Update README.md

ADC_function.py

@@ -1,10 +1,42 @@
 import requests
+from configparser import RawConfigParser
+import os
+import re
 
-def get_html(url):#网页请求核心
+# content = open('proxy.ini').read()
-    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+# content = re.sub(r"\xfe\xff","", content)
-    getweb = requests.get(str(url),timeout=5,headers=headers)
+# content = re.sub(r"\xff\xfe","", content)
-    getweb.encoding='utf-8'
+# content = re.sub(r"\xef\xbb\xbf","", content)
-    try:
+# open('BaseConfig.cfg', 'w').write(content)
-        return getweb.text
+
-    except:
+config = RawConfigParser()
-        print("[-]Connect Failed! Please check your Proxy.")
+if os.path.exists('proxy.ini'):
+    config.read('proxy.ini', encoding='UTF-8')
+else:
+    with open("proxy.ini", "wt", encoding='UTF-8') as code:
+        print("[proxy]",file=code)
+        print("proxy=127.0.0.1:1080",file=code)
+
+def get_html(url,cookies = None):#网页请求核心
+    if not str(config['proxy']['proxy']) == '':
+        proxies = {
+            "http" : "http://"  + str(config['proxy']['proxy']),
+            "https": "https://" + str(config['proxy']['proxy'])
+        }
+        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
+        getweb = requests.get(str(url), headers=headers, proxies=proxies,cookies=cookies)
+        getweb.encoding = 'utf-8'
+        # print(getweb.text)
+        try:
+            return getweb.text
+        except:
+            print('[-]Connected failed!:Proxy error')
+    else:
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+        getweb = requests.get(str(url),  headers=headers,cookies=cookies)
+        getweb.encoding = 'utf-8'
+        try:
+            return getweb.text
+        except:
+             print("[-]Connect Failed.")

AV_Data_Capture.py

@@ -2,6 +2,21 @@ import glob
 import os
 import time
 import re
+import sys
+from ADC_function import *
+import json
+
+version='0.10.3'
+
+def UpdateCheck():
+    html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
+    html = json.loads(str(html2))
+
+    if not version == html['version']:
+        print('[*]        * New update '+html['version']+' *')
+        print('[*]             * Download *')
+        print('[*] '+html['download'])
+        print('[*]=====================================')
 
 def movie_lists():
     #MP4
@@ -18,8 +33,10 @@ def movie_lists():
     f2 = glob.glob(os.getcwd() + r"\*.mkv")
     # FLV
     g2 = glob.glob(os.getcwd() + r"\*.flv")
+    # TS
+    h2 = glob.glob(os.getcwd() + r"\*.ts")
 
-    total = a2+b2+c2+d2+e2+f2+g2
+    total = a2+b2+c2+d2+e2+f2+g2+h2
     return total
 
 def lists_from_test(custom_nuber): #电影列表
@@ -45,6 +62,10 @@ def rreplace(self, old, new, *max):
     return new.join(self.rsplit(old, count))
 
 if __name__ =='__main__':
+    print('[*]===========AV Data Capture===========')
+    print('[*]           Version '+version)
+    print('[*]=====================================')
+    UpdateCheck()
     os.chdir(os.getcwd())
     for i in movie_lists(): #遍历电影列表 交给core处理
         if '_' in i:
@@ -57,4 +78,4 @@ if __name__ =='__main__':
     print("[!]Cleaning empty folders")
     CEF('JAV_output')
     print("[+]All finished!!!")
-    time.sleep(3)
+    input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看错误信息。")

README.md

@@ -1,37 +1,36 @@
-# 日本AV元数据抓取工具  （刮削器）
+# 前言
-
+&emsp;&emsp;目前，我下的AV越来越多，也意味着AV要集中地管理，形成媒体库。现在有两款主流的AV元数据获取器，"EverAver"和"Javhelper"。前者的优点是元数据获取比较全，缺点是不能批量处理；后者优点是可以批量处理，但是元数据不够全。<br>
-## 关于本软件 （~路star谢谢）
+&emsp;&emsp;为此，综合上述软件特点，我写出了本软件，为了方便的管理本地AV，和更好的手冲体验。
-
-**#0.5重大更新：新增对FC2,259LUXU,SIRO,300MAAN系列影片抓取支持,优化对无码视频抓取**
-
-目前，我下的AV越来越多，也意味着AV要集中地管理，形成媒体库。现在有两款主流的AV元数据获取器，"EverAver"和"Javhelper"。前者的优点是元数据获取比较全，缺点是不能批量处理；后者优点是可以批量处理，但是元数据不够全。
-
-为此，综合上述软件特点，我写出了本软件，为了方便的管理本地AV，和更好的手冲体验。没女朋友怎么办ʅ(‾◡◝)ʃ 
-
-**预计本周末适配DS Video，暂时只支持Kodi,EMBY**
-
-**tg官方电报群:https://t.me/AV_Data_Capture_Official**
-
-### **请认真阅读下面使用说明再使用** * [如何使用](#如何使用)
 
+**可以结合pockies大神的[ 打造本地AV（毛片）媒体库 ](https://pockies.github.io/2019/03/25/everaver-emby-kodi/)看本文档**<br>
+**tg官方电报群:[ 点击进群](https://t.me/AV_Data_Capture_Official)**<br>
+**推荐用法: 按照 [如何使用](#如何使用) 使用该软件后，对于不能正常获取元数据的电影可以用[ Everaver ](http://everaver.blogspot.com/)来补救**<br>
 ![](https://i.loli.net/2019/06/02/5cf2b5d0bbecf69019.png)
 
+# 捐助二维码
+如果你觉得本软件好用，可以考虑捐助作者，你的支持就是我的动力，非常感谢您的捐助
+![](https://i.loli.net/2019/06/21/5d0c3dcdc95c979755.png)
 
-## 软件流程图
+# 免责声明
-![](https://i.loli.net/2019/06/02/5cf2bb9a9e2d997635.png)
+1.本软件仅供技术交流，学术交流使用<br>
+2.本软件不提供任何有关淫秽色情的影视下载方式<br>
+3.使用者使用该软件产生的一切法律后果由使用者承担<br>
+4.该软件禁止任何商用行为<br>
 
-## 如何使用
+# 如何使用
-### **请认真阅读下面使用说明**
+release的程序可脱离python环境运行，可跳过第一步<br>
-  **release的程序可脱离python环境运行，可跳过第一步（仅限windows平台)**
+下载地址(仅限Windows):https://github.com/wenead99/AV_Data_Capture/releases
-  **下载地址(Windows):https://github.com/wenead99/AV_Data_Capture/releases**
+### 简要教程:<br>
-1. 请安装requests,pyquery,lxml,Beautifulsoup4,pillow模块,可在CMD逐条输入以下命令安装
+**1.把软件拉到和电影的同一目录<br>2.设置ini文件的代理<br>3.运行软件等待完成<br>4.把JAV_output导入至KODI,EMBY中。<br>详细请看以下教程**
+
+## 1.请安装模块,在CMD/终端逐条输入以下命令安装
 ```python
 pip install requests
 ```
-###
+### 
 ```python
 pip install pyquery
-   ```
+```
 ###
 ```python
 pip install lxml
@@ -44,34 +43,62 @@ pip install Beautifulsoup4
 ```python
 pip install pillow
 ```
+###
 
-2. 你的AV在被软件管理前最好命名为番号:
+## 2. 配置
+#### 1.针对网络审查国家或地区
+
+打开```proxy.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowsocks/R,V2RAY本地代理端口:<br>
+例子:```proxy=127.0.0.1:1080```<br>
+**如果遇到tineout错误，可以把文件的proxy=后面的地址和端口删除，并开启vpn全局模式，或者重启电脑，vpn，网卡**
+
+#### 2.（可选）设置自定义目录和影片重命名规则
+**已有默认配置**<br>
+##### 命名参数<br>
+>title = 片名<br>
+>actor = 演员<br>
+>studio = 公司<br>
+>director = 导演<br>
+>release = 发售日<br>
+>year = 发行年份<br>
+>number = 番号<br>
+>cover = 封面链接<br>
+>tag = 类型<br>
+>outline = 简介<br>
+>runtime = 时长<br>
+##### **例子**:<br>
+>目录结构：'JAV_output/'+actor+'/'+actor+' '+' ['+year+']'+title+' ['+number+']'<br>
+>影片命名（上面目录之下的文件）:'['+number+']-'+title
+
+## 3. 关于番号提取失败或者异常
+**目前可以提取元素的影片:JAVBUS上有元数据的电影，素人系列(需要日本代理):300Maan,259luxu,siro等,FC2系列**<br>
+>下一张图片来自Pockies的blog:https://pockies.github.io/2019/03/25/everaver-emby-kodi/ 原作者已授权<br>
+
+![](https://raw.githubusercontent.com/Pockies/pic/master/741f9461gy1g1cxc31t41j20i804zdgo.jpg)
+
+目前作者已经完善了番号提取机制，功能较为强大，可提取上述文件名的的番号，如果出现提取失败或者异常的情况，请用以下规则命名<br>
+**妈蛋不要喂软件那么多野鸡片子，不让软件好好活了，操**
 ```
 COSQ-004.mp4
 ```
-或者
+
-```
-COSQ_004.mp4
-```
 文件名中间要有下划线或者减号"_","-"，没有多余的内容只有番号为最佳，可以让软件更好获取元数据
-对于多影片重命名，可以用ReNamer来批量重命名
+对于多影片重命名，可以用[ReNamer](http://www.den4b.com/products/renamer)来批量重命名
-软件官网:http://www.den4b.com/products/renamer
-
-![](https://i.loli.net/2019/06/02/5cf2b5cfbfe1070559.png)
-
-3. 把软件拷贝到AV的所在目录下，运行程序（中国大陆用户必须挂VPN，Shsadowsocks开全局代理）
-4. 运行AV_Data_capture.py
-5. **你也可以把单个影片拖动到core程序**
 
+## 4. 把软件拷贝和AV的统一目录下
+## 5. 运行 ```AV_Data_capture.py/.exe```
+你也可以把单个影片拖动到core程序<br>
 ![](https://i.loli.net/2019/06/02/5cf2b5d03640e73201.gif)
 
-6. 软件会自动把元数据获取成功的电影移动到JAV_output文件夹中，根据女优分类，失败的电影移动到failed文件夹中。
+## 6. 软件会自动把元数据获取成功的电影移动到JAV_output文件夹中，根据女优分类，失败的电影移动到failed文件夹中。
-
+## 7. 把JAV_output文件夹导入到EMBY,KODI中，根据封面选片子，享受手冲乐趣
-7. 把JAV_output文件夹导入到EMBY,KODI中，根据封面选片子，享受手冲乐趣
+## 8.输出的文件如下
-
 ![](https://i.loli.net/2019/06/02/5cf2b5cfd1b0226763.png)
 ![](https://i.loli.net/2019/06/02/5cf2b5cfd1b0246492.png)
 ![](https://i.loli.net/2019/06/02/5cf2b5d009e4930666.png)
 
+## 软件流程图
+![](https://i.loli.net/2019/06/02/5cf2bb9a9e2d997635.png)
+
 
 

core.py

@@ -8,6 +8,8 @@ import javbus
 import json
 import fc2fans_club
 import siro
+from ADC_function import *
+from configparser import ConfigParser
 
 #初始化全局变量
 title=''
@@ -16,36 +18,197 @@ year=''
 outline=''
 runtime=''
 director=''
-actor=[]
+actor_list=[]
+actor=''
 release=''
 number=''
 cover=''
 imagecut=''
 tag=[]
+naming_rule  =''#eval(config['Name_Rule']['naming_rule'])
+location_rule=''#eval(config['Name_Rule']['location_rule'])
+#=====================本地文件处理===========================
+def argparse_get_file():
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument("file", help="Write the file path on here")
+    args = parser.parse_args()
+    return args.file
+def CreatFailedFolder():
+    if not os.path.exists('failed/'):  # 新建failed文件夹
+        try:
+            os.makedirs('failed/')
+        except:
+            print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
+            os._exit(0)
+def getNumberFromFilename(filepath):
+    global title
+    global studio
+    global year
+    global outline
+    global runtime
+    global director
+    global actor_list
+    global actor
+    global release
+    global number
+    global cover
+    global imagecut
+    global tag
 
+    global naming_rule
+    global location_rule
+
+#================================================获取文件番号================================================
+    try:    #试图提取番号
+    # ====番号获取主程序====
+        try:  # 普通提取番号 主要处理包含减号-的番号
+            filepath.strip('22-sht.me').strip('-HD').strip('-hd')
+            filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath))  # 去除文件名中文件名
+            file_number = re.search('\w+-\d+', filename).group()
+        except:  # 提取不含减号-的番号
+            try:  # 提取东京热番号格式 n1087
+                filename1 = str(re.sub("h26\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
+                filename0 = str(re.sub(".*?\.com-\d+", "", filename1)).strip('_')
+                file_number = str(re.search('n\d{4}', filename0).group(0))
+            except:  # 提取无减号番号
+                filename1 = str(re.sub("h26\d", "", filepath))  # 去除h264/265
+                filename0 = str(re.sub(".*?\.com-\d+", "", filename1))
+                file_number2 = str(re.match('\w+', filename0).group())
+                file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),re.match("^[A-Za-z]+", file_number2).group() + '-'))
+                if not re.search('\w-', file_number).group() == 'None':
+                    file_number = re.search('\w+-\w+', filename).group()
+                #上面是插入减号-到番号中
+        print("[!]Making Data for   [" + filename + "],the number is [" + file_number + "]")
+    # ====番号获取主程序=结束===
+    except Exception as e: #番号提取异常
+        print('[-]'+str(os.path.basename(filepath))+' Cannot catch the number :')
+        print('[-]' + str(os.path.basename(filepath)) + ' :', e)
+        print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+        os._exit(0)
+    except IOError as e2:
+        print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
+        print('[-]' + str(os.path.basename(filepath)) + ' :',e2)
+        print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+        os._exit(0)
+    try:
+
+
+
+
+# ================================================网站规则添加开始================================================
+
+        try:  #添加 需要 正则表达式的规则
+            #=======================javbus.py=======================
+            if re.search('^\d{5,}', file_number).group() in filename:
+                json_data = json.loads(javbus.main_uncensored(file_number))
+        except: #添加 无需 正则表达式的规则
+            # ====================fc2fans_club.py===================
+            if 'fc2' in filename:
+                json_data = json.loads(fc2fans_club.main(file_number.strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-')))
+            elif 'FC2' in filename:
+                json_data = json.loads(fc2fans_club.main(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-')))
+                #print(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-'))
+            #=======================javbus.py=======================
+            else:
+                json_data = json.loads(javbus.main(file_number))
+
+
+
+#================================================网站规则添加结束================================================
+
+
+
+
+        title     = json_data['title']
+        studio    = json_data['studio']
+        year      = json_data['year']
+        outline   = json_data['outline']
+        runtime   = json_data['runtime']
+        director  = json_data['director']
+        actor_list= str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
+        release   = json_data['release']
+        number    = json_data['number']
+        cover     = json_data['cover']
+        imagecut  = json_data['imagecut']
+        tag       = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')   #字符串转列表
+        actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
+
+        naming_rule  = eval(config['Name_Rule']['naming_rule'])
+        location_rule =eval(config['Name_Rule']['location_rule'])
+    except IOError as e:
+        print('[-]'+str(e))
+        print('[-]Move ' + filename + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
+        os._exit(0)
+
+    except Exception as e:
+        print('[-]'+str(e))
+        print('[-]Move ' + filename + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
+        os._exit(0)
+path = '' #设置path为全局变量，后面移动文件要用
+def creatFolder():
+    global path
+    if len(actor) > 240:                    #新建成功输出文件夹
+        path = location_rule.replace("'actor'","'超多人'",3).replace("actor","'超多人'",3) #path为影片+元数据所在目录
+        #print(path)
+    else:
+        path = location_rule
+        #print(path)
+    if not os.path.exists(path):
+        os.makedirs(path)
 #=====================资源下载部分===========================
 def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
-    import requests
+    config = ConfigParser()
-    try:
+    config.read('proxy.ini', encoding='UTF-8')
-        if not os.path.exists(path):
+    proxy = str(config['proxy']['proxy'])
-            os.makedirs(path)
+    if not str(config['proxy']['proxy']) == '':
-        r = requests.get(url)
+        try:
-        with open(str(path) + "/"+str(filename), "wb") as code:
+            if not os.path.exists(path):
-            code.write(r.content)
+                os.makedirs(path)
-    except IOError as e:
+            headers = {
-        print("[-]Movie not found in All website!")
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
-        #print("[*]=====================================")
+            r = requests.get(url, headers=headers,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)})
-        return "failed"
+            with open(str(path) + "/" + filename, "wb") as code:
-    except Exception as e1:
+                code.write(r.content)
-        print(e1)
+                # print(bytes(r),file=code)
-        print("[-]Download Failed2!")
+        except IOError as e:
-        time.sleep(3)
+            print("[-]Movie not found in All website!")
-        os._exit(0)
+            print("[-]" + filename, e)
+            # print("[*]=====================================")
+            return "failed"
+        except Exception as e1:
+            print(e1)
+            print("[-]Download Failed2!")
+            time.sleep(3)
+            os._exit(0)
+    else:
+        try:
+            if not os.path.exists(path):
+                os.makedirs(path)
+            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+            r = requests.get(url, headers=headers)
+            with open(str(path) + "/" + filename, "wb") as code:
+                code.write(r.content)
+                # print(bytes(r),file=code)
+        except IOError as e:
+            print("[-]Movie not found in All website!")
+            print("[-]" + filename, e)
+            # print("[*]=====================================")
+            return "failed"
+        except Exception as e1:
+            print(e1)
+            print("[-]Download Failed2!")
+            time.sleep(3)
+            os._exit(0)
 def PrintFiles(path):
     try:
         if not os.path.exists(path):
             os.makedirs(path)
-        with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code:
+        with open(path + "/" + naming_rule + ".nfo", "wt", encoding='UTF-8') as code:
             print("<movie>", file=code)
             print(" <title>" + title + "</title>", file=code)
             print("  <set>", file=code)
@@ -56,11 +219,11 @@ def PrintFiles(path):
             print("  <plot>"+outline+"</plot>", file=code)
             print("  <runtime>"+str(runtime).replace(" ","")+"</runtime>", file=code)
             print("  <director>" + director + "</director>", file=code)
-            print("  <poster>" + number + ".png</poster>", file=code)
+            print("  <poster>" + naming_rule + ".png</poster>", file=code)
-            print("  <thumb>" + number + ".png</thumb>", file=code)
+            print("  <thumb>" + naming_rule + ".png</thumb>", file=code)
-            print("  <fanart>"+number + '.jpg'+"</fanart>", file=code)
+            print("  <fanart>"+naming_rule + '.jpg'+"</fanart>", file=code)
             try:
-                for u in actor:
+                for u in actor_list:
                     print("  <actor>", file=code)
                     print("   <name>" + u + "</name>", file=code)
                     print("  </actor>", file=code)
@@ -73,153 +236,54 @@ def PrintFiles(path):
                 for i in tag:
                     print("  <tag>" + i + "</tag>", file=code)
             except:
-                aaaa=''
+                aaaaa=''
+            try:
+                for i in tag:
+                    print("  <genre>" + i + "</genre>", file=code)
+            except:
+                aaaaaaaa=''
             print("  <num>" + number + "</num>", file=code)
             print("  <release>" + release + "</release>", file=code)
             print("  <cover>"+cover+"</cover>", file=code)
             print("  <website>" + "https://www.javbus.com/"+number + "</website>", file=code)
             print("</movie>", file=code)
-            print("[+]Writeed!    "+path + "/" + number + ".nfo")
+            print("[+]Writeed!          "+path + "/" + naming_rule + ".nfo")
     except IOError as e:
         print("[-]Write Failed!")
         print(e)
     except Exception as e1:
         print(e1)
         print("[-]Write Failed!")
-
-#=====================本地文件处理===========================
-def argparse_get_file():
-    import argparse
-    parser = argparse.ArgumentParser()
-    parser.add_argument("file", help="Write the file path on here")
-    args = parser.parse_args()
-    return args.file
-def getNumberFromFilename(filepath):
-    global title
-    global studio
-    global year
-    global outline
-    global runtime
-    global director
-    global actor
-    global release
-    global number
-    global cover
-    global imagecut
-    global tag
-
-    filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", os.path.basename(filepath)))
-    print("[!]Making Data for ["+filename+"]")
-    file_number = str(re.search('\w+-\w+', filename).group())
-    #print(a)
-    try:
-
-
-
-
-
-#================================================网站规则添加开始================================================
-
-
-        try:  #添加 需要 正则表达式的规则
-            if re.search('^\d{5,}', file_number).group() in filename:
-                json_data = json.loads(javbus.main_uncensored(file_number))
-        except: #添加 无需 正则表达式的规则
-            if 'fc2' in filename:
-                json_data = json.loads(fc2fans_club.main(file_number))
-            elif 'FC2' in filename:
-                json_data = json.loads(fc2fans_club.main(file_number))
-            elif 'siro' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif 'SIRO' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '259luxu' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '259LUXU' in filename:
-                json_data = json.loads(siro.main(file_number))
-            else:
-                json_data = json.loads(javbus.main(file_number))
-
-
-#================================================网站规则添加结束================================================
-
-
-
-
-
-
-        title = json_data['title']
-        studio = json_data['studio']
-        year = json_data['year']
-        outline = json_data['outline']
-        runtime = json_data['runtime']
-        director = json_data['director']
-        actor = str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',')
-        release = json_data['release']
-        number = json_data['number']
-        cover = json_data['cover']
-        imagecut = json_data['imagecut']
-        tag =   str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')
-    except:
-        print('[-]File '+filename+'`s number can not be caught')
-        print('[-]Move ' + filename + ' to failed folder')
-        if not os.path.exists('failed/'):  # 新建failed文件夹
-            os.makedirs('failed/')
-            if not os.path.exists('failed/'):
-                print("[-]failed!Dirs can not be make (Please run as Administrator)")
-                time.sleep(3)
-                os._exit(0)
-        shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
-        os._exit(0)
-
-path = '' #设置path为全局变量，后面移动文件要用
-
-def creatFolder():
-    actor2 = str(actor).strip("[ ]").replace("'",'').replace(" ",'')
-    global path
-    if not os.path.exists('failed/'): #新建failed文件夹
-        os.makedirs('failed/')
-        if not os.path.exists('failed/'):
-            print("[-]failed!Dirs can not be make (Please run as Administrator)")
-            os._exit(0)
-    if len(actor2) > 240:    #新建成功输出文件夹
-        path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录
-    else:
-        path = 'JAV_output' + '/' + str(actor2) + '/' + str(number)
-    if not os.path.exists(path):
-        os.makedirs(path)
-    path = str(os.getcwd())+'/'+path
-
 def imageDownload(filepath): #封面是否下载成功，否则移动到failed
-    if DownloadFileWithFilename(cover,str(number) + '.jpg', path) == 'failed':
+    if DownloadFileWithFilename(cover,naming_rule+ '.jpg', path) == 'failed':
         shutil.move(filepath, 'failed/')
         os._exit(0)
-    DownloadFileWithFilename(cover, number + '.jpg', path)
+    DownloadFileWithFilename(cover, naming_rule + '.jpg', path)
-    print('[+]Image Downloaded!', path +'/'+number+'.jpg')
+    print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg')
 def cutImage():
     if imagecut == 1:
         try:
-            img = Image.open(path + '/' + number + '.jpg')
+            img = Image.open(path + '/' + naming_rule + '.jpg')
             imgSize = img.size
             w = img.width
             h = img.height
             img2 = img.crop((w / 1.9, 0, w, h))
-            img2.save(path + '/' + number + '.png')
+            img2.save(path + '/' + naming_rule + '.png')
         except:
             print('[-]Cover cut failed!')
     else:
-        img = Image.open(path + '/' + number + '.jpg')
+        img = Image.open(path + '/' + naming_rule + '.jpg')
         w = img.width
         h = img.height
-        img.save(path + '/' + number + '.png')
+        img.save(path + '/' + naming_rule + '.png')
-
 def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
-    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$', filepath).group())
+    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
-    os.rename(filepath, number + houzhui)
+    os.rename(filepath, naming_rule + houzhui)
-    shutil.move(number + houzhui, path)
+    shutil.move(naming_rule + houzhui, path)
 
 if __name__ == '__main__':
     filepath=argparse_get_file() #影片的路径
+    CreatFailedFolder()
     getNumberFromFilename(filepath) #定义番号
     creatFolder() #创建文件夹
     imageDownload(filepath) #creatFoder会返回番号路径

fc2fans_club.py

@@ -7,7 +7,9 @@ def getTitle(htmlcode): #获取厂商
     #print(htmlcode)
     html = etree.fromstring(htmlcode,etree.HTMLParser())
     result = str(html.xpath('/html/body/div[2]/div/div[1]/h3/text()')).strip(" ['']")
-    return result
+    result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
+    #print(result2)
+    return result2
 def getStudio(htmlcode): #获取厂商
     html = etree.fromstring(htmlcode,etree.HTMLParser())
     result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
@@ -15,6 +17,7 @@ def getStudio(htmlcode): #获取厂商
 def getNum(htmlcode):     #获取番号
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
+    #print(result)
     return result
 def getRelease(number):
     a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
@@ -37,22 +40,26 @@ def getOutline(htmlcode,number):     #获取番号
 #     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
 #     return result
 
-def main(number):
+def main(number2):
-    str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")
+    number=number2.replace('PPV','').replace('ppv','')
     htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
     dic = {
         'title': getTitle(htmlcode),
         'studio': getStudio(htmlcode),
-        'year': getRelease(number),
+        'year': str(re.search('\d{4}',getRelease(number)).group()),
         'outline': getOutline(htmlcode,number),
         'runtime': '',
         'director': getStudio(htmlcode),
         'actor': '',
         'release': getRelease(number),
-        'number': number,
+        'number': 'FC2-'+number,
         'cover': getCover(htmlcode,number),
         'imagecut': 0,
         'tag':" ",
     }
+    #print(getTitle(htmlcode))
+    #print(getNum(htmlcode))
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
-    return js
+    return js
+
+#print(main('1104989'))

javbus.py

@@ -9,14 +9,8 @@ from bs4 import BeautifulSoup#need install
 from PIL import Image#need install
 import time
 import json
-
+from ADC_function import *
-def get_html(url):#网页请求核心
+import siro
-    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
-    getweb = requests.get(str(url),timeout=5,headers=headers).text
-    try:
-        return getweb
-    except:
-        print("[-]Connect Failed! Please check your Proxy.")
 
 def getTitle(htmlcode):  #获取标题
     doc = pq(htmlcode)
@@ -34,7 +28,6 @@ def getCover(htmlcode):  #获取封面链接
     doc = pq(htmlcode)
     image = doc('a.bigImage')
     return image.attr('href')
-    print(image.attr('href'))
 def getRelease(htmlcode): #获取出版日期
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
@@ -62,8 +55,10 @@ def getOutline(htmlcode):  #获取演员
     doc = pq(htmlcode)
     result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
     return result
-
+def getSerise(htmlcode):
-
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
+    return result
 def getTag(htmlcode):  # 获取演员
     tag = []
     soup = BeautifulSoup(htmlcode, 'lxml')
@@ -76,10 +71,57 @@ def getTag(htmlcode):  # 获取演员
 
 
 def main(number):
-    htmlcode=get_html('https://www.javbus.com/'+number)
+    try:
-    dww_htmlcode=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+        htmlcode = get_html('https://www.javbus.com/' + number)
+        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+        dic = {
+            'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
+            'studio': getStudio(htmlcode),
+            'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
+            'outline': getOutline(dww_htmlcode),
+            'runtime': getRuntime(htmlcode),
+            'director': getDirector(htmlcode),
+            'actor': getActor(htmlcode),
+            'release': getRelease(htmlcode),
+            'number': getNum(htmlcode),
+            'cover': getCover(htmlcode),
+            'imagecut': 1,
+            'tag': getTag(htmlcode),
+            'label': getSerise(htmlcode),
+        }
+        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+
+        if 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
+            htmlcode = get_html('https://www.javbus.com/' + number)
+            dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+            dic = {
+                'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
+                'studio': getStudio(htmlcode),
+                'year': getYear(htmlcode),
+                'outline': getOutline(dww_htmlcode),
+                'runtime': getRuntime(htmlcode),
+                'director': getDirector(htmlcode),
+                'actor': getActor(htmlcode),
+                'release': getRelease(htmlcode),
+                'number': getNum(htmlcode),
+                'cover': getCover(htmlcode),
+                'imagecut': 1,
+                'tag': getTag(htmlcode),
+                'label': getSerise(htmlcode),
+            }
+            js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
+                             separators=(',', ':'), )  # .encode('UTF-8')
+            return js2
+        return js
+    except:
+        a=siro.main(number)
+        return a
+
+def main_uncensored(number):
+    htmlcode = get_html('https://www.javbus.com/' + number)
+    dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
     dic = {
-        'title': getTitle(htmlcode),
+        'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
         'studio': getStudio(htmlcode),
         'year': getYear(htmlcode),
         'outline': getOutline(dww_htmlcode),
@@ -89,44 +131,20 @@ def main(number):
         'release': getRelease(htmlcode),
         'number': getNum(htmlcode),
         'cover': getCover(htmlcode),
-        'imagecut': 1,
-        'tag':getTag(htmlcode)
-    }
-    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
-    return js
-
-def main_uncensored(number):
-    htmlcode = get_html('https://www.javbus.com/' + number)
-    dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
-    #print('un')
-    #print('https://www.javbus.com/' + number)
-    dic = {
-        'title': getTitle(htmlcode),
-        'studio': getStudio(htmlcode),
-        'year': getYear(htmlcode),
-        'outline': getOutline(htmlcode),
-        'runtime': getRuntime(htmlcode),
-        'director': getDirector(htmlcode),
-        'actor': getActor(htmlcode),
-        'release': getRelease(htmlcode),
-        'number': getNum(htmlcode),
-        'cover': getCover(htmlcode),
         'tag': getTag(htmlcode),
+        'label': getSerise(htmlcode),
         'imagecut': 0,
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
 
-    if getYear(htmlcode) == '':
+    if getYear(htmlcode) == '' or getYear(htmlcode) == 'null':
-        #print('un2')
         number2 = number.replace('-', '_')
         htmlcode = get_html('https://www.javbus.com/' + number2)
-        #print('https://www.javbus.com/' + number2)
+        dic2 = {
-        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number2.replace("_", ''))
+            'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
-        dic = {
-            'title': getTitle(htmlcode),
             'studio': getStudio(htmlcode),
             'year': getYear(htmlcode),
-            'outline': getOutline(htmlcode),
+            'outline': '',
             'runtime': getRuntime(htmlcode),
             'director': getDirector(htmlcode),
             'actor': getActor(htmlcode),
@@ -134,13 +152,15 @@ def main_uncensored(number):
             'number': getNum(htmlcode),
             'cover': getCover(htmlcode),
             'tag': getTag(htmlcode),
+            'label':getSerise(htmlcode),
             'imagecut': 0,
         }
-        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        js2 = json.dumps(dic2, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
-        #print(js)
+        return js2
-        return js
+
-    else:
+    return js
-        bbb=''
+
+#print(main('SIRO-3821'))
 
 
 # def return1():

proxy.ini

@@ -0,0 +1,6 @@
+[proxy]
+proxy=127.0.0.1:1080
+
+[Name_Rule]
+location_rule='JAV_output/'+actor+'/'+'['+number+']-'+title
+naming_rule=number

siro.py

@@ -3,70 +3,74 @@ from lxml import etree
 import json
 import requests
 from bs4 import BeautifulSoup
-
+from ADC_function import *
-def get_html(url):#网页请求核心
-    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
-    cookies = {'adc':'1'}
-    getweb = requests.get(str(url),timeout=5,cookies=cookies,headers=headers).text
-    try:
-        return getweb
-    except:
-        print("[-]Connect Failed! Please check your Proxy.")
 
 def getTitle(a):
     html = etree.fromstring(a, etree.HTMLParser())
     result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
     return result
 def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
-    html = etree.fromstring(a, etree.HTMLParser())
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[1]/td/a/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table/tr[1]/td[1]/text()')).strip(" ['\\n                                        ']")
-    return result
+    result1 = str(html.xpath('//table/tr[1]/td[1]/a/text()')).strip(" ['\\n                                        ']")
+    return str(result1+result2).strip('+')
 def getStudio(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    result=str(html.xpath('//table[2]/tr[2]/td/a/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table[2]/tr[2]/td/text()')).strip(" ['\\n                                        ']")
-    return result
+    result1 = str(html.xpath('//table/tr[2]/td[1]/a/text()')).strip(" ['\\n                                        ']")
+    return str(result1+result2).strip('+')
 def getRuntime(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    result=str(html.xpath('//table[2]/tr[3]/td/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table/tr[3]/td[1]/text()')).strip(" ['\\n                                        ']")
-    return result
+    result1 = str(html.xpath('//table/tr[3]/td[1]/a/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+').strip('mi')
+def getLabel(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result2=str(html.xpath('//table/tr[6]/td[1]/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//table/tr[6]/td[1]/a/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+')
 def getNum(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    result=str(html.xpath('//table[2]/tr[4]/td/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table/tr[2]/td[4]/a/text()')).strip(" ['\\n                                        ']")
-    return result
+    result1 = str(html.xpath('//table/tr[2]/td[4]/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+')
 def getYear(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    #result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table/tr[2]/td[5]/a/text()')).strip(" ['\\n                                        ']")
-    result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    result1=str(html.xpath('//table/tr[2]/td[5]/text()')).strip(" ['\\n                                        ']")
-    return result
+    return result2+result1
 def getRelease(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table/tr[5]/td[1]/text()')).strip(" ['\\n                                        ']")
-    return result
+    result1 = str(html.xpath('//table/tr[5]/a/td[1]/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+')
 def getTag(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    result=str(html.xpath('//table[2]/tr[9]/td/text()')).strip(" ['\\n                                        ']")
+    result2=str(html.xpath('//table/tr[8]/td[1]/a/text()')).strip(" ['\\n                                        ']")
-    return result
+    result1=str(html.xpath('//table/tr[8]/td[1]/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+')
 def getCover(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']")
     return result
 def getDirector(a):
     html = etree.fromstring(a, etree.HTMLParser())
-    result = str(html.xpath('//table[2]/tr[7]/td/a/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//table/tr[2]/td[1]/text()')).strip(" ['\\n                                        ']")
-    return result
+    result2 = str(html.xpath('//table/tr[2]/td[1]/a/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+')
 def getOutline(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
     return result
-
 def main(number):
-    htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number))
+    htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number),cookies={'adc':'1'})
     soup = BeautifulSoup(htmlcode, 'lxml')
     a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n                                        ','')
+    #print(a)
     dic = {
         'title': getTitle(htmlcode).replace("\\n",'').replace('        ',''),
         'studio': getStudio(a),
-        'year': getYear(a),
+        'year': str(re.search('\d{4}',getRelease(a)).group()),
         'outline': getOutline(htmlcode),
         'runtime': getRuntime(a),
         'director': getDirector(a),
@@ -75,7 +79,10 @@ def main(number):
         'number': number,
         'cover': getCover(htmlcode),
         'imagecut': 0,
-        'tag':' ',
+        'tag': getTag(a).replace("'\\n',",'').replace(' ', '').replace("\\n','\\n",','),
+        'label':getLabel(a)
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
-    return js
+    #print('https://www.mgstage.com/product/product_detail/'+str(number))
+    return js
+#print(main('SIRO-3552'))

update_check.json

@@ -0,0 +1,5 @@
+{
+	"version": "0.10.3",
+	"version_show":"Beta 10.3",
+	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
+}