Beta 11.5 Update

ADC_function.py

@@ -0,0 +1,71 @@
+import requests
+from configparser import RawConfigParser
+import os
+import re
+from retrying import retry
+import time
+import sys
+
+config = RawConfigParser()
+if os.path.exists('config.ini'):
+    try:
+        config.read('config.ini', encoding='UTF-8')
+    except:
+        print('[-]Config.ini read failed! Please use the offical file!')
+else:
+    print('[+]config.ini: not found, creating...')
+    with open("config.ini", "wt", encoding='UTF-8') as code:
+        print("[proxy]",file=code)
+        print("proxy=127.0.0.1:1080",file=code)
+        print("timeout=10", file=code)
+        print("retry=3", file=code)
+        print("", file=code)
+        print("[Name_Rule]", file=code)
+        print("location_rule='JAV_output/'+actor+'/'+number",file=code)
+        print("naming_rule=number+'-'+title",file=code)
+        print("", file=code)
+        print("[update]",file=code)
+        print("update_check=1",file=code)
+    time.sleep(2)
+    print('[+]config.ini: created!')
+    try:
+        config.read('config.ini', encoding='UTF-8')
+    except:
+        print('[-]Config.ini read failed! Please use the offical file!')
+
+def UpdateCheckSwitch():
+    check=str(config['update']['update_check'])
+    if check == '1':
+        return '1'
+    elif check == '0':
+        return '0'
+def get_html(url,cookies = None):#网页请求核心
+    i = 0
+    retry_count = int(config['proxy']['retry'])
+    while i < retry_count:
+        try:
+            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, timeout=int(config['proxy']['timeout']),proxies=proxies, cookies=cookies)
+                getweb.encoding = 'utf-8'
+                return getweb.text
+            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, timeout=int(config['proxy']['timeout']), cookies=cookies)
+                getweb.encoding = 'utf-8'
+                return getweb.text
+        except requests.exceptions.RequestException:
+            i += 1
+            print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+        except requests.exceptions.ConnectionError:
+            i += 1
+            print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+        except requests.exceptions.ProxyError:
+            i += 1
+            print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+        except requests.exceptions.ConnectTimeout:
+            i += 1
+            print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+
+

AV_Data_Capture.py

@@ -1,32 +1,59 @@
 import glob
 import os
 import time
+import re
+import sys
+import ADC_function
+import json
+import shutil
 
+version='0.11.5'
+os.chdir(os.getcwd())
+
+def UpdateCheck():
+    if ADC_function.UpdateCheckSwitch() == '1':
+        html2 = ADC_function.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('[*]=====================================')
+    else:
+        print('[+]Update Check disabled!')
 def movie_lists():
     #MP4
-    a2 = glob.glob(os.getcwd() + r"\*.mp4")
+    a2 = glob.glob(r".\*.mp4")
     # AVI
-    b2 = glob.glob(os.getcwd() + r"\*.avi")
+    b2 = glob.glob(r".\*.avi")
     # RMVB
-    c2 = glob.glob(os.getcwd() + r"\*.rmvb")
+    c2 = glob.glob(r".\*.rmvb")
     # WMV
-    d2 = glob.glob(os.getcwd() + r"\*.wmv")
+    d2 = glob.glob(r".\*.wmv")
     # MOV
-    e2 = glob.glob(os.getcwd() + r"\*.mov")
+    e2 = glob.glob(r".\*.mov")
     # MKV
-    f2 = glob.glob(os.getcwd() + r"\*.mkv")
+    f2 = glob.glob(r".\*.mkv")
     # FLV
-    g2 = glob.glob(os.getcwd() + r"\*.flv")
+    g2 = glob.glob(r".\*.flv")
+    # TS
+    h2 = glob.glob(r".\*.ts")
 
-    total = a2+b2+c2+d2+e2+f2+g2
+    total = a2+b2+c2+d2+e2+f2+g2+h2
     return total
-
+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 lists_from_test(custom_nuber): #电影列表
 
     a=[]
     a.append(custom_nuber)
     return a
-
 def CEF(path):
     files = os.listdir(path)  # 获取路径下的子文件(夹)列表
     for file in files:
@@ -35,26 +62,80 @@ def CEF(path):
             print('[+]Deleting empty folder',path + '/' + file)
         except:
             a=''
-
 def rreplace(self, old, new, *max):
 #从右开始替换文件名中内容，源字符串，将被替换的子字符串， 新字符串，用于替换old子字符串，可选字符串, 替换不超过 max 次
     count = len(self)
     if max and str(max[0]).isdigit():
         count = max[0]
     return new.join(self.rsplit(old, count))
+def getNumber(filepath):
+    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
+            filepath1 = filepath.replace("_", "-")
+            filepath1.strip('22-sht.me').strip('-HD').strip('-hd')
+            filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath1))  # 去除文件名中时间
+            file_number = re.search('\w+-\d+', filename).group()
+            return file_number
+        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('_')
+                if '-C.' in filepath or '-c.' in filepath:
+                    cn_sub = '1'
+                file_number = str(re.search('n\d{4}', filename0).group(0))
+                return file_number
+            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())
+                if '-C.' in filepath or '-c.' in filepath:
+                    cn_sub = '1'
+                file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),
+                                                       re.match("^[A-Za-z]+", file_number2).group() + '-'))
+                return file_number
+                # 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
+    # ====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/')
+    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/')
+
+def RunCore():
+    if os.path.exists('core.py'):
+        os.system('python core.py' + '   "' + i + '" --number "'+getNumber(i)+'"')     #从py文件启动（用于源码py）
+    elif os.path.exists('core.exe'):
+        os.system('core.exe' + '   "' + i + '" --number "'+getNumber(i)+'"')           #从exe启动（用于EXE版程序）
+    elif os.path.exists('core.py') and os.path.exists('core.exe'):
+        os.system('python core.py' + '   "' + i + '" --number "' + getNumber(i) + '"') #从py文件启动（用于源码py）
 
 if __name__ =='__main__':
+    print('[*]===========AV Data Capture===========')
+    print('[*]           Version '+version)
+    print('[*]=====================================')
+    CreatFailedFolder()
+    UpdateCheck()
     os.chdir(os.getcwd())
+
+    count = 0
+    count_all = str(len(movie_lists()))
     for i in movie_lists(): #遍历电影列表 交给core处理
-        if '_' in i:
-            os.rename(i, rreplace(i,'_','-',1))
-            i = rreplace(i,'_','-',1)
-        os.system('python core.py' + ' "' + i + '"') #选择从py文件启动  （用于源码py）
-        #os.system('core.exe' + ' "' + i + '"')      #选择从exe文件启动（用于EXE版程序）
+        count = count + 1
+        percentage = str(count/int(count_all)*100)[:4]+'%'
+        print('[!] - '+percentage+' ['+str(count)+'/'+count_all+'] -')
+        print("[!]Making Data for   [" + i + "], the number is [" + getNumber(i) + "]")
+        RunCore()
         print("[*]=====================================")
 
-    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和错误信息。")

README.md

@@ -1,35 +1,77 @@
-# 日本AV元数据抓取工具  （刮削器）
-
-## 关于本软件 （~路star谢谢）
-
-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)
-
-![](readme/readme5.png)
+# AV Data Capture 日本电影元数据抓取工具（刮削器）
 
 
-## 软件流程图
-![](readme/flow_chart2.png)
+<a title="Hits" target="_blank" href="https://github.com/b3log/hits"><img src="https://hits.b3log.org/b3log/hits.svg"></a>
+![](https://img.shields.io/badge/build-passing-brightgreen.svg?style=flat-square)
+![](https://img.shields.io/github/downloads/yoshiko2/av_data_capture/total.svg?style=flat-square)<br>
+![](https://img.shields.io/github/languages/code-size/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/issues/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/license/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/release/yoshiko2/av_data_capture.svg?style=flat-square)<br>
+![](https://img.shields.io/github/forks/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/stars/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/watchers/yoshiko2/av_data_capture.svg?style=flat-square)
 
-## 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（仅限windows平台)**
-  **下载地址(Windows):https://github.com/wenead99/AV_Data_Capture/releases**
-1. 请安装requests,pyquery,lxml,Beautifulsoup4,pillow模块,可在CMD逐条输入以下命令安装
+# 目录
+* [免责声明](#免责声明)
+* [注意](#注意)
+* [你问我答 FAQ](#你问我答-faq)
+* [效果图](#效果图)
+* [如何使用](#如何使用)
+* [下载](#下载)
+* [简明教程](#简要教程)
+* [模块安装](#1请安装模块在cmd终端逐条输入以下命令安装)
+* [配置](#2配置configini)
+* [运行软件](#4运行-av_data_capturepyexe)
+* [异常处理（重要）](#5异常处理重要)
+* [导入至媒体库](#7把jav_output文件夹导入到embykodi中根据封面选片子享受手冲乐趣)
+* [写在后面](#8写在后面)
+
+# 免责声明
+1.本软件仅供**技术交流，学术交流**使用，本项目旨在学习Beautifulsoup, xpath, PyQuery<br>
+2.本软件禁止用于任何非法用途<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.不可使用于商业和个人其他意图<br>
+
+# 注意
+**tg官方电报群:[ 点击进群](https://t.me/AV_Data_Capture_Official)**<br>
+**推荐用法: 使用该软件后，对于不能正常获取元数据的电影可以用 Everaver 来补救**<br>
+暂不支持多P电影<br>
+
+# 你问我答 FAQ
+### F：这软件是干什么用的？
+**Q**：配合本地影片管理软件EMBY,KODI管理本地影片，该软件起到分类与元数据抓取作用，利用元数据信息来分类，**注意：不提供任何影片下载地址**。
+### F：什么是元数据？
+**Q**：元数据包括了影片的：封面，导演，演员，简介，类型......
+### F：软件收费吗？
+**Q**：软件是开源的，永久免费，作者强烈谴责那些**利用本软件牟利**的人，并希望他们**死妈**
+### F：软件运行异常怎么办？
+**Q**：认真看 [异常处理（重要）](#5异常处理重要)
+
+# 效果图
+**图片来自网络**，由于相关法律法规，具体效果请自行联想
+![](https://i.loli.net/2019/07/04/5d1cf9bb1b08b86592.jpg)
+![](https://i.loli.net/2019/07/04/5d1cf9bb2696937880.jpg)<br>
+
+# 如何使用
+### 下载
+* release的程序可脱离**python环境**运行，可跳过 [模块安装](#1请安装模块在cmd终端逐条输入以下命令安装)<br>Release 下载地址(**仅限Windows**):<br>[![](https://img.shields.io/badge/%E4%B8%8B%E8%BD%BD-windows-blue.svg?style=for-the-badge&logo=windows)](https://github.com/yoshiko2/AV_Data_Capture/releases/download/0.11.4/Beta11.4.zip)<br>
+* Linux,MacOS请下载源码包运行
+
+* Windows Python环境:[点击前往](https://www.python.org/downloads/windows/) 选中executable installer下载
+* MacOS Python环境：[点击前往](https://www.python.org/downloads/mac-osx/)
+* Linux Python环境：Linux用户懂的吧，不解释下载地址
+### 简要教程:<br>
+**1.把软件拉到和电影的同一目录<br>2.设置ini文件的代理（路由器拥有自动代理功能的可以把proxy=后面内容去掉）<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**<br>
+
+## 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
@@ -42,32 +84,100 @@ 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config.ini
+config.ini
+>[proxy]<br>
+>proxy=127.0.0.1:1080<br>
+>timeout=10<br>
+>retry=3<br>
+>
+>[Name_Rule]<br>
+>location_rule='JAV_output/'+actor+'/['+number+']-'+title<br>
+>naming_rule=number+'-'+title<br>
+>
+>[update]<br>
+>update_check=1<br>
+
+### 1.网络设置
+#### * 针对“某些地区”的代理设置
+打开```config.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowxxxx/X,V2XXX本地代理端口:<br>
+例子:```proxy=127.0.0.1:1080```<br>素人系列抓取建议使用日本代理<br>
+**路由器拥有自动代理功能的可以把proxy=后面内容去掉**<br>
+**本地代理软件开全局模式的同志同上**<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**<br>
+#### 连接超时重试设置
+>[proxy]<br>
+>timeout=10<br>
+
+10为超时重试时间 单位：秒
+#### 连接重试次数设置
+>[proxy]<br>
+>retry=3<br>
+
+3即为重试次数
+
+### (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>
+>目录结构规则:location_rule='JAV_output/'+actor+'/'+number **不推荐修改目录结构规则，抓取数据时新建文件夹容易出错**<br>
+>影片命名规则:naming_rule='['+number+']-'+title<br> **在EMBY,KODI等本地媒体库显示的标题**
+### 3.更新开关
+>[update]<br>update_check=1<br>
+1为开，0为关
+## 3.把软件拷贝和电影的统一目录下
+## 4.运行 ```AV_Data_capture.py/.exe```
+当文件名包含:<br>
+中文，字幕，-c., -C., 处理元数据时会加上**中文字幕**标签
+## 5.异常处理（重要）
+### 请确保软件是完整地！确保ini文件内容是和下载提供ini文件内容的一致的！
+### 关于软件打开就闪退
+可以打开cmd命令提示符，把 ```AV_Data_capture.py/.exe```拖进cmd窗口回车运行，查看错误，出现的错误信息**依据以下条目解决**
+### 关于```Updata_check```
+跳转 [网络设置](#1网络设置)
+### 关于```FileNotFoundError: [WinError 3] 系统找不到指定的路径。: 'JAV_output''```
+在软件所在文件夹下新建 JAV_output 文件夹
+### 关于连接拒绝的错误
+请设置好[代理](#1针对某些地区的代理设置)<br>
+### 关于Nonetype,xpath报错
+同上<br>
+### 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:300Maan,259luxu,siro等,FC2系列**<br>
+>下一张图片来自Pockies的blog 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
-软件官网:http://www.den4b.com/products/renamer
 
-![](readme/readme1.PNG)
+针对**野鸡番号**，你需要把文件名命名为与抓取网站提供的番号一致（文件拓展名除外），然后把文件拖拽至core.exe/.py<br>
+**野鸡番号**:比如 XXX-XXX-1这种野鸡三段式番号，在javbus等资料库存在的作品。<br>（除了SSNI-XXX-C，后面这种-C的是指电影有中文字幕！）<br>
+条件：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](http://www.den4b.com/products/renamer)来批量重命名<br>
+### 关于PIL/image.py
+暂时无解，可能是网络问题或者pillow模块打包问题，你可以用源码运行（要安装好第一步的模块）
 
-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**
 
-![](readme/single.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。
-
-![](readme/readme2.PNG)
-![](readme/readme3.PNG)
-![](readme/readme4.PNG)
+## 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，根据演员分类，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，等待元数据刷新，完成
+## 8.写在后面
+怎么样，看着自己的日本电影被这样完美地管理，是不是感觉成就感爆棚呢?<br>
 
 
 

config.ini

@@ -0,0 +1,12 @@
+[proxy]
+proxy=127.0.0.1:1080
+timeout=10
+retry=3
+
+[Name_Rule]
+location_rule='JAV_output/'+actor+'/'+number
+naming_rule=number+'-'+title
+
+[update]
+update_check=1
+#on=1,off=0

core.py

@@ -1,197 +1,323 @@
 import re
-import requests #need install
-from pyquery import PyQuery as pq#need install
-from lxml import etree#need install
 import os
 import os.path
 import shutil
-from bs4 import BeautifulSoup#need install
-from PIL import Image#need install
+from PIL import Image
 import time
+import javbus
+import json
+import fc2fans_club
+import siro
+from ADC_function import *
+from configparser import ConfigParser
+import argparse
+import javdb
 
-#=====================爬虫核心部分==========================
-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'}
-    getweb = requests.get(str(url),timeout=5,headers=headers).text
-    try:
-        return getweb
-    except:
-        print("[-]Connect Failed! Please check your Proxy.")
+#初始化全局变量
+title=''
+studio=''
+year=''
+outline=''
+runtime=''
+director=''
+actor_list=[]
+actor=''
+release=''
+number=''
+cover=''
+imagecut=''
+tag=[]
+cn_sub=''
+path=''
+houzhui=''
+website=''
+json_data={}
+actor_photo={}
+naming_rule  =''#eval(config['Name_Rule']['naming_rule'])
+location_rule=''#eval(config['Name_Rule']['location_rule'])
 
-def getTitle(htmlcode):  #获取标题
-    doc = pq(htmlcode)
-    title=str(doc('div.container h3').text()).replace(' ','-')
-    return title
-def getStudio(htmlcode): #获取厂商
-    html = etree.fromstring(htmlcode,etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
-    return result
-def getYear(htmlcode):   #获取年份
-    html = etree.fromstring(htmlcode,etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
-    result2 = str(re.search('\d{4}', result).group(0))
-    return result2
-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(" ['']")
-    return result
-def getRuntime(htmlcode): #获取分钟
-    soup = BeautifulSoup(htmlcode, 'lxml')
-    a = soup.find(text=re.compile('分鐘'))
-    return a
-def getActor(htmlcode):   #获取女优
-    b=[]
-    soup=BeautifulSoup(htmlcode,'lxml')
-    a=soup.find_all(attrs={'class':'star-name'})
-    for i in a:
-        b.append(i.text)
-    return ",".join(b)
-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(" ['']")
-    return result
-def getDirector(htmlcode): #获取导演
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
-    return result
-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
+#=====================本地文件处理===========================
+def moveFailedFolder():
+    global filepath
+    print('[-]Move to "failed"')
+    shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+    os._exit(0)
+def argparse_get_file():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--number", help="Enter Number on here", default='')
+    parser.add_argument("file", help="Write the file path on here")
+    args = parser.parse_args()
+    return (args.file, args.number)
+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 getDataFromJSON(file_number): #从JSON返回元数据
+    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 image_main
+    global cn_sub
+    global website
+    global actor_photo
+
+    global naming_rule
+    global location_rule
+
+
+    # ================================================网站规则添加开始================================================
+
+    try:    # 添加 需要 正则表达式的规则
+        # =======================javdb.py=======================
+        if re.search('^\d{5,}', file_number).group() in file_number:
+            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 file_number:
+            json_data = json.loads(fc2fans_club.main(
+                file_number.strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-')))
+        elif 'FC2' in file_number:
+            json_data = json.loads(fc2fans_club.main(
+                file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').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       = str(json_data['title']).replace(' ','')
+    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("'", '').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(" ", '')
+    actor_photo =     json_data['actor_photo']
+    website     =     json_data['website']
+
+    if title == '' or number == '':
+        print('[-]Movie Data not found!')
+        moveFailedFolder()
+
+    # ====================处理异常字符====================== #\/:*?"<>|
+    if '\\' in title:
+        title=title.replace('\\', ' ')
+    elif '/' in title:
+        title=title.replace('/', '')
+    elif ':' in title:
+        title=title.replace('/', '')
+    elif '*' in title:
+        title=title.replace('*', '')
+    elif '?' in title:
+        title=title.replace('?', '')
+    elif '"' in title:
+        title=title.replace('"', '')
+    elif '<' in title:
+        title=title.replace('<', '')
+    elif '>' in title:
+        title=title.replace('>', '')
+    elif '|' in title:
+        title=title.replace('|', '')
+    # ====================处理异常字符 END================== #\/:*?"<>|
+
+    naming_rule   = eval(config['Name_Rule']['naming_rule'])
+    location_rule = eval(config['Name_Rule']['location_rule'])
+def creatFolder(): #创建文件夹
+    global actor
+    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):
+        try:
+            os.makedirs(path)
+        except:
+            path = location_rule.replace('/['+number+']-'+title,"/number")
+            #print(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()
+    config.read('config.ini', encoding='UTF-8')
+    proxy       = str(config['proxy']['proxy'])
+    timeout     = int(config['proxy']['timeout'])
+    retry_count = int(config['proxy']['retry'])
+    i = 0
+
+    while i < retry_count:
+        try:
+            if not str(config['proxy']['proxy']) == '':
+                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, timeout=timeout,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)})
+                if r == '':
+                    print('[-]Movie Data not found!')
+                    os._exit(0)
+                with open(str(path) + "/" + filename, "wb") as code:
+                    code.write(r.content)
+                return
+            else:
+                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, timeout=timeout, headers=headers)
+                if r == '':
+                    print('[-]Movie Data not found!')
+                    os._exit(0)
+                with open(str(path) + "/" + filename, "wb") as code:
+                    code.write(r.content)
+                return
+        except requests.exceptions.RequestException:
+            i += 1
+            print('[-]Image Download :  Connect retry '+str(i)+'/'+str(retry_count))
+        except requests.exceptions.ConnectionError:
+            i += 1
+            print('[-]Image Download :  Connect retry '+str(i)+'/'+str(retry_count))
+        except requests.exceptions.ProxyError:
+            i += 1
+            print('[-]Image Download :  Connect retry '+str(i)+'/'+str(retry_count))
+        except requests.exceptions.ConnectTimeout:
+            i += 1
+            print('[-]Image Download :  Connect retry '+str(i)+'/'+str(retry_count))
+    moveFailedFolder()
+def imageDownload(filepath): #封面是否下载成功，否则移动到failed
+    global path
+    if DownloadFileWithFilename(cover,'fanart.jpg', path) == 'failed':
+        moveFailedFolder()
+    DownloadFileWithFilename(cover, 'fanart.jpg', path)
+    print('[+]Image Downloaded!', path +'/fanart.jpg')
+def PrintFiles(filepath):
+    #global path
+    global title
+    global cn_sub
+    global actor_photo
     try:
         if not os.path.exists(path):
             os.makedirs(path)
-        r = requests.get(url)
-        with open(str(path) + "/"+str(filename), "wb") as code:
-            code.write(r.content)
-    except IOError as e:
-        print("[-]Movie not found in All website!")
-        #print("[*]=====================================")
-        return "failed"
-    except Exception as e1:
-        print(e1)
-        print("[-]Download Failed2!")
-        time.sleep(3)
-        os._exit(0)
-def PrintFiles(html,path,number):
-    try:
-        if not os.path.exists(path):
-            os.makedirs(path)
-        with open(path + "/" + getNum(html) + ".nfo", "wt", encoding='UTF-8') as code:
+        with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code:
             print("<movie>", file=code)
-            print(" <title>" + getTitle(html) + "</title>", file=code)
+            print(" <title>" + naming_rule + "</title>", file=code)
             print("  <set>", file=code)
             print("  </set>", file=code)
-            print("  <studio>" + getStudio(html) + "+</studio>", file=code)
-            print("  <year>" + getYear(html) + "</year>", file=code)
-            print("  <outline>"+getOutline(get_html_dww(number))+"</outline>", file=code)
-            print("  <plot>"+getOutline(get_html_dww(number))+"</plot>", file=code)
-            print("  <runtime>"+str(getRuntime(html)).replace(" ","")+"</runtime>", file=code)
-            print("  <director>" + getDirector(html) + "</director>", file=code)
-            print("  <poster>" + getNum(html) + ".png</poster>", file=code)
-            print("  <thumb>" + getNum(html) + ".png</thumb>", file=code)
-            print("  <fanart>"+getNum(html) + '.jpg'+"</fanart>", file=code)
-            print("  <actor>", file=code)
-            print("    <name>" + getActor(html) + "</name>", file=code)
-            print("  </actor>", file=code)
-            print("  <maker>" + getStudio(html) + "</maker>", file=code)
+            print("  <studio>" + studio + "+</studio>", file=code)
+            print("  <year>" + year + "</year>", file=code)
+            print("  <outline>"+outline+"</outline>", file=code)
+            print("  <plot>"+outline+"</plot>", file=code)
+            print("  <runtime>"+str(runtime).replace(" ","")+"</runtime>", file=code)
+            print("  <director>" + director + "</director>", file=code)
+            print("  <poster>poster.png</poster>", file=code)
+            print("  <thumb>thumb.png</thumb>", file=code)
+            print("  <fanart>fanart.jpg</fanart>", file=code)
+            try:
+                for key, value in actor_photo.items():
+                    print("  <actor>", file=code)
+                    print("   <name>" + key + "</name>", file=code)
+                    if not actor_photo == '':  # or actor_photo == []:
+                        print("   <thumb>" + value + "</thumb>", file=code)
+                    print("  </actor>", file=code)
+            except:
+                aaaa=''
+            print("  <maker>" + studio + "</maker>", file=code)
             print("  <label>", file=code)
             print("  </label>", file=code)
-            print("  <num>" + getNum(html) + "</num>", file=code)
-            print("  <release>" + getRelease(html) + "</release>", file=code)
-            print("  <cover>"+getCover(html)+"</cover>", file=code)
-            print("  <website>" + "https://www.javbus.com/"+getNum(html) + "</website>", file=code)
+            if cn_sub == '1':
+                print("  <tag>中文字幕</tag>", file=code)
+            try:
+                for i in tag:
+                    print("  <tag>" + i + "</tag>", file=code)
+            except:
+                aaaaa=''
+            try:
+                for i in tag:
+                    print("  <genre>" + i + "</genre>", file=code)
+            except:
+                aaaaaaaa=''
+            if cn_sub == '1':
+                print("  <genre>中文字幕</genre>", file=code)
+            print("  <num>" + number + "</num>", file=code)
+            print("  <release>" + release + "</release>", file=code)
+            print("  <cover>"+cover+"</cover>", file=code)
+            print("  <website>" + website + "</website>", file=code)
             print("</movie>", file=code)
-            print("[+]Writeed!    "+path + "/" + getNum(html) + ".nfo")
+            print("[+]Writeed!          "+path + "/" + number + ".nfo")
     except IOError as e:
         print("[-]Write Failed!")
         print(e)
+        moveFailedFolder()
     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):
-    filename = str(os.path.basename(filepath)) #电影文件名
-    str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filename))
-
-    print("[!]Making Data for ["+filename+"]")
-    try:
-        a = str(re.search('\w+-\w+', filename).group())
-        return a
-    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)
-def get_html_javbus(number):
-    return get_html("https://www.javbus.com/" + str(number))
-def get_html_dww(number):
-    return get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
-path = '' #设置path为全局变量，后面移动文件要用
-def creatFolder(html,number):
-    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(getActor(html)) > 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
+        moveFailedFolder()
+def cutImage():
+    if imagecut == 1:
+        try:
+            img = Image.open(path + '/fanart.jpg')
+            imgSize = img.size
+            w = img.width
+            h = img.height
+            img2 = img.crop((w / 1.9, 0, w, h))
+            img2.save(path + '/poster.png')
+        except:
+            print('[-]Cover cut failed!')
     else:
-        path = 'JAV_output' + '/' + getActor(html) + '/' + number
-    if not os.path.exists(path):
-        os.makedirs(path)
-    path = str(os.getcwd())+'/'+path
-def imageDownload(htmlcode,filepath,number): #封面是否下载成功，否则移动到failed
-    if DownloadFileWithFilename(getCover(htmlcode),number + '.jpg', path) == 'failed':
-        shutil.move(filepath, 'failed/')
-        os._exit(0)
-    DownloadFileWithFilename(getCover(htmlcode), number + '.jpg', path)
-    print('[+]Image Downloaded!', path +'/'+number+'.jpg')
-def cutImage(number):
-    try:
-        img = Image.open(path + '/' + number + '.jpg')
-        imgSize=img.size
-        w=img.width
-        h=img.height
-        img2 = img.crop((w/1.9, 0, w, h))
-        img2.save(path + '/' + number + '.png')
-    except:
-        print('[-]Cover cut failed!')
-def pasteFileToFolder(filepath, number, 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)$', filepath).group())
+        img = Image.open(path + '/fanart.jpg')
+        w = img.width
+        h = img.height
+        img.save(path + '/poster.png')
+def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
+    global houzhui
+    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
     os.rename(filepath, number + houzhui)
     shutil.move(number + houzhui, path)
+def renameJpgToBackdrop_copy():
+    shutil.copy(path + '/fanart.jpg', path + '/Backdrop.jpg')
+    shutil.copy(path + '/poster.png', path + '/thumb.png')
 
 if __name__ == '__main__':
-    filepath=argparse_get_file() #影片的路径
-    number=getNumberFromFilename(filepath) #定义番号
-    htmlcode=get_html_javbus(number) #获取的HTML代码
-    creatFolder(htmlcode,number) #创建文件夹
-    imageDownload(htmlcode,filepath,number) #creatFoder会返回番号路径
-    PrintFiles(htmlcode, path,number)#打印文件
-    cutImage(number) #裁剪图
-    pasteFileToFolder(filepath,number,path) #移动文件
+    filepath=argparse_get_file()[0] #影片的路径
+
+    if '-c.' in filepath or '-C.' in filepath or '中文' in filepath or '字幕' in filepath:
+        cn_sub='1'
+
+    if argparse_get_file()[1] == '':    #获取手动拉去影片获取的番号
+        try:
+            number = str(re.findall(r'(.+?)\.',str(re.search('([^<>/\\\\|:""\\*\\?]+)\\.\\w+$',filepath).group()))).strip("['']").replace('_','-')
+            print("[!]Making Data for   [" + number + "]")
+        except:
+            print("[-]failed!Please rename the filename again!")
+            moveFailedFolder()
+    else:
+        number = argparse_get_file()[1]
+    CreatFailedFolder()
+    getDataFromJSON(number)  # 定义番号
+    creatFolder()  # 创建文件夹
+    imageDownload(filepath)  # creatFoder会返回番号路径
+    PrintFiles(filepath)  # 打印文件
+    cutImage()  # 裁剪图
+    pasteFileToFolder(filepath, path)  # 移动文件
+    renameJpgToBackdrop_copy()

fc2fans_club.py

@@ -0,0 +1,84 @@
+import re
+from lxml import etree#need install
+import json
+import ADC_function
+
+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(" ['']")
+    result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
+    #print(result2)
+    return result2
+def getActor(htmlcode):
+    try:
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
+        return result
+    except:
+        return ''
+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(" ['']")
+    return result
+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(htmlcode2): #
+    #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')
+    html=etree.fromstring(htmlcode2,etree.HTMLParser())
+    result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
+    return result
+def getCover(htmlcode,number,htmlcode2): #获取厂商 #
+    #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')
+    html = etree.fromstring(htmlcode2, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
+    if result == '':
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
+        return 'http://fc2fans.club' +  result2
+    return 'http:' + result
+def getOutline(htmlcode2,number):     #获取番号 #
+    #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')
+    html = etree.fromstring(htmlcode2, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
+    return result
+def getTag(htmlcode):     #获取番号
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
+    return result.strip(" ['']").replace("'",'').replace(' ','')
+def getYear(release):
+    try:
+        result = re.search('\d{4}',release).group()
+        return result
+    except:
+        return ''
+
+def main(number2):
+    number=number2.replace('PPV','').replace('ppv','')
+    htmlcode2 = 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')
+    htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
+    dic = {
+        'title':    getTitle(htmlcode),
+        'studio':   getStudio(htmlcode),
+        'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
+        'outline':  getOutline(htmlcode,number),
+        'runtime':  getYear(getRelease(htmlcode)),
+        'director': getStudio(htmlcode),
+        'actor':    getActor(htmlcode),
+        'release':  getRelease(number),
+        'number':  'FC2-'+number,
+        'cover':    getCover(htmlcode,number,htmlcode2),
+        'imagecut': 0,
+        'tag':      getTag(htmlcode),
+        'actor_photo':'',
+        'website':  'http://fc2fans.club/html/FC2-' + number + '.html',
+    }
+    #print(getTitle(htmlcode))
+    #print(getNum(htmlcode))
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
+    return js
+
+#print(main('1051725'))

javbus.py

@@ -0,0 +1,176 @@
+import re
+import requests #need install
+from pyquery import PyQuery as pq#need install
+from lxml import etree#need install
+import os
+import os.path
+import shutil
+from bs4 import BeautifulSoup#need install
+from PIL import Image#need install
+import time
+import json
+from ADC_function import *
+import javdb
+import siro
+
+def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    a = soup.find_all(attrs={'class': 'star-name'})
+    d={}
+    for i in a:
+        l=i.a['href']
+        t=i.get_text()
+        html = etree.fromstring(get_html(l), etree.HTMLParser())
+        p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
+        p2={t:p}
+        d.update(p2)
+    return d
+def getTitle(htmlcode):  #获取标题
+    doc = pq(htmlcode)
+    title=str(doc('div.container h3').text()).replace(' ','-')
+    try:
+        title2 = re.sub('n\d+-','',title)
+        return title2
+    except:
+        return title
+def getStudio(htmlcode): #获取厂商
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
+    return result
+def getYear(htmlcode):   #获取年份
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
+    return result
+def getCover(htmlcode):  #获取封面链接
+    doc = pq(htmlcode)
+    image = doc('a.bigImage')
+    return 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(" ['']")
+    return result
+def getRuntime(htmlcode): #获取分钟
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    a = soup.find(text=re.compile('分鐘'))
+    return a
+def getActor(htmlcode):   #获取女优
+    b=[]
+    soup=BeautifulSoup(htmlcode,'lxml')
+    a=soup.find_all(attrs={'class':'star-name'})
+    for i in a:
+        b.append(i.get_text())
+    return b
+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(" ['']")
+    return result
+def getDirector(htmlcode): #获取导演
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
+    return result
+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')
+    a = soup.find_all(attrs={'class': 'genre'})
+    for i in a:
+        if 'onmouseout' in str(i):
+            continue
+        tag.append(i.get_text())
+    return tag
+
+
+def main(number):
+    try:
+        if re.search('\d+\D+', number).group() in number or 'siro' in number or 'SIRO' in number or 'Siro' in number:
+            js = siro.main(number)
+            return js
+    except:
+        aaaa=''
+
+    try:
+        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),
+            'actor_photo': getActorPhoto(htmlcode),
+            'website': 'https://www.javbus.com/' + number,
+        }
+        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': '',
+                '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),
+                'actor_photo': getActorPhoto(htmlcode),
+                'website': 'https://www.javbus.com/' + number,
+            }
+            js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
+                             separators=(',', ':'), )  # .encode('UTF-8')
+            return js2
+        return js
+    except:
+        a=javdb.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("-", ''))
+    if getTitle(htmlcode) == '':
+        htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
+        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+    dic = {
+        'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(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),
+        'tag': getTag(htmlcode),
+        'label': getSerise(htmlcode),
+        'imagecut': 0,
+        'actor_photo': '',
+        'website': 'https://www.javbus.com/' + number,
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+
+    if getYear(htmlcode) == '' or getYear(htmlcode) == 'null':
+        js2 = javdb.main(number)
+        return js2
+
+    return js

javdb.py

@@ -0,0 +1,140 @@
+import re
+from lxml import etree
+import json
+import requests
+from bs4 import BeautifulSoup
+from ADC_function import *
+
+def getTitle(a):
+    try:
+        html = etree.fromstring(a, etree.HTMLParser())
+        result = str(html.xpath('/html/body/section/div/h2/strong/text()')).strip(" ['']")
+        return re.sub('.*\] ','',result.replace('/', ',').replace('\\xa0','').replace(' : ',''))
+    except:
+        return re.sub('.*\] ','',result.replace('/', ',').replace('\\xa0',''))
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace(",\\xa0","").replace("'","").replace(' ','').replace(',,','').lstrip(',').replace(',',', ')
+def getStudio(a):
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"製作")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"製作")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1+result2).strip('+').replace("', '",'').replace('"','')
+def getRuntime(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').rstrip('mi')
+def getLabel(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+def getNum(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+')
+def getYear(getRelease):
+    try:
+        result = str(re.search('\d{4}',getRelease).group())
+        return result
+    except:
+        return getRelease
+def getRelease(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+')
+def getTag(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace(",\\xa0","").replace("'","").replace(' ','').replace(',,','').lstrip(',')
+def getCover(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']")
+    if result == '':
+        result = str(html.xpath('/html/body/section/div/div[3]/div[1]/a/img/@src')).strip(" ['']")
+    return result
+def getDirector(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+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):
+    try:
+        a = get_html('https://javdb.com/search?q=' + number + '&f=all')
+        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+        if result1 == '':
+            a = get_html('https://javdb.com/search?q=' + number.replace('-', '_') + '&f=all')
+            html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+            result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+        b = get_html('https://javdb1.com' + result1)
+        soup = BeautifulSoup(b, 'lxml')
+
+        a = str(soup.find(attrs={'class': 'panel'}))
+        dic = {
+            'actor': getActor(a),
+            'title': getTitle(b).replace("\\n", '').replace('        ', '').replace(getActor(a), '').replace(getNum(a),
+                                                                                                             '').replace(
+                '无码', '').replace('有码', '').lstrip(' '),
+            'studio': getStudio(a),
+            'outline': getOutline(a),
+            'runtime': getRuntime(a),
+            'director': getDirector(a),
+            'release': getRelease(a),
+            'number': getNum(a),
+            'cover': getCover(b),
+            'imagecut': 0,
+            'tag': getTag(a),
+            'label': getLabel(a),
+            'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+            'actor_photo': '',
+            'website': 'https://javdb1.com' + result1,
+        }
+        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        return js
+    except:
+        a = get_html('https://javdb.com/search?q=' + number + '&f=all')
+        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+        if result1 == '':
+            a = get_html('https://javdb.com/search?q=' + number.replace('-', '_') + '&f=all')
+            html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+            result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+
+        b = get_html('https://javdb.com' + result1)
+        soup = BeautifulSoup(b, 'lxml')
+
+        a = str(soup.find(attrs={'class': 'panel'}))
+        dic = {
+            'actor': getActor(a),
+            'title': getTitle(b).replace("\\n", '').replace('        ', '').replace(getActor(a), '').replace(getNum(a),
+                                                                                                             '').replace(
+                '无码', '').replace('有码', '').lstrip(' '),
+            'studio': getStudio(a),
+            'outline': getOutline(a),
+            'runtime': getRuntime(a),
+            'director': getDirector(a),
+            'release': getRelease(a),
+            'number': getNum(a),
+            'cover': getCover(b),
+            'imagecut': 0,
+            'tag': getTag(a),
+            'label': getLabel(a),
+            'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+            'actor_photo': '',
+            'website':'https://javdb.com' + result1,
+        }
+        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        return js
+
+#print(main('061519-861'))

siro.py

@@ -0,0 +1,104 @@
+import re
+from lxml import etree
+import json
+import requests
+from bs4 import BeautifulSoup
+from ADC_function import *
+
+def getTitle(a):
+    try:
+        html = etree.fromstring(a, etree.HTMLParser())
+        result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
+        return result.replace('/', ',')
+    except:
+        return ''
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+    result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
+def getStudio(a):
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+    result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    return str(result1+result2).strip('+').replace("', '",'').replace('"','')
+def getRuntime(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    return str(result1 + result2).strip('+').rstrip('mi')
+def getLabel(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+def getNum(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    return str(result1 + result2).strip('+')
+def getYear(getRelease):
+    try:
+        result = str(re.search('\d{4}',getRelease).group())
+        return result
+    except:
+        return getRelease
+def getRelease(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    return str(result1 + result2).strip('+')
+def getTag(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','')
+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())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+        '\\n')
+    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+def getOutline(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
+    return result
+def main(number2):
+    number=number2.upper()
+    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                                        ','').replace('                                ','').replace('\n                            ','').replace('\n                        ','')
+    dic = {
+        'title': getTitle(htmlcode).replace("\\n",'').replace('        ',''),
+        'studio': getStudio(a),
+        'outline': getOutline(htmlcode),
+        'runtime': getRuntime(a),
+        'director': getDirector(a),
+        'actor': getActor(a),
+        'release': getRelease(a),
+        'number': getNum(a),
+        'cover': getCover(htmlcode),
+        'imagecut': 0,
+        'tag': getTag(a),
+        'label':getLabel(a),
+        'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+        'actor_photo': '',
+        'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
+    return js
+
+#print(main('300maan-373'))

update_check.json

@@ -0,0 +1,5 @@
+{
+	"version": "0.11.5",
+	"version_show":"Beta 11.5",
+	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
+}