<fix>1.修复日志不落盘的问题 2.修复fc2,javbus爬虫 3.添加默认windows特权目录跳过

Author: ShawnQiang1

config.yml

@@ -15,7 +15,7 @@ scanner:
   # 哪些后缀的文件应当视为影片？
   filename_extensions: [.3gp, .avi, .f4v, .flv, .iso, .m2ts, .m4v, .mkv, .mov, .mp4, .mpeg, .rm, .rmvb, .ts, .vob, .webm, .wmv, .strm, .mpg]
   # 扫描影片文件时忽略指定的文件夹
-  ignored_folder_name_pattern: ['^\.', '^#recycle$', '^#整理完成$', '^#不要扫描$']
+  ignored_folder_name_pattern: ['^\.', '^#recycle$', '^#整理完成$','^#未整理$', '^#不要扫描$', 'System Volume Information','\$RECYCLE.BIN']
   # 匹配番号时忽略小于指定大小的文件
   # 格式要求：https://docs.pydantic.dev/2.0/usage/types/bytesize/
   minimum_size: 232MiB
@@ -29,7 +29,7 @@ network:
   # 各个站点的免代理地址。地址失效时软件会自动尝试获取新地址，你也可以手动设置
   proxy_free:
     avsox: 'https://avsox.click'
-    javbus: 'https://www.seedmm.help'
+    javbus: 'https://www.seedmm.help' #已失效，自己开个代理吧
     javdb: 'https://javdb368.com'
     javlib: 'https://www.y78k.com'
   # 网络问题导致抓取数据失败时的重试次数，通常3次就差不多了

javsp/__main__.py

@@ -26,12 +26,56 @@
 from javsp.cropper import Cropper, get_cropper
 
 
-# 将StreamHandler的stream修改为TqdmOut，以与Tqdm协同工作
-root_logger = logging.getLogger()
-for handler in root_logger.handlers:
-    if type(handler) == logging.StreamHandler:
-        handler.stream = TqdmOut
+def setup_logging():
+    """配置日志系统，同时输出到控制台和文件"""
+    from javsp.lib import resource_path
+    
+    # 清除现有的handlers，避免重复
+    root_logger = logging.getLogger()
+    root_logger.handlers.clear()
+    
+    # 设置日志级别
+    root_logger.setLevel(logging.INFO)
+    
+    # 创建日志格式
+    formatter = logging.Formatter(
+        '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+    
+    # 配置控制台输出（重定向到TqdmOut）
+    console_handler = logging.StreamHandler(TqdmOut)
+    console_handler.setLevel(logging.INFO)  # 控制台只显示INFO及以上级别
+    console_handler.setFormatter(formatter)
+    root_logger.addHandler(console_handler)
+    
+    # 配置文件输出到JavSP.log
+    log_file = os.path.join(resource_path('.'), 'JavSP.log')
+    file_handler = logging.FileHandler(log_file, encoding='utf-8')
+    file_handler.setLevel(logging.DEBUG)  # 文件记录DEBUG及以上所有级别
+    file_handler.setFormatter(formatter)
+    root_logger.addHandler(file_handler)
+    
+    # 为filemove logger配置独立的文件处理器
+    filemove_handler = logging.FileHandler(
+        os.path.join(resource_path('.'), 'FileMove.log'),
+        encoding='utf-8'
+    )
+    filemove_handler.setLevel(logging.DEBUG)
+    filemove_handler.setFormatter(formatter)
+    
+    filemove_logger = logging.getLogger('filemove')
+    filemove_logger.addHandler(filemove_handler)
+    filemove_logger.setLevel(logging.DEBUG)
+    # 防止日志向上传播到root logger造成重复
+    filemove_logger.propagate = False
+    
+    print(f"日志配置完成: 控制台输出 + 文件输出到 {log_file}")
+
+# 设置日志系统
+setup_logging()
 
+# 获取主logger
 logger = logging.getLogger('main')
 
 
@@ -45,7 +89,7 @@
 from javsp.web.exceptions import *
 from javsp.web.translate import translate_movie_info
 
-from javsp.config import Cfg, CrawlerID
+from javsp.config import Cfg, CrawlerID, UseJavDBCover
 from javsp.prompt import prompt
 
 actressAliasMap = {}
@@ -523,9 +567,9 @@ def check_step(result, msg='步骤错误'):
             if movie != all_movies[-1] and Cfg().crawler.sleep_after_scraping > Duration(0):
                 time.sleep(Cfg().crawler.sleep_after_scraping.total_seconds())
             return_movies.append(movie)
-        # except Exception as e:
-        #     logger.debug(e, exc_info=True)
-        #     logger.error(f'整理失败: {e}')
+        except Exception as e:
+            # logger.debug(e, exc_info=True)
+            logger.error(f'整理失败: {e}')
         finally:
             inner_bar.close()
     return return_movies

javsp/file.py

@@ -36,6 +36,7 @@ def scan_movies(root: str) -> List[Movie]:
         for name in dirnames.copy():
             if ignore_folder_name_pattern.match(name):
                 dirnames.remove(name)
+                continue # 直接跳过,防止因为没有访问权限到下面又报错
             # 移除有nfo的文件夹
             if Cfg().scanner.skip_nfo_dir:
                 if any(file.lower().endswith(".nfo") for file in os.listdir(os.path.join(dirpath, name)) if isinstance(file, str)):

javsp/web/base.py

@@ -21,7 +21,13 @@
 __all__ = ['Request', 'get_html', 'post_html', 'request_get', 'resp2html', 'is_connectable', 'download', 'get_resp_text', 'read_proxy']
 
 
-headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36'}
+headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
+        'Connection': 'keep-alive',
+        'Upgrade-Insecure-Requests': '1',
+    }
 
 logger = logging.getLogger(__name__)
 # 删除js脚本相关的tag，避免网页检测到没有js运行环境时强行跳转，影响调试

javsp/web/fc2.py

@@ -56,8 +56,8 @@ def parse_data(movie: MovieInfo):
     # FC2没有制作商和发行商的区分，作为个人市场，影片页面的'by'更接近于制作商
     producer = container.xpath("//li[text()='by ']/a/text()")[0]
     genre = container.xpath("//a[@class='tag tagTag']/text()")
-    date_str = container.xpath("//div[@class='items_article_Releasedate']/p/text()")[0]
-    publish_date = date_str[-10:].replace('/', '-')  # '販売日 : 2017/11/30'
+    date_str = container.xpath("//div[@class='items_article_softDevice'][2]/p/text()")[0]
+    publish_date = date_str.split(' : ')[1].replace('/', '-')  # '販売日 : 2017/11/30'
     preview_pics = container.xpath("//ul[@data-feed='sample-images']/li/a/@href")
 
     if Cfg().crawler.hardworking: