Update update_check.json

ADC_function.py

@@ -1,8 +1,15 @@
 import requests
-from configparser import ConfigParser
+from configparser import RawConfigParser
 import os
+import re
 
-config = ConfigParser()
+# content = open('proxy.ini').read()
+# content = re.sub(r"\xfe\xff","", content)
+# content = re.sub(r"\xff\xfe","", content)
+# content = re.sub(r"\xef\xbb\xbf","", content)
+# open('BaseConfig.cfg', 'w').write(content)
+
+config = RawConfigParser()
 if os.path.exists('proxy.ini'):
     config.read('proxy.ini', encoding='UTF-8')
 else:
@@ -10,14 +17,14 @@ else:
         print("[proxy]",file=code)
         print("proxy=127.0.0.1:1080",file=code)
 
-def get_html(url):#网页请求核心
+def get_html(url,cookies = None):#网页请求核心
     if not str(config['proxy']['proxy']) == '':
         proxies = {
             "http" : "http://"  + str(config['proxy']['proxy']),
             "https": "https://" + str(config['proxy']['proxy'])
         }
         headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
-        getweb = requests.get(str(url), headers=headers, proxies=proxies)
+        getweb = requests.get(str(url), headers=headers, proxies=proxies,cookies=cookies)
         getweb.encoding = 'utf-8'
         # print(getweb.text)
         try:
@@ -27,7 +34,7 @@ def get_html(url):#网页请求核心
     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)
+        getweb = requests.get(str(url),  headers=headers,cookies=cookies)
         getweb.encoding = 'utf-8'
         try:
             return getweb.text

AV_Data_Capture.py

@@ -3,6 +3,20 @@ import os
 import time
 import re
 import sys
+from ADC_function import *
+import json
+
+version='0.10.6'
+
+def UpdateCheck():
+    html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')
+    html = json.loads(str(html2))
+
+    if not version == html['version']:
+        print('[*]        * New update '+html['version']+' *')
+        print('[*]             * Download *')
+        print('[*] '+html['download'])
+        print('[*]=====================================')
 
 def movie_lists():
     #MP4
@@ -19,8 +33,10 @@ def movie_lists():
     f2 = glob.glob(os.getcwd() + r"\*.mkv")
     # FLV
     g2 = glob.glob(os.getcwd() + r"\*.flv")
+    # TS
+    h2 = glob.glob(os.getcwd() + r"\*.ts")
 
-    total = a2+b2+c2+d2+e2+f2+g2
+    total = a2+b2+c2+d2+e2+f2+g2+h2
     return total
 
 def lists_from_test(custom_nuber): #电影列表
@@ -46,13 +62,17 @@ def rreplace(self, old, new, *max):
     return new.join(self.rsplit(old, count))
 
 if __name__ =='__main__':
+    print('[*]===========AV Data Capture===========')
+    print('[*]           Version '+version)
+    print('[*]=====================================')
+    UpdateCheck()
     os.chdir(os.getcwd())
     for i in movie_lists(): #遍历电影列表 交给core处理
         if '_' in i:
             os.rename(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1))
             i = rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1)
-        #os.system('python core.py' + ' "' + i + '"') #选择从py文件启动  （用于源码py）
+        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）
+        #os.system('core.exe' + ' "' + i + '"')      #选择从exe文件启动（用于EXE版程序）
         print("[*]=====================================")
 
     print("[!]Cleaning empty folders")

README.md

@@ -1,29 +1,79 @@
-<h1 style="text-align:center">日本AV元数据抓取工具</h1>
+# AV Data Capture 日本AV元数据刮削器
-
-## 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。
+<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/wenead99/av_data_capture/total.svg?style=flat-square)<br>
+![](https://img.shields.io/github/languages/code-size/wenead99/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/issues/wenead99/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/license/wenead99/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/release/wenead99/av_data_capture.svg?style=flat-square)<br>
+![](https://img.shields.io/github/forks/wenead99/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/stars/wenead99/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/watchers/wenead99/av_data_capture.svg?style=flat-square)
 
-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 
 
-**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)
+# 目录
+* [前言](#前言)
+* [注意事项](#注意事项)
+* [捐助二维码](#捐助二维码)
+* [效果图](#效果图)
+* [免责声明](#免责声明)
+* [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proxyini)
+* [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EMBY](#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)
+* [输出文件示例](#8输出的文件如下)
+* [写在后面](#9写在后面)
+* [软件流程图](#10软件流程图)
+* []()
+# 前言
+&emsp;&emsp;目前，我下的AV越来越多，也意味着AV要**集中地管理**，形成本地媒体库。现在有两款主流的AV元数据获取器，"EverAver"和"Javhelper"。前者的优点是元数据获取比较全，缺点是不能批量处理；后者优点是可以批量处理，但是元数据不够全。<br>
+&emsp;&emsp;为此，综合上述软件特点，我写出了本软件，为了方便的管理本地AV，和更好的手冲体验。<br>
+&emsp;&emsp;希望大家可以认真耐心地看完本文档，你的耐心换来的是完美的管理方式。<br>
+&emsp;&emsp;本软件更新可能比较**频繁**，麻烦诸位用户**积极更新新版本**以获得**最佳体验**。
+- - -
+**可以结合pockies大神的[ 打造本地AV（毛片）媒体库 ](https://pockies.github.io/2019/03/25/everaver-emby-kodi/)看本文档**<br>
+**tg官方电报群:[ 点击进群](https://t.me/AV_Data_Capture_Official)**<br>
+**推荐用法: 使用该软件后，对于不能正常获取元数据的电影可以用[ Everaver ](http://everaver.blogspot.com/)来补救**<br>
+暂不支持多P电影<br>
+[回到目录](#目录)
 
+# 注意事项
+**如果在中国大陆网站，请低调传播本软件或者不传播该软件**<br>
+
+# 效果图
+**由于法律因素，图片必须经马赛克处理**<br>
 ![](https://i.loli.net/2019/06/02/5cf2b5d0bbecf69019.png)
+![](https://i.loli.net/2019/06/22/5d0d10dd6255e44008.png)<br>
+[回到目录](#目录)
 
+# 捐助二维码
+如果你觉得本软件好用，可以考虑捐助作者，多少钱无所谓，不强求，你的支持就是我的动力，非常感谢您的捐助
+![](https://i.loli.net/2019/06/21/5d0cb02ca489d19393.png)<br>
+[回到目录](#目录)
 
-## 软件流程图
+# 免责声明
-![](https://i.loli.net/2019/06/02/5cf2bb9a9e2d997635.png)
+1.本软件仅供技术交流，学术交流使用<br>
+2.本软件不提供任何有关淫秽色情的影视下载方式<br>
+3.使用者使用该软件产生的一切法律后果由使用者承担<br>
+4.该软件禁止任何商用行为<br>
+[回到目录](#目录)
 
 # 如何使用
----------------
+### 下载
-release的程序可脱离python环境运行，可跳过第一步
+* 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>下载地址(**仅限Windows**):https://github.com/wenead99/AV_Data_Capture/releases
+* Linux,MacOS请下载源码包运行
+### 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>
+[回到目录](#目录)
 
-下载地址(Windows):https://github.com/wenead99/AV_Data_Capture/releases
+## 1.请安装模块,在CMD/终端逐条输入以下命令安装
-
-## 1. 请安装requests,pyquery,lxml,Beautifulsoup4,pillow模块,在 CMD/终端 逐条输入以下命令安装
 ```python
 pip install requests
 ```
@@ -43,46 +93,80 @@ pip install Beautifulsoup4
 ```python
 pip install pillow
 ```
-
+###
-## 2. 设置本地代理
-**针对网络审查国家或地区**
-
-打开```proxy.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowsocks/R,V2RAY本地代理端口:
-```proxy=127.0.0.1:1080```
 
 
-## 3. 关于番号提取失败或者异常
+[回到目录](#目录)
->下一张图片来自Pockies的blog:https://pockies.github.io/2019/03/25/everaver-emby-kodi/ 原作者已授权
+
+## 2.配置proxy.ini
+#### 1.针对网络审查国家或地区的代理设置
+打开```proxy.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowsocks/R,V2RAY本地代理端口:<br>
+例子:```proxy=127.0.0.1:1080```<br>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>
+**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>
+[回到目录](#目录)
+
+#### 2.（可选）设置自定义目录和影片重命名规则
+**已有默认配置**<br>
+##### 命名参数<br>
+>title = 片名<br>
+>actor = 演员<br>
+>studio = 公司<br>
+>director = 导演<br>
+>release = 发售日<br>
+>year = 发行年份<br>
+>number = 番号<br>
+>cover = 封面链接<br>
+>tag = 类型<br>
+>outline = 简介<br>
+>runtime = 时长<br>
+##### **例子**:<br>
+>目录结构规则: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**
+[回到目录](#目录)
+## 3.把软件拷贝和AV的统一目录下
+## 4.运行 ```AV_Data_capture.py/.exe```
+你也可以把单个影片拖动到core程序<br>
+![](https://i.loli.net/2019/06/02/5cf2b5d03640e73201.gif)<br>
+[回到目录](#目录)
+## 5.异常处理（重要）
+### 关于连接拒绝的错误
+请设置好[代理](#1针对网络审查国家或地区的代理设置)<br>
+### 关于Nonetype,xpath报错
+同上<br>
+[回到目录](#目录)
+### 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:https://pockies.github.io/2019/03/25/everaver-emby-kodi/ 原作者已授权<br>
 
 ![](https://raw.githubusercontent.com/Pockies/pic/master/741f9461gy1g1cxc31t41j20i804zdgo.jpg)
 
-
+目前作者已经完善了番号提取机制，功能较为强大，可提取上述文件名的的番号，如果出现提取失败或者异常的情况，请用以下规则命名<br>
-**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**
+**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
 ```
 
->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
+文件名中间要有下划线或者减号"_","-"，没有多余的内容只有番号为最佳，可以让软件更好获取元数据
->对于多影片重命名，可以用ReNamer来批量重命名
+对于多影片重命名，可以用[ReNamer](http://www.den4b.com/products/renamer)来批量重命名<br>
->软件官网:http://www.den4b.com/products/renamer
+[回到目录](#目录)
 
 
-## 4. 把软件拷贝和AV的统一目录下
-
-## 5. 运行 ```AV_Data_capture.py/.exe```
->**你也可以把单个影片拖动到core程序**
-
-![](https://i.loli.net/2019/06/02/5cf2b5d03640e73201.gif)
-
 ## 6.软件会自动把元数据获取成功的电影移动到JAV_output文件夹中，根据女优分类，失败的电影移动到failed文件夹中。
-
 ## 7.把JAV_output文件夹导入到EMBY,KODI中，根据封面选片子，享受手冲乐趣
-
+cookies大神的EMBY教程:[链接](https://pockies.github.io/2019/03/25/everaver-emby-kodi/#%E5%AE%89%E8%A3%85emby%E5%B9%B6%E6%B7%BB%E5%8A%A0%E5%AA%92%E4%BD%93%E5%BA%93)<br>
+[回到目录](#目录)
 ## 8.输出的文件如下
 ![](https://i.loli.net/2019/06/02/5cf2b5cfd1b0226763.png)
 ![](https://i.loli.net/2019/06/02/5cf2b5cfd1b0246492.png)
-![](https://i.loli.net/2019/06/02/5cf2b5d009e4930666.png)
+![](https://i.loli.net/2019/06/02/5cf2b5d009e4930666.png)<br>
+[回到目录](#目录)
+## 9.写在后面
+怎么样，看着自己的AV被这样完美地管理，是不是感觉成就感爆棚呢?<br>
+[回到目录](#目录)
+## 10.软件流程图
+![](https://i.loli.net/2019/06/02/5cf2bb9a9e2d997635.png)<br>
+[回到目录](#目录)
 
 
 

core.py

@@ -55,6 +55,7 @@ def getNumberFromFilename(filepath):
     global cover
     global imagecut
     global tag
+    global image_main
 
     global naming_rule
     global location_rule
@@ -76,8 +77,8 @@ def getNumberFromFilename(filepath):
                 filename0 = str(re.sub(".*?\.com-\d+", "", filename1))
                 file_number2 = str(re.match('\w+', filename0).group())
                 file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),re.match("^[A-Za-z]+", file_number2).group() + '-'))
-                if not re.search('\w-', file_number).group() == 'None':
+                #if not re.search('\w-', file_number).group() == 'None':
-                    file_number = re.search('\w+-\w+', filename).group()
+                    #file_number = re.search('\w+-\w+', filename).group()
                 #上面是插入减号-到番号中
         print("[!]Making Data for   [" + filename + "],the number is [" + file_number + "]")
     # ====番号获取主程序=结束===
@@ -107,32 +108,10 @@ def getNumberFromFilename(filepath):
         except: #添加 无需 正则表达式的规则
             # ====================fc2fans_club.py===================
             if 'fc2' in filename:
-                json_data = json.loads(fc2fans_club.main(file_number))
+                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 filename:
-                json_data = json.loads(fc2fans_club.main(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-')))
-
+                #print(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-'))
-            #========================siro.py========================
-            elif 'siro' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif 'SIRO' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '259luxu' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '259LUXU' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '300MAAN' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '300maan' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '326SCP' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '326scp' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '326URF' in filename:
-                json_data = json.loads(siro.main(file_number))
-            elif '326urf' in filename:
-                json_data = json.loads(siro.main(file_number))
-
             #=======================javbus.py=======================
             else:
                 json_data = json.loads(javbus.main(file_number))
@@ -158,6 +137,10 @@ def getNumberFromFilename(filepath):
         tag        = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')   #字符串转列表
         actor      = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
 
+        #====================处理异常字符====================== #\/:*?"<>|
+        #if "\\" in title or "/" in title or ":" in title or "*" in title or "?" in title or '"' in title or '<' in title or ">" in title or "|" in title or len(title) > 200:
+        #    title = title.
+
         naming_rule  = eval(config['Name_Rule']['naming_rule'])
         location_rule =eval(config['Name_Rule']['location_rule'])
     except IOError as e:
@@ -173,6 +156,7 @@ def getNumberFromFilename(filepath):
         os._exit(0)
 path = '' #设置path为全局变量，后面移动文件要用
 def creatFolder():
+    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
@@ -181,7 +165,13 @@ def creatFolder():
         path = location_rule
         #print(path)
     if not os.path.exists(path):
+        try:
             os.makedirs(path)
+        except:
+            path = location_rule.replace(actor,"'其他'")
+            os.makedirs(path)
+
+
 #=====================资源下载部分===========================
 def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
     config = ConfigParser()
@@ -226,13 +216,14 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
             print("[-]Download Failed2!")
             time.sleep(3)
             os._exit(0)
-def PrintFiles(path):
+def PrintFiles(path,naming_rule):
+    global title
     try:
         if not os.path.exists(path):
             os.makedirs(path)
-        with open(path + "/" + naming_rule + ".nfo", "wt", encoding='UTF-8') as code:
+        with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code:
             print("<movie>", file=code)
-            print(" <title>" + title + "</title>", file=code)
+            print(" <title>" + naming_rule + "</title>", file=code)
             print("  <set>", file=code)
             print("  </set>", file=code)
             print("  <studio>" + studio + "+</studio>", file=code)
@@ -269,7 +260,7 @@ def PrintFiles(path):
             print("  <cover>"+cover+"</cover>", file=code)
             print("  <website>" + "https://www.javbus.com/"+number + "</website>", file=code)
             print("</movie>", file=code)
-            print("[+]Writeed!          "+path + "/" + naming_rule + ".nfo")
+            print("[+]Writeed!          "+path + "/" + number + ".nfo")
     except IOError as e:
         print("[-]Write Failed!")
         print(e)
@@ -277,31 +268,31 @@ def PrintFiles(path):
         print(e1)
         print("[-]Write Failed!")
 def imageDownload(filepath): #封面是否下载成功，否则移动到failed
-    if DownloadFileWithFilename(cover,naming_rule+ '.jpg', path) == 'failed':
+    if DownloadFileWithFilename(cover,'Backdrop.jpg', path) == 'failed':
         shutil.move(filepath, 'failed/')
         os._exit(0)
-    DownloadFileWithFilename(cover, naming_rule + '.jpg', path)
+    DownloadFileWithFilename(cover, 'Backdrop.jpg', path)
-    print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg')
+    print('[+]Image Downloaded!', path +'/'+'Backdrop.jpg')
 def cutImage():
     if imagecut == 1:
         try:
-            img = Image.open(path + '/' + naming_rule + '.jpg')
+            img = Image.open(path + '/' + 'Backdrop' + '.jpg')
             imgSize = img.size
             w = img.width
             h = img.height
             img2 = img.crop((w / 1.9, 0, w, h))
-            img2.save(path + '/' + naming_rule + '.png')
+            img2.save(path + '/' + number + '.png')
         except:
             print('[-]Cover cut failed!')
     else:
-        img = Image.open(path + '/' + naming_rule + '.jpg')
+        img = Image.open(path + '/' + 'Backdrop' + '.jpg')
         w = img.width
         h = img.height
-        img.save(path + '/' + naming_rule + '.png')
+        img.save(path + '/' + number + '.png')
 def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
-    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$', filepath).group())
+    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
-    os.rename(filepath, naming_rule + houzhui)
+    os.rename(filepath, number + houzhui)
-    shutil.move(naming_rule + houzhui, path)
+    shutil.move(number + houzhui, path)
 
 if __name__ == '__main__':
     filepath=argparse_get_file() #影片的路径
@@ -309,6 +300,6 @@ if __name__ == '__main__':
     getNumberFromFilename(filepath) #定义番号
     creatFolder() #创建文件夹
     imageDownload(filepath) #creatFoder会返回番号路径
-    PrintFiles(path)#打印文件
+    PrintFiles(path,naming_rule)#打印文件
     cutImage() #裁剪图
     pasteFileToFolder(filepath,path) #移动文件

fc2fans_club.py

@@ -7,7 +7,17 @@ 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(" ['']")
@@ -15,46 +25,60 @@ def getStudio(htmlcode): #获取厂商
 def getNum(htmlcode):     #获取番号
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
+    #print(result)
     return result
-def getRelease(number):
+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')
+    #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(a,etree.HTMLParser())
+    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): #获取厂商
+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')
+    #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(a, etree.HTMLParser())
+    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(htmlcode,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')
+def getOutline(htmlcode2,number):     #获取番号 #
-    html = etree.fromstring(a, etree.HTMLParser())
+    #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,number):     #获取番号
+def getTag(htmlcode):     #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(htmlcode, etree.HTMLParser())
-#     html = etree.fromstring(a, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
-#     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
+    return result.strip(" ['']").replace("'",'').replace(' ','')
-#     return result
+def getYear(release):
+    try:
+        result = re.search('\d{4}',release).group()
+        return result
+    except:
+        return ''
 
-def main(number):
+def main(number2):
-    str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")
+    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()),
+        'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
         'outline': getOutline(htmlcode,number),
-        'runtime': '',
+        'runtime': getYear(getRelease(htmlcode)),
         'director': getStudio(htmlcode),
-        'actor': '',
+        'actor': getActor(htmlcode),
         'release': getRelease(number),
         'number': 'FC2-'+number,
-        'cover': getCover(htmlcode,number),
+        'cover': getCover(htmlcode,number,htmlcode2),
         'imagecut': 0,
-        'tag':" ",
+        'tag':getTag(htmlcode),
     }
+    #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('1104989'))
+#print(main('1051725'))

javbus.py

@@ -9,18 +9,16 @@ from bs4 import BeautifulSoup#need install
 from PIL import Image#need install
 import time
 import json
-
+from ADC_function import *
-def get_html(url):#网页请求核心
+import siro
-    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
-    getweb = requests.get(str(url),timeout=10,headers=headers).text
-    try:
-        return getweb
-    except:
-        print("[-]Connect Failed! Please check your Proxy.")
 
 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())
@@ -34,7 +32,6 @@ def getCover(htmlcode):  #获取封面链接
     doc = pq(htmlcode)
     image = doc('a.bigImage')
     return image.attr('href')
-    print(image.attr('href'))
 def getRelease(htmlcode): #获取出版日期
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
@@ -62,8 +59,10 @@ def getOutline(htmlcode):  #获取演员
     doc = pq(htmlcode)
     result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
     return result
-
+def getSerise(htmlcode):
-
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
+    return result
 def getTag(htmlcode):  # 获取演员
     tag = []
     soup = BeautifulSoup(htmlcode, 'lxml')
@@ -76,10 +75,11 @@ def getTag(htmlcode):  # 获取演员
 
 
 def main(number):
+    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':    getTitle(htmlcode),
+            'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
             'studio': getStudio(htmlcode),
             'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
             'outline': getOutline(dww_htmlcode),
@@ -90,7 +90,8 @@ def main(number):
             'number': getNum(htmlcode),
             'cover': getCover(htmlcode),
             'imagecut': 1,
-        'tag':      getTag(htmlcode)
+            'tag': getTag(htmlcode),
+            'label': getSerise(htmlcode),
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
 
@@ -98,7 +99,7 @@ def main(number):
             htmlcode = get_html('https://www.javbus.com/' + number)
             dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
             dic = {
-            'title': getTitle(htmlcode),
+                'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
                 'studio': getStudio(htmlcode),
                 'year': getYear(htmlcode),
                 'outline': getOutline(dww_htmlcode),
@@ -109,20 +110,25 @@ def main(number):
                 'number': getNum(htmlcode),
                 'cover': getCover(htmlcode),
                 'imagecut': 1,
-            'tag': getTag(htmlcode)
+                'tag': getTag(htmlcode),
+                'label': getSerise(htmlcode),
             }
-        js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+            js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
+                             separators=(',', ':'), )  # .encode('UTF-8')
             return js2
-
         return js
+    except:
+        a=siro.main(number)
+        return a
 
 def main_uncensored(number):
     htmlcode = get_html('https://www.javbus.com/' + number)
+    dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
     dic = {
-        'title': getTitle(htmlcode),
+        'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
         'studio': getStudio(htmlcode),
         'year': getYear(htmlcode),
-        'outline': getOutline(htmlcode),
+        'outline': getOutline(dww_htmlcode),
         'runtime': getRuntime(htmlcode),
         'director': getDirector(htmlcode),
         'actor': getActor(htmlcode),
@@ -130,6 +136,7 @@ def main_uncensored(number):
         'number': getNum(htmlcode),
         'cover': getCover(htmlcode),
         'tag': getTag(htmlcode),
+        'label': getSerise(htmlcode),
         'imagecut': 0,
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
@@ -138,7 +145,7 @@ def main_uncensored(number):
         number2 = number.replace('-', '_')
         htmlcode = get_html('https://www.javbus.com/' + number2)
         dic2 = {
-            'title': getTitle(htmlcode),
+            'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
             'studio': getStudio(htmlcode),
             'year': getYear(htmlcode),
             'outline': '',
@@ -149,6 +156,7 @@ def main_uncensored(number):
             'number': getNum(htmlcode),
             'cover': getCover(htmlcode),
             'tag': getTag(htmlcode),
+            'label':getSerise(htmlcode),
             'imagecut': 0,
         }
         js2 = json.dumps(dic2, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')

proxy.ini

@@ -2,15 +2,5 @@
 proxy=127.0.0.1:1080
 
 [Name_Rule]
-location_rule='JAV_output/'+actor+'/'+actor+'-'+year+'- '+title+'['+number+']'
+location_rule='JAV_output/'+actor+'/'+number
-naming_rule=actor+'-'+year+'- '+title+'['+number+']'
+naming_rule=number+'-'+title
-#============================================================
-#
-#   title=标题,number=番号，stdio=片商,year=年份,director=导演，actor=女优，outline=简介
-#   runtime=时长，release=上市日期，cover=封面URL，tag=类型
-#   例子:
-#   rule=str('JAV_output/'+actor+'/'+actor+' '+' ['+year+']'+title+' ['+number+']')
-#   例子结束
-#   自定义字符(字符串)要加冒号'(内容)'，字符串连接要用加号+
-#
-#============================================================

siro.py

@@ -3,79 +3,100 @@ from lxml import etree
 import json
 import requests
 from bs4 import BeautifulSoup
-
+from ADC_function import *
-def get_html(url):#网页请求核心
-    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
-    cookies = {'adc':'1'}
-    getweb = requests.get(str(url),timeout=10,cookies=cookies,headers=headers).text
-    try:
-        return getweb
-    except:
-        print("[-]Connect Failed! Please check your Proxy.")
 
 def getTitle(a):
+    try:
         html = etree.fromstring(a, etree.HTMLParser())
         result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
-    return result
+        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())
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[1]/td/a/text()')).strip(" ['\\n                                        ']")
+    result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    return result
+    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())
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[2]/td/a/text()')).strip(" ['\\n                                        ']")
+    result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    return result
+    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())
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[3]/td/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    return result
+    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())
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[4]/td/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return result
+        '\\n')
-def getYear(a):
+    result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
-    html = etree.fromstring(a, etree.HTMLParser())
+        '\\n')
-    #result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    return str(result1 + result2).strip('+')
-    result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+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())
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return result
+        '\\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())
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result=str(html.xpath('//table[2]/tr[9]/td/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return result
+        '\\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())
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result = str(html.xpath('//table[2]/tr[7]/td/a/text()')).strip(" ['\\n                                        ']")
+    result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return result
+        '\\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):
-def main(number):
+    number=number2.upper()
-    htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number))
+    htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'})
     soup = BeautifulSoup(htmlcode, 'lxml')
-    a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n                                        ','')
+    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),
-        'year': getYear(a),
         'outline': getOutline(htmlcode),
         'runtime': getRuntime(a),
         'director': getDirector(a),
         'actor': getActor(a),
         'release': getRelease(a),
-        'number': number,
+        'number': getNum(a),
         'cover': getCover(htmlcode),
         'imagecut': 0,
-        'tag':' ',
+        'tag': getTag(a),
+        'label':getLabel(a),
+        'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
     return js
+
+#print(main('200GANA-1581'))

update_check.json

@@ -0,0 +1,5 @@
+{
+	"version": "0.11.1",
+	"version_show":"Beta 11.1",
+	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
+}