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+# @Time    : 2025-09-10 22:00
+# @Author  : crawl-coder
+# @Desc    : Crawlo框架工具包集合
+"""
+
+# 日期工具封装
+from .date_tools import (
+    TimeUtils,
+    parse_time,
+    format_time,
+    time_diff,
+    to_timestamp,
+    to_datetime,
+    now,
+    to_timezone,
+    to_utc,
+    to_local,
+    from_timestamp_with_tz
+)
+
+# 数据清洗工具封装
+from ..cleaners import (
+    TextCleaner,
+    DataFormatter,
+    EncodingConverter,
+    remove_html_tags,
+    decode_html_entities,
+    remove_extra_whitespace,
+    remove_special_chars,
+    normalize_unicode,
+    clean_text,
+    extract_numbers,
+    extract_emails,
+    extract_urls,
+    format_number,
+    format_currency,
+    format_percentage,
+    format_phone_number,
+    format_chinese_id_card,
+    capitalize_words,
+    detect_encoding,
+    to_utf8,
+    convert_encoding
+)
+
+# 数据验证工具封装
+from .data_validator import (
+    DataValidator,
+    validate_email,
+    validate_phone,
+    validate_url,
+    validate_chinese_id_card,
+    validate_date,
+    validate_number_range,
+    check_data_integrity
+)
+
+# 重试机制封装
+from .retry_mechanism import (
+    RetryMechanism,
+    retry,
+    should_retry,
+    exponential_backoff
+)
+
+# 反爬虫应对工具
+from .anti_crawler import (
+    ProxyPoolManager,
+    CaptchaHandler,
+    AntiCrawler,
+    get_random_user_agent,
+    rotate_proxy,
+    handle_captcha,
+    detect_rate_limiting
+)
+
+# 带认证代理工具
+from .authenticated_proxy import (
+    AuthenticatedProxy,
+    create_proxy_config,
+    format_proxy_for_request,
+    parse_proxy_url,
+    validate_proxy_url,
+    get_proxy_info
+)
+
+# 分布式协调工具
+from .distributed_coordinator import (
+    TaskDistributor,
+    DeduplicationTool,
+    DistributedCoordinator,
+    generate_task_id,
+    claim_task,
+    report_task_status,
+    get_cluster_info,
+    generate_pagination_tasks,
+    distribute_tasks
+)
+
+__all__ = [
+    # 日期工具
+    "TimeUtils",
+    "parse_time",
+    "format_time",
+    "time_diff",
+    "to_timestamp",
+    "to_datetime",
+    "now",
+    "to_timezone",
+    "to_utc",
+    "to_local",
+    "from_timestamp_with_tz",
+    
+    # 数据清洗工具
+    "TextCleaner",
+    "DataFormatter",
+    "EncodingConverter",
+    "remove_html_tags",
+    "decode_html_entities",
+    "remove_extra_whitespace",
+    "remove_special_chars",
+    "normalize_unicode",
+    "clean_text",
+    "extract_numbers",
+    "extract_emails",
+    "extract_urls",
+    "format_number",
+    "format_currency",
+    "format_percentage",
+    "format_phone_number",
+    "format_chinese_id_card",
+    "capitalize_words",
+    "detect_encoding",
+    "to_utf8",
+    "convert_encoding",
+    
+    # 数据验证工具
+    "DataValidator",
+    "validate_email",
+    "validate_phone",
+    "validate_url",
+    "validate_chinese_id_card",
+    "validate_date",
+    "validate_number_range",
+    "check_data_integrity",
+    
+    # 重试机制封装
+    "RetryMechanism",
+    "retry",
+    "should_retry",
+    "exponential_backoff",
+    
+    # 反爬虫应对工具
+    "ProxyPoolManager",
+    "CaptchaHandler",
+    "AntiCrawler",
+    "get_random_user_agent",
+    "rotate_proxy",
+    "handle_captcha",
+    "detect_rate_limiting",
+    
+    # 带认证代理工具
+    "AuthenticatedProxy",
+    "create_proxy_config",
+    "format_proxy_for_request",
+    "parse_proxy_url",
+    "validate_proxy_url",
+    "get_proxy_info",
+    
+    # 分布式协调工具
+    "TaskDistributor",
+    "DeduplicationTool",
+    "DistributedCoordinator",
+    "generate_task_id",
+    "claim_task",
+    "report_task_status",
+    "get_cluster_info",
+    "generate_pagination_tasks",
+    "distribute_tasks"
 ]