Merge pull request #621 from lededev/storyline-1

三种调用接口保持一致性

.vscode/launch.json

@@ -5,8 +5,26 @@
             "name": "AV_Data_Capture",
             "type": "python",
             "request": "launch",
+            "console": "integratedTerminal",
+            "env": {
+                "PYTHONIOENCODING": "utf-8"
+            },
             "program": "${workspaceFolder}/AV_Data_capture.py",
-            "console": "integratedTerminal"
+            "program1": "${workspaceFolder}/WebCrawler/javbus.py",
+            "program2": "${workspaceFolder}/WebCrawler/javdb.py",
+            "program3": "${workspaceFolder}/WebCrawler/xcity.py",
+            "program4": "${workspaceFolder}/number_parser.py",
+            "program5": "${workspaceFolder}/config.py",
+            "cwd0": "${fileDirname}",
+            "cwd1": "${workspaceFolder}/dist",
+            "cwd2": "${env:HOME}${env:USERPROFILE}/.avdc",
+            "args0": ["-a","-p","J:/Downloads","-o","J:/log"],
+            "args1": ["-g","-m","3","-c","1","-d","0"],
+            "args2": ["-igd0", "-m3", "-p", "J:/JAV_output", "-q", "121220_001"],
+            "args3": ["-agd0","-m3", "-q", ".*","-p","J:/#JAV_output3"],
+            "args4": ["-gic1", "-d0", "-m3", "-o", "avlog", "-p", "I:/JAV_output"],
+            "args5": ["-gic1", "-d0", "-m1", "-o", "avlog", "-p", "J:/Downloads"],
+            "args6": ["-z", "-o", "J:/log"]
         }
     ]
-}
+}

AV_Data_Capture.py

@@ -35,7 +35,7 @@ def check_update(local_version):
         print("[*]======================================================")
 
 
-def argparse_function(ver: str) -> typing.Tuple[str, str, bool]:
+def argparse_function(ver: str) -> typing.Tuple[str, str, str, str, bool]:
     conf = config.getInstance()
     parser = argparse.ArgumentParser(epilog=f"Load Config file '{conf.ini_path}'.")
     parser.add_argument("file", default='', nargs='?', help="Single Movie file path.")
@@ -61,7 +61,7 @@ def argparse_function(ver: str) -> typing.Tuple[str, str, bool]:
                         help="""Only show job list of files and numbers, and **NO** actual operation
 is performed. It may help you correct wrong numbers before real job.""")
     parser.add_argument("-v", "--version", action="version", version=ver)
-    #ini_path
+
     args = parser.parse_args()
     def get_natural_number_or_none(value):
         return int(value) if isinstance(value, str) and value.isnumeric() and int(value)>=0 else None

WebCrawler/avsox.py

@@ -58,7 +58,7 @@ def getCover_small(html):
     return result
 def getTag(html):
     x = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
-    return x[2:] if len(x) > 2 else []
+    return [translateTag_to_sc(i.strip()) for i in x[2:]]  if len(x) > 2 else []
 def getSeries(html):
     try:
         result1 = str(html.xpath('//span[contains(text(),"系列:")]/../span[2]/text()')).strip(" ['']")

WebCrawler/storyline.py

@@ -16,7 +16,7 @@ G_mode_txt = ('顺序执行','线程池','进程池')
 
 class noThread(object):
     def map(self, fn, param):
-        return builtins.map(fn, param)
+        return list(builtins.map(fn, param))
     def __enter__(self):
         return self
     def __exit__(self, exc_type, exc_val, exc_tb):
@@ -34,11 +34,14 @@ def getStoryline(number, title, sites: list=None):
     else:
         storyine_sites += conf.storyline_censored_site().split(',')
     r_dup = set()
-    apply_sites = []
+    sort_sites = []
     for s in storyine_sites:
-        if s in G_registered_storyline_site and s not in r_dup:
-            apply_sites.append(s)
-            r_dup.add(s)
+        ns = re.sub(r'.*?:', '', s, re.A)
+        if ns in G_registered_storyline_site and ns not in r_dup:
+            sort_sites.append(s)
+            r_dup.add(ns)
+    sort_sites.sort()
+    apply_sites = [re.sub(r'.*?:', '', s, re.A) for s in sort_sites]
     mp_args = ((site, number, title, debug) for site in apply_sites)
     cores = min(len(apply_sites), os.cpu_count())
     if cores == 0:
@@ -47,7 +50,6 @@ def getStoryline(number, title, sites: list=None):
     assert run_mode in (0,1,2)
     with ThreadPool(cores) if run_mode == 1 else Pool(cores) if run_mode == 2 else noThread() as pool:
         result = pool.map(getStoryline_mp, mp_args)
-    result = list(result) if run_mode == 0 else result
     if not debug and conf.storyline_show() == 0:
         for value in result:
             if isinstance(value, str) and len(value):
@@ -126,7 +128,7 @@ def getStoryline_airav(number, debug):
         return desc
     except Exception as e:
         if debug:
-            print(f"[-]MP getOutline_amazon Error: {e},number [{number}].")
+            print(f"[-]MP getStoryline_airav Error: {e},number [{number}].")
         pass
     return None
 

config.ini

@@ -89,15 +89,15 @@ extrafanart_folder=extrafanart
 ; 剧情简介
 [storyline]
 ; website为javbus javdb avsox xcity carib时，site censored_site uncensored_site 为获取剧情简介信息的
-; 可选数据源站点列表。列表内站点同时并发查询，取值优先级从左到右，靠左站点没数据才会采用后面站点获得的。
+; 可选数据源站点列表。列表内站点同时并发查询，取值优先级由冒号前的序号决定，从小到大，数字小的站点没数据才会采用后面站点获得的。
 ; 其中airav avno1 58avgo是中文剧情简介，区别是airav只能查有码，avno1有码无码都能查，58avgo只能查无码或者
 ; 流出破解马赛克的影片(此功能没使用)。
 ; xcity和amazon是日语的，由于amazon商城没有番号信息，选中对应DVD的准确率仅99.6%。如果三个列表全部为空则不查询，
 ; 设置成不查询可大幅提高刮削速度。
 ; site=
-site=avno1
-censored_site=airav,xcity,amazon
-uncensored_site=58avgo
+site=3:avno1
+censored_site=1:airav,4:xcity,5:amazon
+uncensored_site=2:58avgo
 ; 运行模式：0:顺序执行(最慢) 1:线程池(默认值) 2:进程池(启动开销比线程池大，并发站点越多越快)
 run_mode=1
 ; show_result剧情简介调试信息 0关闭 1简略 2详细(详细部分不记入日志)，剧情简介失效时可打开2查看原因