Update update_check.json

Fix the path error under Linux and specify Python3 as the runtime.

ADC_function.py

@@ -1,3 +1,5 @@
+# -*- coding: utf-8 -*-
+
 import requests
 from configparser import ConfigParser
 import os
@@ -16,13 +18,18 @@ if os.path.exists(config_file):
 else:
     print('[+]config.ini: not found, creating...')
     with open("config.ini", "wt", encoding='UTF-8') as code:
+        print("[common]", file=code)
+        print("main_mode=1", file=code)
+        print("failed_output_folder=failed", file=code)
+        print("success_output_folder=JAV_output", file=code)
+        print("", file=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("location_rule=actor+'/'+number",file=code)
         print("naming_rule=number+'-'+title",file=code)
         print("", file=code)
         print("[update]",file=code)
@@ -34,10 +41,8 @@ else:
         print("#plex only test!", file=code)
         print("", file=code)
         print("[directory_capture]", file=code)
-        print("switch=0", file=code)
         print("directory=", file=code)
         print("", file=code)
-        print("everyone switch:1=on, 0=off", file=code)
     time.sleep(2)
     print('[+]config.ini: created!')
     try:

AV_Data_Capture.py

@@ -1,3 +1,6 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
 import glob
 import os
 import time
@@ -7,16 +10,22 @@ from ADC_function import *
 import json
 import shutil
 from configparser import ConfigParser
-
-version='0.11.6'
 os.chdir(os.getcwd())
 
+# ============global var===========
+
+version='1.1'
+
 config = ConfigParser()
 config.read(config_file, encoding='UTF-8')
 
+Platform = sys.platform
+
+# ==========global var end=========
+
 def UpdateCheck():
     if UpdateCheckSwitch() == '1':
-        html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
+        html2 = get_html('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/update_check.json')
         html = json.loads(str(html2))
 
         if not version == html['version']:
@@ -27,28 +36,36 @@ def UpdateCheck():
     else:
         print('[+]Update Check disabled!')
 def movie_lists():
-    if config['directory_capture']['switch'] == '0' or config['directory_capture']['switch'] == '':
-        a2 = glob.glob(r".\*.mp4")
-        b2 = glob.glob(r".\*.avi")
-        c2 = glob.glob(r".\*.rmvb")
-        d2 = glob.glob(r".\*.wmv")
-        e2 = glob.glob(r".\*.mov")
-        f2 = glob.glob(r".\*.mkv")
-        g2 = glob.glob(r".\*.flv")
-        h2 = glob.glob(r".\*.ts")
-        total = a2 + b2 + c2 + d2 + e2 + f2 + g2 + h2
-        return total
-    elif config['directory_capture']['switch'] == '1':
     directory = config['directory_capture']['directory']
-        a2 = glob.glob(r".\\" + directory + "\*.mp4")
+    mp4=[]
-        b2 = glob.glob(r".\\" + directory + "\*.avi")
+    avi=[]
-        c2 = glob.glob(r".\\" + directory + "\*.rmvb")
+    rmvb=[]
-        d2 = glob.glob(r".\\" + directory + "\*.wmv")
+    wmv=[]
-        e2 = glob.glob(r".\\" + directory + "\*.mov")
+    mov=[]
-        f2 = glob.glob(r".\\" + directory + "\*.mkv")
+    mkv=[]
-        g2 = glob.glob(r".\\" + directory + "\*.flv")
+    flv=[]
-        h2 = glob.glob(r".\\" + directory + "\*.ts")
+    ts=[]
-        total = a2 + b2 + c2 + d2 + e2 + f2 + g2 + h2
+    if directory=='*':
+        for i in os.listdir(os.getcwd()):
+            mp4 += glob.glob(r"./" + i + "/*.mp4")
+            avi += glob.glob(r"./" + i + "/*.avi")
+            rmvb += glob.glob(r"./" + i + "/*.rmvb")
+            wmv += glob.glob(r"./" + i + "/*.wmv")
+            mov += glob.glob(r"./" + i + "/*.mov")
+            mkv += glob.glob(r"./" + i + "/*.mkv")
+            flv += glob.glob(r"./" + i + "/*.flv")
+            ts += glob.glob(r"./" + i + "/*.ts")
+        total = mp4 + avi + rmvb + wmv + mov + mkv + flv + ts
+        return total
+    mp4 = glob.glob(r"./" + directory + "/*.mp4")
+    avi = glob.glob(r"./" + directory + "/*.avi")
+    rmvb = glob.glob(r"./" + directory + "/*.rmvb")
+    wmv = glob.glob(r"./" + directory + "/*.wmv")
+    mov = glob.glob(r"./" + directory + "/*.mov")
+    mkv = glob.glob(r"./" + directory + "/*.mkv")
+    flv = glob.glob(r"./" + directory + "/*.flv")
+    ts = glob.glob(r"./" + directory + "/*.ts")
+    total = mp4 + avi + rmvb + wmv + mov + mkv + flv + ts
     return total
 def CreatFailedFolder():
     if not os.path.exists('failed/'):  # 新建failed文件夹
@@ -76,54 +93,47 @@ def rreplace(self, old, new, *max):
         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
+        try:
             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:
+            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+-\w+', 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
+        try:
-                filename1 = str(re.sub("h26\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
+            filename1 = str(re.sub("ts6\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
             filename0 = str(re.sub(".*?\.com-\d+", "", filename1)).strip('_')
-                if '-C.' in filepath or '-c.' in filepath:
+            file_number = str(re.search('\w+\d{4}', filename0).group(0))
-                    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
+            filename1 = str(re.sub("ts6\d", "", filepath))  # 去除ts64/265
             filename0 = str(re.sub(".*?\.com-\d+", "", filename1))
             file_number2 = str(re.match('\w+', filename0).group())
-                if '-C.' in filepath or '-c.' in filepath:
+            file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),re.match("^[A-Za-z]+", file_number2).group() + '-'))
-                    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 Platform == 'win32':
         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）
+    else:
+        if os.path.exists('core.py'):
+            os.system('python3 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('python3 core.py' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从py文件启动（用于源码py）
 
 if __name__ =='__main__':
     print('[*]===========AV Data Capture===========')
@@ -135,13 +145,21 @@ if __name__ =='__main__':
 
     count = 0
     count_all = str(len(movie_lists()))
+    print('[+]Find',str(len(movie_lists())),'movies')
     for i in movie_lists(): #遍历电影列表 交给core处理
         count = count + 1
         percentage = str(count/int(count_all)*100)[:4]+'%'
         print('[!] - '+percentage+' ['+str(count)+'/'+count_all+'] -')
+        try:
             print("[!]Making Data for   [" + i + "], the number is [" + getNumber(i) + "]")
             RunCore()
             print("[*]=====================================")
+        except:  # 番号提取异常
+            print('[-]' + i + ' Cannot catch the number :')
+            print('[-]Move ' + i + ' to failed folder')
+            shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
+            continue
+
 
     CEF('JAV_output')
     print("[+]All finished!!!")

README.md

@@ -5,7 +5,8 @@
 ![](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/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/release/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/badge/Python-3.7-yellow.svg?style=flat-square&logo=python)<br>
 
 
 **日本电影元数据 抓取工具 | 刮削器**，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，供本地影片分类整理使用。
@@ -20,10 +21,13 @@
 * [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)
+* [(可选)设置自定义目录和影片重命名规则](#3可选设置自定义目录和影片重命名规则)
-* [异常处理（重要）](#5异常处理重要)
+* [运行软件](#5运行-av_data_capturepyexe)
-* [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)
+* [影片原路径处理](#4建议把软件拷贝和电影的统一目录下)
-* [写在后面](#8写在后面)
+* [异常处理（重要）](#51异常处理重要)
+* [导入至媒体库](#7把jav_output文件夹导入到embykodi中等待元数据刷新完成)
+* [关于群晖NAS](#8关于群晖NAS)
+* [写在后面](#9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 Python3<br>
@@ -52,7 +56,7 @@
 
 # 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/0.11.5/Beta11.5.zip)<br>
+* 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)<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
@@ -85,13 +89,18 @@ pip install pillow
 
 ## 2.配置config.ini
 config.ini
+>[common]<br>
+>main_mode=1<br>
+>failed_output_folder=failed<br>
+>success_output_folder=JAV_output<br>
+>
 >[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>
+>location_rule=actor+'/'+number<br>
 >naming_rule=number+'-'+title<br>
 >
 >[update]<br>
@@ -100,15 +109,25 @@ config.ini
 >[media]<br>
 >media_warehouse=emby<br>
 >#emby or plex<br>
->#plex only test!<br>
 >
 >[directory_capture]<br>
->switch=0<br>
 >directory=<br>
->
->#everyone switch:1=on, 0=off<br>
 
-### 1.网络设置
+### 全局设置
+---
+#### 软件模式
+>[common]<br>
+>main_mode=1<br>
+
+1为普通模式，2为整理模式：仅根据女优把电影命名为番号并分类到女优名称的文件夹下
+
+>failed_output_folder=failed<br>
+>success_output_folder=JAV_outputd<br>
+
+设置成功输出目录和失败输出目录
+
+---
+### 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>
@@ -120,32 +139,44 @@ config.ini
 >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
 
+---
 #### 检查更新开关
 >[update]<br>
 >update_check=1<br>
+
 0为关闭，1为开启，不建议关闭
 
+---
 ##### 媒体库选择 
 >[media]<br>
 >media_warehouse=emby<br>
 >#emby or plex<br>
->#plex only test!<br>
-建议选择emby, plex不完善
 
+可选择emby, plex<br>
+如果是PLEX，请安装插件：```XBMCnfoMoviesImporter```
+
+---
 #### 抓取目录选择
 >[directory_capture]<br>
->switch=0<br>
 >directory=<br>
-switch为1时，directory才会被触发，抓取程序目录下的directory目录下的电影；如果为0则不触发，抓取和程序同一目录下的影片，directory不生效
+如果directory后面为空，则抓取和程序同一目录下的影片，设置为``` * ```可抓取软件所在目录下的所有子目录中的影片
+## 3.(可选)设置自定义目录和影片重命名规则
+>[Name_Rule]<br>
+>location_rule=actor+'/'+number<br>
+>naming_rule=number+'-'+title<br>
 
-### (可选)设置自定义目录和影片重命名规则
+已有默认配置
-**已有默认配置**<br>
+
-##### 命名参数<br>
+---
+#### 命名参数
 >title = 片名<br>
 >actor = 演员<br>
 >studio = 公司<br>
@@ -157,28 +188,46 @@ switch为1时，directory才会被触发，抓取程序目录下的directory目
 >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>
+上面的参数以下都称之为**变量**
->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
+#### 例子：
+自定义规则方法：有两种元素，变量和字符，无论是任何一种元素之间连接必须要用加号 **+** ，比如：```'naming_rule=['+number+']-'+title```，其中冒号 ' ' 内的文字是字符，没有冒号包含的文字是变量，元素之间连接必须要用加号 **+** <br>
+目录结构规则：默认 ```location_rule=actor+'/'+number```<br> **不推荐修改时在这里添加title**，有时title过长，因为Windows API问题，抓取数据时新建文件夹容易出错。<br>
+影片命名规则：默认 ```naming_rule=number+'-'+title```<br> **在EMBY,KODI等本地媒体库显示的标题，不影响目录结构下影片文件的命名**，依旧是 番号+后缀。
+
+---
+### 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.建议把软件拷贝和电影的统一目录下
-## 4.运行 ```AV_Data_capture.py/.exe```
+如果```config.ini```中```directory=```后面为空的情况下
+## 5.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）
+## 5.1 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``` 和 ```JSON``` 相关的错误
-跳转 [网络设置](#1网络设置)
+跳转 [网络设置](#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，可能是你没有把软件拉到和电影的同一目录
+
+---
 ### 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>
+请设置好[代理](#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>
@@ -195,13 +244,17 @@ COSQ-004.mp4
 **野鸡番号**:比如 ```XXX-XXX-1```,  ```1301XX-MINA_YUKA``` 这种**野鸡**番号，在javbus等资料库存在的作品。<br>**重要**：除了 **影片文件名**  ```XXXX-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）
 
 
 ## 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
+## 8.关于群晖NAS
+开启SMB在Windows上挂载为网络磁盘即可使用本软件，也适用于其他NAS
+## 9.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>
 **tg官方电报群:[ 点击进群](https://t.me/AV_Data_Capture_Official)**<br>
 

avsox.py

@@ -0,0 +1,112 @@
+import re
+from lxml import etree
+import json
+from bs4 import BeautifulSoup
+from ADC_function import *
+
+def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    a = soup.find_all(attrs={'class': 'avatar-box'})
+    d = {}
+    for i in a:
+        l = i.img['src']
+        t = i.span.get_text()
+        p2 = {t: l}
+        d.update(p2)
+    return d
+def getTitle(a):
+    try:
+        html = etree.fromstring(a, etree.HTMLParser())
+        result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0]
+        return result.replace('/', '')
+    except:
+        return ''
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+    soup = BeautifulSoup(a, 'lxml')
+    a = soup.find_all(attrs={'class': 'avatar-box'})
+    d = []
+    for i in a:
+        d.append(i.span.get_text())
+    return d
+def getStudio(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ')
+    return result1
+def getRuntime(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']")
+    return result1
+def getLabel(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']")
+    return result1
+def getNum(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']")
+    return result1
+def getYear(release):
+    try:
+        result = str(re.search('\d{4}',release).group())
+        return result
+    except:
+        return release
+def getRelease(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']")
+    return result1
+def getCover(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']")
+    return result
+def getCover_small(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
+    return result
+def getTag(a):  # 获取演员
+    soup = BeautifulSoup(a, 'lxml')
+    a = soup.find_all(attrs={'class': 'genre'})
+    d = []
+    for i in a:
+        d.append(i.get_text())
+    return d
+
+def main(number):
+    a = get_html('https://avsox.asia/cn/search/' + number)
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
+    if result1 == '' or result1 == 'null' or result1 == 'None':
+        a = get_html('https://avsox.asia/cn/search/' + number.replace('-', '_'))
+        print(a)
+        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
+        if result1 == '' or result1 == 'null' or result1 == 'None':
+            a = get_html('https://avsox.asia/cn/search/' + number.replace('_', ''))
+            print(a)
+            html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+            result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
+    web = get_html(result1)
+    soup = BeautifulSoup(web, 'lxml')
+    info = str(soup.find(attrs={'class': 'row movie'}))
+    dic = {
+        'actor': getActor(web),
+        'title': getTitle(web).strip(getNum(web)),
+        'studio': getStudio(info),
+        'outline': '',#
+        'runtime': getRuntime(info),
+        'director': '', #
+        'release': getRelease(info),
+        'number': getNum(info),
+        'cover': getCover(web),
+        'cover_small': getCover_small(a),
+        'imagecut': 3,
+        'tag': getTag(web),
+        'label': getLabel(info),
+        'year': getYear(getRelease(info)),  # str(re.search('\d{4}',getRelease(a)).group()),
+        'actor_photo': getActorPhoto(web),
+        'website': result1,
+        'source': 'avsox.py',
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+    return js
+
+#print(main('041516_541'))

config.ini

@@ -1,12 +1,23 @@
+[common]
+main_mode=1
+failed_output_folder=failed
+success_output_folder=JAV_output
+
 [proxy]
 proxy=127.0.0.1:1080
 timeout=10
 retry=3
 
 [Name_Rule]
-location_rule='JAV_output/'+actor+'/'+number
+location_rule=actor+'/'+number
 naming_rule=number+'-'+title
 
 [update]
 update_check=1
-#on=1,off=0
+
+[media]
+media_warehouse=emby
+#emby or plex
+
+[directory_capture]
+directory=

core.py

@@ -1,17 +1,29 @@
+# -*- coding: utf-8 -*-
+
 import re
 import os
 import os.path
 import shutil
 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
+#=========website========
+import fc2fans_club
+import siro
+import avsox
+import javbus
 import javdb
+#=========website========
+
+Config = ConfigParser()
+Config.read(config_file, encoding='UTF-8')
+try:
+    option = ReadMediaWarehouse()
+except:
+    print('[-]Config media_warehouse read failed!')
 
 #初始化全局变量
 title=''
@@ -33,21 +45,17 @@ houzhui=''
 website=''
 json_data={}
 actor_photo={}
+cover_small=''
 naming_rule  =''#eval(config['Name_Rule']['naming_rule'])
 location_rule=''#eval(config['Name_Rule']['location_rule'])
-
+program_mode = Config['common']['main_mode']
-Config = ConfigParser()
+failed_folder= Config['common']['failed_output_folder']
-Config.read(config_file, encoding='UTF-8')
+success_folder=Config['common']['success_output_folder']
-try:
-    option = ReadMediaWarehouse()
-except:
-    print('[-]Config media_warehouse read failed!')
-
 #=====================本地文件处理===========================
 def moveFailedFolder():
     global filepath
-    print('[-]Move to "failed"')
+    print('[-]Move to Failed output folder')
-    shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+    shutil.move(filepath, str(os.getcwd()) + '/' + failed_folder + '/')
     os._exit(0)
 def argparse_get_file():
     parser = argparse.ArgumentParser()
@@ -56,12 +64,17 @@ def argparse_get_file():
     args = parser.parse_args()
     return (args.file, args.number)
 def CreatFailedFolder():
-    if not os.path.exists('failed/'):  # 新建failed文件夹
+    if not os.path.exists(failed_folder+'/'):  # 新建failed文件夹
         try:
-            os.makedirs('failed/')
+            os.makedirs(failed_folder+'/')
         except:
-            print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
+            print("[-]failed!can not be make Failed output folder\n[-](Please run as Administrator)")
             os._exit(0)
+def getDataState(json_data): #元数据获取失败检测
+    if json_data['title'] == '' or json_data['title'] == 'None' or json_data['title'] == 'null':
+        return 0
+    else:
+        return 1
 def getDataFromJSON(file_number): #从JSON返回元数据
     global title
     global studio
@@ -80,6 +93,7 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     global cn_sub
     global website
     global actor_photo
+    global cover_small
 
     global naming_rule
     global location_rule
@@ -88,20 +102,33 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     # ================================================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))
+            json_data = json.loads(avsox.main(file_number))
+            if getDataState(json_data) == 0:    #如果元数据获取失败，请求番号至其他网站抓取
+                json_data = json.loads(javdb.main(file_number))
+
+        elif re.search('\d+\D+', file_number).group() in file_number:
+            json_data = json.loads(siro.main(file_number))
+            if getDataState(json_data) == 0:    #如果元数据获取失败，请求番号至其他网站抓取
+                json_data = json.loads(javbus.main(file_number))
+            elif getDataState(json_data) == 0:  #如果元数据获取失败，请求番号至其他网站抓取
+                json_data = json.loads(javdb.main(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(
+            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-')))
-                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(
+            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-')))
-                file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-')))
+        elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
-        # =======================javbus.py=======================
+            json_data = json.loads(avsox.main(file_number))
+        elif 'siro' in file_number or 'SIRO' in file_number or 'Siro' in file_number:
+            json_data = json.loads(siro.main(file_number))
         else:
             json_data = json.loads(javbus.main(file_number))
+            if getDataState(json_data) == 0:    #如果元数据获取失败，请求番号至其他网站抓取
+                json_data = json.loads(avsox.main(file_number))
+            elif getDataState(json_data) == 0:  #如果元数据获取失败，请求番号至其他网站抓取
+                json_data = json.loads(javdb.main(file_number))
 
     # ================================================网站规则添加结束================================================
 
@@ -115,23 +142,32 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     release     =     json_data['release']
     number      =     json_data['number']
     cover       =     json_data['cover']
+    try:
+        cover_small = json_data['cover_small']
+    except:
+        aaaaaaa=''
     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']
+    source      =     json_data['source']
 
     if title == '' or number == '':
         print('[-]Movie Data not found!')
         moveFailedFolder()
 
+    if imagecut == '3':
+        DownloadFileWithFilename()
+
+
     # ====================处理异常字符====================== #\/:*?"<>|
     if '\\' in title:
         title=title.replace('\\', ' ')
-    elif '/' in title:
+    elif r'/' in title:
-        title=title.replace('/', '')
+        title=title.replace(r'/', '')
     elif ':' in title:
-        title=title.replace('/', '')
+        title=title.replace(':', '')
     elif '*' in title:
         title=title.replace('*', '')
     elif '?' in title:
@@ -148,20 +184,37 @@ def getDataFromJSON(file_number): #从JSON返回元数据
 
     naming_rule   = eval(config['Name_Rule']['naming_rule'])
     location_rule = eval(config['Name_Rule']['location_rule'])
+def smallCoverCheck():
+    if imagecut == 3:
+        if option == 'emby':
+            DownloadFileWithFilename(cover_small, '1.jpg', path)
+            img = Image.open(path + '/1.jpg')
+            w = img.width
+            h = img.height
+            img.save(path + '/' + number + '.png')
+            time.sleep(1)
+            os.remove(path + '/1.jpg')
+        if option == 'plex':
+            DownloadFileWithFilename(cover_small, '1.jpg', path)
+            img = Image.open(path + '/1.jpg')
+            w = img.width
+            h = img.height
+            img.save(path + '/poster.png')
+            os.remove(path + '/1.jpg')
 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
+        path = success_folder+'/'+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
+        path = success_folder+'/'+location_rule
         #print(path)
     if not os.path.exists(path):
         try:
             os.makedirs(path)
         except:
-            path = location_rule.replace('/['+number+']-'+title,"/number")
+            path = success_folder+'/'+location_rule.replace('/['+number+']-'+title,"/number")
             #print(path)
             os.makedirs(path)
 #=====================资源下载部分===========================
@@ -347,7 +400,7 @@ def cutImage():
                 img2.save(path + '/poster.png')
             except:
                 print('[-]Cover cut failed!')
-        else:
+        elif imagecut == 0:
             img = Image.open(path + '/fanart.jpg')
             w = img.width
             h = img.height
@@ -363,7 +416,7 @@ def cutImage():
                 img2.save(path + '/' + number + '.png')
             except:
                 print('[-]Cover cut failed!')
-        else:
+        elif imagecut == 0:
             img = Image.open(path + '/' + number + '.jpg')
             w = img.width
             h = img.height
@@ -372,13 +425,17 @@ def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移
     global houzhui
     houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
     try:
-        os.rename(filepath, number + houzhui)
+        os.rename(filepath, path + '/' + number + houzhui)
     except FileExistsError:
         print('[-]File Exists! Please check your movie!')
         print('[-]move to the root folder of the program.')
         os._exit(0)
+def pasteFileToFolder_mode2(filepath, path): #文件路径，番号，后缀，要移动至的位置
+    global houzhui
+    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
     try:
-        shutil.move(number + houzhui, path)
+        os.rename(filepath, path + houzhui)
+        print('[+]Movie ' + number + ' move to target folder Finished!')
     except:
         print('[-]File Exists! Please check your movie!')
         print('[-]move to the root folder of the program.')
@@ -387,6 +444,8 @@ def renameJpgToBackdrop_copy():
     if option == 'plex':
         shutil.copy(path + '/fanart.jpg', path + '/Backdrop.jpg')
         shutil.copy(path + '/poster.png', path + '/thumb.png')
+    if option == 'emby':
+        shutil.copy(path + '/' + number + '.jpg', path + '/Backdrop.jpg')
 
 if __name__ == '__main__':
     filepath=argparse_get_file()[0] #影片的路径
@@ -406,8 +465,12 @@ if __name__ == '__main__':
     CreatFailedFolder()
     getDataFromJSON(number)  # 定义番号
     creatFolder()  # 创建文件夹
+    if program_mode == '1':
         imageDownload(filepath)  # creatFoder会返回番号路径
         PrintFiles(filepath)  # 打印文件
+        smallCoverCheck()
         cutImage()  # 裁剪图
         pasteFileToFolder(filepath, path)  # 移动文件
         renameJpgToBackdrop_copy()
+    elif program_mode == '2':
+        pasteFileToFolder_mode2(filepath, path)  # 移动文件

fc2fans_club.py

@@ -75,6 +75,7 @@ def main(number2):
         'tag':      getTag(htmlcode),
         'actor_photo':'',
         'website':  'http://fc2fans.club/html/FC2-' + number + '.html',
+        'source': 'fc2fans_club.py',
     }
     #print(getTitle(htmlcode))
     #print(getNum(htmlcode))

javbus.py

@@ -1,17 +1,9 @@
 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')
@@ -88,16 +80,12 @@ def getTag(htmlcode):  # 获取演员
 
 
 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)
+        try:
             dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+        except:
+            dww_htmlcode = ''
         dic = {
             'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
             'studio': getStudio(htmlcode),
@@ -114,35 +102,12 @@ def main(number):
             'label': getSerise(htmlcode),
             'actor_photo': getActorPhoto(htmlcode),
             'website': 'https://www.javbus.com/' + number,
+            'source' : 'javbus.py',
         }
         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 main_uncensored(number)
-        return a
 
 def main_uncensored(number):
     htmlcode = get_html('https://www.javbus.com/' + number)
@@ -166,11 +131,7 @@ def main_uncensored(number):
         'imagecut': 0,
         'actor_photo': '',
         'website': 'https://www.javbus.com/' + number,
+        'source': 'javbus.py',
     }
     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

@@ -1,7 +1,6 @@
 import re
 from lxml import etree
 import json
-import requests
 from bs4 import BeautifulSoup
 from ADC_function import *
 
@@ -79,7 +78,6 @@ def main(number):
             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),
@@ -99,6 +97,7 @@ def main(number):
             'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
             'actor_photo': '',
             'website': 'https://javdb1.com' + result1,
+            'source': 'javdb.py',
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
         return js
@@ -106,18 +105,17 @@ def main(number):
         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 == '':
+        if result1 == '' or result1 == 'null':
             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),
+            'title': getTitle(b).replace("\\n", '').replace('        ', '').replace(getActor(a), '').replace(
+                getNum(a),
                 '').replace(
                 '无码', '').replace('有码', '').lstrip(' '),
             'studio': getStudio(a),
@@ -133,6 +131,7 @@ def main(number):
             'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
             'actor_photo': '',
             'website': 'https://javdb.com' + result1,
+            'source': 'javdb.py',
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), )  # .encode('UTF-8')
         return js

siro.py

@@ -1,7 +1,6 @@
 import re
 from lxml import etree
 import json
-import requests
 from bs4 import BeautifulSoup
 from ADC_function import *
 
@@ -97,6 +96,7 @@ def main(number2):
         'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
         'actor_photo': '',
         'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
+        'source': 'siro.py',
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
     return js

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "0.11.6",
+	"version": "1.1",
-	"version_show":"Beta 11.6",
+	"version_show":"Beta 1.1",
 	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
 }