cnks 0.3.0__tar.gz → 0.3.2__tar.gz

{cnks-0.3.0 → cnks-0.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cnks
-Version: 0.3.0
+Version: 0.3.2
 Summary: 中国知网搜索与引文处理系统
 Author-email: bai-z-l <b@iziliang.com>
 Requires-Python: >=3.12

{cnks-0.3.0 → cnks-0.3.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cnks"
-version = "0.3.0"
+version = "0.3.2"
 description = "中国知网搜索与引文处理系统"
 readme = "README.md"
 requires-python = ">=3.12"

{cnks-0.3.0 → cnks-0.3.2}/src/citzer.py

@@ -13,7 +13,6 @@
 3. 处理验证页面和特殊情况
 4. 返回结构化引文数据
 """
-import logging
 import os
 import platform
 import traceback
@@ -21,45 +20,36 @@ import time
 import re
 from typing import Dict, List, Any, Optional, Union
 
-# 配置日志记录
-try:
-    # 尝试使用绝对路径
-    log_dir = os.path.dirname(os.path.abspath(__file__))
-    log_file = os.path.join(os.path.dirname(log_dir), "cnks_citzer.log")
+# 禁用日志记录
+class DummyLogger:
+    """空日志记录器，用于禁用日志输出"""
+    def __init__(self, *args, **kwargs):
+        pass
+    
+    def debug(self, *args, **kwargs):
+        pass
     
-    # 创建处理器
-    file_handler = logging.FileHandler(log_file, mode="a")
-    console_handler = logging.StreamHandler()
+    def info(self, *args, **kwargs):
+        pass
     
-    # 设置格式
-    formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
-    file_handler.setFormatter(formatter)
-    console_handler.setFormatter(formatter)
+    def warning(self, *args, **kwargs):
+        pass
     
-    # 获取日志记录器并添加处理器
-    logger = logging.getLogger("cnks.citzer")
-    logger.setLevel(logging.DEBUG)
+    def error(self, *args, **kwargs):
+        pass
     
-    # 移除现有处理器以避免重复
-    if logger.handlers:
-        for handler in logger.handlers:
-            logger.removeHandler(handler)
+    def critical(self, *args, **kwargs):
+        pass
     
-    logger.addHandler(file_handler)
-    logger.addHandler(console_handler)
+    def addHandler(self, *args, **kwargs):
+        pass
     
-    # 打印确认信息
-    print(f"Citzer logger initialized, logging to: {log_file}")
-    logger.info(f"Citzer logging to: {log_file}")
-except Exception as e:
-    # 回退到基本控制台日志记录
-    logging.basicConfig(
-        level=logging.DEBUG,
-        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-    )
-    logger = logging.getLogger("cnks.citzer")
-    logger.error(f"Failed to set up file logging: {str(e)}")
-    print(f"Error setting up citzer file logging: {str(e)}")
+    def setLevel(self, *args, **kwargs):
+        pass
+
+# 使用空日志记录器
+logger = DummyLogger()
+print = lambda *args, **kwargs: None  # 禁用print函数
 
 # 导入必要的模块
 try:
@@ -67,7 +57,6 @@ try:
     PLAYWRIGHT_AVAILABLE = True
 except ImportError:
     PLAYWRIGHT_AVAILABLE = False
-    logger.error("Playwright not available. Install with: pip install playwright")
 
 # 尝试导入其他模块
 try:
@@ -76,7 +65,7 @@ except ImportError:
     try:
         from ifverify import check_verification_needed, handle_verification
     except ImportError:
-        logger.warning("无法导入验证处理模块，部分功能可能不可用")
+        pass
 
 class Citzer:
     """引文分析器类，负责浏览器管理和引文内容提取"""
@@ -88,11 +77,8 @@ class Citzer:
         self.context = None
         self.browser_started = False
         
-        # 创建调试截图目录
-        self.debug_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "debug_screenshots")
-        os.makedirs(self.debug_dir, exist_ok=True)
-        
-        logger.info("Citzer初始化完成")
+        # 不创建调试截图目录
+        self.debug_dir = "/dev/null" if platform.system() != "Windows" else "NUL"
     
     async def start_browser(self) -> bool:
         """
@@ -102,24 +88,18 @@ class Citzer:
             bool: 浏览器是否成功启动
         """
         if self.browser_started:
-            logger.info("浏览器已启动，重用现有实例")
             return True
             
         if not PLAYWRIGHT_AVAILABLE:
-            logger.error("Playwright未安装，无法启动浏览器")
             return False
             
         try:
-            logger.info("使用持久上下文启动浏览器")
-            
             # 创建Playwright实例
             self.playwright = await async_playwright().start()
-            logger.info("Playwright已启动")
             
             # 创建用户数据目录（如果不存在）
             user_data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "chrome_data")
             os.makedirs(user_data_dir, exist_ok=True)
-            logger.info(f"使用Chrome用户数据目录: {user_data_dir}")
             
             # 设置Chrome参数
             browser_args = [
@@ -129,8 +109,6 @@ class Citzer:
             
             # 查找Chrome可执行文件
             chrome_path = self._find_chrome_executable()
-            if chrome_path:
-                logger.info(f"使用Chrome路径: {chrome_path}")
             
             # 使用持久上下文启动浏览器
             self.context = await self.playwright.chromium.launch_persistent_context(
@@ -139,22 +117,17 @@ class Citzer:
                 headless=False,
                 args=browser_args
             )
-            logger.info("使用持久上下文启动浏览器成功")
             
             # 创建一个初始页面确保上下文已激活
             init_page = await self.context.new_page()
             await init_page.goto("about:blank")
             await init_page.close()
-            logger.info("使用空白页初始化浏览器")
             
             # 标记浏览器已启动
             self.browser_started = True
             return True
             
         except Exception as e:
-            logger.error(f"启动浏览器时出错: {str(e)}")
-            logger.error(traceback.format_exc())
-            
             # 清理资源
             await self.close_browser()
             return False
@@ -166,29 +139,22 @@ class Citzer:
         Returns:
             bool: 是否成功关闭
         """
-        logger.info("关闭浏览器资源")
-        
         try:
             # 关闭浏览器上下文
             if self.context:
                 await self.context.close()
                 self.context = None
-                logger.info("浏览器上下文已关闭")
             
             # 停止Playwright
             if self.playwright:
                 await self.playwright.stop()
                 self.playwright = None
-                logger.info("Playwright已停止")
             
             # 重置浏览器状态
             self.browser_started = False
-            logger.info("浏览器资源已成功关闭")
             return True
             
-        except Exception as e:
-            logger.error(f"关闭浏览器时出错: {str(e)}")
-            logger.error(traceback.format_exc())
+        except Exception:
             self.browser_started = False
             return False
     
@@ -225,10 +191,8 @@ class Citzer:
         for path in candidates:
             expanded_path = os.path.expanduser(path)
             if os.path.exists(expanded_path) and os.access(expanded_path, os.X_OK):
-                logger.info(f"找到Chrome路径: {expanded_path}")
                 return expanded_path
         
-        logger.warning("未找到Chrome可执行文件")
         return None
     
     async def open_page(self, url: str) -> Optional[Page]:
@@ -245,13 +209,11 @@ class Citzer:
         if self.context is None and not self.browser_started:
             success = await self.start_browser()
             if not success:
-                logger.error("无法启动浏览器，放弃打开页面")
                 return None
         
         try:
             # 创建新标签页
             page = await self.context.new_page()
-            logger.info(f"已创建新标签页，正在导航到URL: {url}")
             
             # 导航到指定URL
             await page.goto(url, wait_until="domcontentloaded", timeout=30000)
@@ -259,19 +221,14 @@ class Citzer:
             # 检查是否需要验证
             verification_needed = await check_verification_needed(page)
             if verification_needed:
-                logger.info("检测到需要人工验证，等待10秒钟...")
                 await page.wait_for_timeout(10000)  # 等待10秒
-            else:
-                logger.info("未检测到验证页面，继续执行")
             
             # 等待页面完全加载
             await page.wait_for_load_state("networkidle", timeout=30000)
             
             return page
             
-        except Exception as e:
-            logger.error(f"打开页面时出错: {str(e)}")
-            logger.error(traceback.format_exc())
+        except Exception:
             return None
     
     async def process_link(self, link: str) -> Dict[str, Any]:
@@ -286,31 +243,22 @@ class Citzer:
         """
         page = None
         try:
-            logger.info(f"处理链接: {link}")
-            
             # 检查是否已经有浏览器上下文(可能是共享的)
             if self.context is None and not self.browser_started:
-                logger.info("尝试启动浏览器")
                 await self.start_browser()
             
             # 打开链接
             page = await self.open_page(link)
             if not page:
-                logger.error(f"无法打开链接: {link}")
                 return {}
             
-            # 获取页面截图用于调试
-            screenshot_path = os.path.join(self.debug_dir, f"link_page_{int(time.time())}.png")
-            await page.screenshot(path=screenshot_path)
-            logger.info(f"已保存页面截图: {screenshot_path}")
+            # 不进行截图操作
             
             # 提取摘要
             abstract = await self._extract_abstract(page)
-            logger.info(f"提取的摘要: {abstract[:100]}..." if abstract else "未提取到摘要")
             
             # 提取引用信息
             citation = await self.extract_citation_from_button(page)
-            logger.info(f"提取的引用信息: {citation}" if citation else "未提取到引用信息")
             
             # 如果提取失败，尝试从页面标题获取基本信息
             if not citation:
@@ -319,7 +267,6 @@ class Citzer:
                     "title": title,
                     "raw_extracted": True
                 }
-                logger.info(f"使用页面标题作为基本信息: {title}")
             
             # 组合结果
             result = {
@@ -333,24 +280,18 @@ class Citzer:
             if not result["title"] and result["cite_format"]:
                 result["title"] = self.extract_title_from_cite(result["cite_format"])
             
-            logger.info(f"成功处理链接: {link}")
             return result
             
-        except Exception as e:
-            logger.error(f"处理链接 {link} 时出错: {str(e)}")
-            logger.error(traceback.format_exc())
+        except Exception:
             return {}
             
         finally:
             if page:
                 await page.close()
-                logger.info(f"已关闭链接页面: {link}")
     
     async def extract_from_html(self, page):
         """从HTML页面提取引用信息"""
         try:
-            logger.info(f"开始从页面提取引用信息")
-            
             # 等待页面加载完成
             await page.wait_for_load_state("networkidle")
             
@@ -371,14 +312,11 @@ class Citzer:
                 if result.get('title') and not result.get('cite_format'):
                     result['cite_format'] = f"{result['title']}"
                 
-                logger.info(f"成功提取引用信息")
                 return result
             else:
-                logger.warning("无法提取引用信息")
                 return None
             
-        except Exception as e:
-            logger.error(f"提取引用信息时出错: {str(e)}")
+        except Exception:
             return None
     
     @staticmethod
@@ -412,13 +350,9 @@ class Citzer:
                 abstract = re.sub(r'\s+', ' ', abstract).strip()
                 result["abstract"] = abstract
             
-            logger.info(f"Citation data processed, title: {result['title']}")
-            print(f"Citzer: processed citation, title: {result.get('title', '')[:30]}...")
             return result
             
-        except Exception as e:
-            logger.error(f"Error processing citation data: {str(e)}")
-            print(f"Citzer error: {str(e)}")
+        except Exception:
             # Return raw data
             return {
                 "title": citation_data.get("title", ""),
@@ -437,8 +371,8 @@ class Citzer:
             match = re.search(r'[\.。]\s*([^\.。]+)[\.。]', cite_format)
             if match:
                 return match.group(1).strip()
-        except Exception as e:
-            logger.error(f"Error extracting title from citation format: {str(e)}")
+        except Exception:
+            pass
         
         return ""
     
@@ -454,8 +388,8 @@ class Citzer:
             if match:
                 authors_str = match.group(1)
                 return [a.strip() for a in re.split(r'[,，、]', authors_str) if a.strip()]
-        except Exception as e:
-            logger.error(f"Error extracting authors from citation format: {str(e)}")
+        except Exception:
+            pass
         
         return []
     
@@ -541,22 +475,13 @@ class Citzer:
                 """
                 abstract = await page.evaluate(abstract_js)
                 if abstract:
-                    logger.info("从页面直接提取到摘要信息")
                     citation_data["abstract"] = abstract
-            except Exception as e:
-                logger.error(f"直接提取页面信息时出错: {str(e)}")
-            
-            # 创建调试截图目录
-            debug_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "debug_screenshots")
-            os.makedirs(debug_dir, exist_ok=True)
+            except Exception:
+                pass
             
-            # 获取当前页面截图用于调试
-            screenshot_path = os.path.join(debug_dir, f"pre_citation_click_{int(time.time())}.png")
-            await page.screenshot(path=screenshot_path)
-            logger.info(f"已保存点击前截图: {screenshot_path}")
+            # 不创建调试截图
             
             # 使用JavaScript定位并点击引用按钮
-            logger.info("使用JavaScript查找并点击引用按钮")
             js_button_finder = """
             () => {
                 // 根据已知的HTML结构首先尝试精确定位
@@ -679,36 +604,27 @@ class Citzer:
             
             button_info = await page.evaluate(js_button_finder)
             if button_info and button_info.get('found'):
-                logger.info(f"通过JavaScript找到引用按钮: {button_info.get('text')} ({button_info.get('tag')})，方法: {button_info.get('method', 'unknown')}")
-                
                 # 使用鼠标点击坐标
                 x, y = button_info.get('x'), button_info.get('y') 
                 await page.mouse.click(x, y)
-                logger.info(f"已点击坐标 ({x}, {y}) 处的引用按钮")
                 
                 # 等待引用对话框出现
                 await page.wait_for_timeout(2000)
                 
-                # 获取点击后截图
-                screenshot_path = os.path.join(debug_dir, f"post_js_click_{int(time.time())}.png")
-                await page.screenshot(path=screenshot_path)
-                logger.info(f"已保存JavaScript点击后截图: {screenshot_path}")
+                # 不获取点击后截图
                 
                 # 提取引用信息
                 cite_result = await self._extract_citation_text(page)
                 if cite_result:
                     cite_result.update(citation_data)
                     return cite_result
-            else:
-                logger.info("未能使用JavaScript找到引用按钮")
             
             # 如果点击按钮都失败了，但我们已经提取到了其他信息
             if citation_data:
                 return citation_data
             
-        except Exception as e:
-            logger.error(f"提取引用信息时出错: {str(e)}")
-            logger.error(traceback.format_exc())
+        except Exception:
+            pass
         
         return {}
         
@@ -767,19 +683,15 @@ class Citzer:
             ''')
             
             if cite_result:
-                logger.info("成功提取引用文本")
                 return {
                     "title": "",
                     "cite_format": cite_result,
                     "abstract": ""
                 }
             else:
-                logger.warning("无法提取引用文本")
                 return {}
             
-        except Exception as e:
-            logger.error(f"提取引用文本时出错: {str(e)}")
-            logger.error(traceback.format_exc())
+        except Exception:
             return {}
     
     async def _extract_abstract(self, page) -> str:
@@ -854,15 +766,12 @@ class Citzer:
             
             abstract = await page.evaluate(abstract_js)
             if abstract:
-                logger.info("成功从页面提取摘要")
                 # 清理摘要文本
                 abstract = abstract.replace("摘要:", "").replace("摘要：", "").replace("Abstract:", "").strip()
                 return abstract
             else:
-                logger.info("未能找到页面摘要内容")
                 return ""
                 
-        except Exception as e:
-            logger.error(f"提取摘要时出错: {str(e)}")
+        except Exception:
             return ""