Beta 10.1 修复FC2元数据提取异常

ADC_function.py

@@ -0,0 +1,35 @@
+import requests
+from configparser import ConfigParser
+import os
+
+config = ConfigParser()
+if os.path.exists('proxy.ini'):
+    config.read('proxy.ini', encoding='UTF-8')
+else:
+    with open("proxy.ini", "wt", encoding='UTF-8') as code:
+        print("[proxy]",file=code)
+        print("proxy=127.0.0.1:1080",file=code)
+
+def get_html(url):#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.encoding = 'utf-8'
+        # print(getweb.text)
+        try:
+            return getweb.text
+        except:
+            print('[-]Connected failed!:Proxy error')
+    else:
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+        getweb = requests.get(str(url),  headers=headers)
+        getweb.encoding = 'utf-8'
+        try:
+            return getweb.text
+        except:
+             print("[-]Connect Failed.")

AV_Data_Capture.py

@@ -1,6 +1,8 @@
 import glob
 import os
 import time
+import re
+import sys
 
 def movie_lists():
     #MP4
@@ -47,8 +49,8 @@ if __name__ =='__main__':
     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(i, rreplace(i,'_','-',1))
+            os.rename(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), rreplace(re.search(r'[^\\/:*?"<>|\r\n]+$', i).group(), '_', '-', 1))
-            i = rreplace(i,'_','-',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('core.exe' + ' "' + i + '"')      #选择从exe文件启动（用于EXE版程序）
         print("[*]=====================================")
@@ -56,5 +58,4 @@ if __name__ =='__main__':
     print("[!]Cleaning empty folders")
     CEF('JAV_output')
     print("[+]All finished!!!")
-    time.sleep(3)
+    input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看错误信息。")
-    

README.md

@@ -1,35 +1,24 @@
-# 日本AV元数据抓取工具  （刮削器）
+## 前言
+&emsp;&emsp;目前，我下的AV越来越多，也意味着AV要集中地管理，形成媒体库。现在有两款主流的AV元数据获取器，"EverAver"和"Javhelper"。前者的优点是元数据获取比较全，缺点是不能批量处理；后者优点是可以批量处理，但是元数据不够全。<br>
+&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。
 
-## 关于本软件 （~路star谢谢）
+**可以结合pockies大神的[ 打造本地AV（毛片）媒体库 ](https://pockies.github.io/2019/03/25/everaver-emby-kodi/)看本文档**<br>
+**tg官方电报群:[ 点击进群](https://t.me/AV_Data_Capture_Official)**<br>
+**推荐用法: 按照 [如何使用](#如何使用) 使用该软件后，对于不能正常获取元数据的电影可以用[ Everaver ](http://everaver.blogspot.com/)来补救**<br>
+![](https://i.loli.net/2019/06/02/5cf2b5d0bbecf69019.png)
 
-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。
+# 如何使用
+release的程序可脱离python环境运行，可跳过第一步<br>
+下载地址(Windows):https://github.com/wenead99/AV_Data_Capture/releases
 
-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 
+## 1.请安装模块,在CMD/终端逐条输入以下命令安装
-
-**预计本周末适配DS Video，暂时只支持Kodi**
-
-**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)
-
-
-## 软件流程图
-![](readme/flow_chart2.png)
-
-## 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
 ```python
 pip install requests
 ```
 ### 
 ```python
 pip install pyquery
-   ```
+```
 ###
 ```python
 pip install lxml
@@ -42,28 +31,61 @@ pip install Beautifulsoup4
 ```python
 pip install pillow
 ```
+###
+
+## 2. 设置proxy.ini
+#### 1.针对网络审查国家或地区
+
+打开```proxy.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowsocks/R,V2RAY本地代理端口:<br>
+例子:```proxy=127.0.0.1:1080```
+
+#### 2.设置自定义目录和影片重命名规则
+
+**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,326scp,326urf,259luxu,siro系列,FC2系列(不推荐)**<br>
+##### 命名参数<br>
+>title = 片名<br>
+>actor = 演员<br>
+>studio = 公司<br>
+>director = 导演<br>
+>release = 发售日<br>
+>year = 发行年份<br>
+>number = 番号<br>
+>cover = 封面链接<br>
+>tag = 类型<br>
+>outline = 简介<br>
+>runtime = 时长<br>
+##### **例子**:<br>
+>目录结构：'JAV_output/'+actor+'/'+actor+' '+' ['+year+']'+title+' ['+number+']'<br>
+>影片命名（上面目录之下的文件）:'['+number+']-'+title
+
+## 3. 关于番号提取失败或者异常
+>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
+
+![](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
 
-2. 你的AV在被软件管理前最好命名为番号:
 ```
 COSQ-004.mp4
 ```
-文件名中间要有减号"-"，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)
+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
 
-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. 把软件拷贝和AV的统一目录下
-4. 运行AV_Data_capture.py
+## 5. 运行 ```AV_Data_capture.py/.exe```
-5. **你也可以把单个影片拖动到core程序**
+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)
 
-![](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。
+## 7. 把JAV_output文件夹导入到EMBY,KODI中，根据封面选片子，享受手冲乐趣
+## 8.输出的文件如下
+![](https://i.loli.net/2019/06/02/5cf2b5cfd1b0226763.png)
+![](https://i.loli.net/2019/06/02/5cf2b5cfd1b0246492.png)
+![](https://i.loli.net/2019/06/02/5cf2b5d009e4930666.png)
 
-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。
+## 软件流程图
-
+![](https://i.loli.net/2019/06/02/5cf2bb9a9e2d997635.png)
-![](readme/readme2.PNG)
-![](readme/readme3.PNG)
-![](readme/readme4.PNG)
 
 
 

core.py

@@ -1,197 +1,314 @@
 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
-from PIL import Image#need install
 import time
+import javbus
+import json
+import fc2fans_club
+import siro
+from ADC_function import *
+from configparser import ConfigParser
 
-#=====================爬虫核心部分==========================
+#初始化全局变量
-def get_html(url):#网页请求核心
+title=''
-    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'}
+studio=''
-    getweb = requests.get(str(url),timeout=5,headers=headers).text
+year=''
-    try:
+outline=''
-        return getweb
+runtime=''
-    except:
+director=''
-        print("[-]Connect Failed! Please check your Proxy.")
+actor_list=[]
-
+actor=''
-def getTitle(htmlcode):  #获取标题
+release=''
-    doc = pq(htmlcode)
+number=''
-    title=str(doc('div.container h3').text()).replace(' ','-')
+cover=''
-    return title
+imagecut=''
-def getStudio(htmlcode): #获取厂商
+tag=[]
-    html = etree.fromstring(htmlcode,etree.HTMLParser())
+naming_rule  =''#eval(config['Name_Rule']['naming_rule'])
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
+location_rule=''#eval(config['Name_Rule']['location_rule'])
-    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
-#=====================资源下载部分===========================
-def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
-    import requests
-    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:
-            print("<movie>", file=code)
-            print(" <title>" + getTitle(html) + "</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("  <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)
-            print("</movie>", file=code)
-            print("[+]Writeed!    "+path + "/" + getNum(html) + ".nfo")
-    except IOError as e:
-        print("[-]Write Failed!")
-        print(e)
-    except Exception as e1:
-        print(e1)
-        print("[-]Write Failed!")
-
 #=====================本地文件处理===========================
-
-
 def argparse_get_file():
     import argparse
     parser = argparse.ArgumentParser()
     parser.add_argument("file", help="Write the file path on here")
     args = parser.parse_args()
     return args.file
-def getNumberFromFilename(filepath):
+def CreatFailedFolder():
-    filename = str(os.path.basename(filepath)) #电影文件名
+    if not os.path.exists('failed/'):  # 新建failed文件夹
-    str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filename))
+        try:
-
-    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/'):
+        except:
-                print("[-]failed!Dirs can not be make (Please run as Administrator)")
+            print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
-                time.sleep(3)
+            os._exit(0)
-                os._exit(0)
+def getNumberFromFilename(filepath):
+    global title
+    global studio
+    global year
+    global outline
+    global runtime
+    global director
+    global actor_list
+    global actor
+    global release
+    global number
+    global cover
+    global imagecut
+    global tag
+
+    global naming_rule
+    global location_rule
+
+#================================================获取文件番号================================================
+    try:    #试图提取番号
+    # ====番号获取主程序====
+        try:  # 普通提取番号 主要处理包含减号-的番号
+            filepath.strip('22-sht.me').strip('-HD').strip('-hd')
+            filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath))  # 去除文件名中文件名
+            file_number = re.search('\w+-\d+', filename).group()
+        except:  # 提取不含减号-的番号
+            try:  # 提取东京热番号格式 n1087
+                filename1 = str(re.sub("h26\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
+                filename0 = str(re.sub(".*?\.com-\d+", "", filename1)).strip('_')
+                file_number = str(re.search('n\d{4}', filename0).group(0))
+            except:  # 提取无减号番号
+                filename1 = str(re.sub("h26\d", "", filepath))  # 去除h264/265
+                filename0 = str(re.sub(".*?\.com-\d+", "", filename1))
+                file_number2 = str(re.match('\w+', filename0).group())
+                file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),re.match("^[A-Za-z]+", file_number2).group() + '-'))
+                if not re.search('\w-', file_number).group() == 'None':
+                    file_number = re.search('\w+-\w+', filename).group()
+                #上面是插入减号-到番号中
+        print("[!]Making Data for   [" + filename + "],the number is [" + file_number + "]")
+    # ====番号获取主程序=结束===
+    except Exception as e: #番号提取异常
+        print('[-]'+str(os.path.basename(filepath))+' Cannot catch the number :')
+        print('[-]' + str(os.path.basename(filepath)) + ' :', e)
+        print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+        os._exit(0)
+    except IOError as e2:
+        print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
+        print('[-]' + str(os.path.basename(filepath)) + ' :',e2)
+        print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+        os._exit(0)
+    try:
+
+
+
+
+# ================================================网站规则添加开始================================================
+
+        try:  #添加 需要 正则表达式的规则
+            #=======================javbus.py=======================
+            if re.search('^\d{5,}', file_number).group() in filename:
+                json_data = json.loads(javbus.main_uncensored(file_number))
+        except: #添加 无需 正则表达式的规则
+            # ====================fc2fans_club.py===================
+            if 'fc2' in filename:
+                json_data = json.loads(fc2fans_club.main(file_number.strip('fc2_').strip('fc2-')))
+            elif 'FC2' in filename:
+                json_data = json.loads(fc2fans_club.main(file_number.strip('FC2_').strip('FC2-')))
+
+            #========================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))
+
+
+
+#================================================网站规则添加结束================================================
+
+
+
+
+        title     = json_data['title']
+        studio    = json_data['studio']
+        year      = json_data['year']
+        outline   = json_data['outline']
+        runtime   = json_data['runtime']
+        director  = json_data['director']
+        actor_list= str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',') #字符串转列表
+        release   = json_data['release']
+        number    = json_data['number']
+        cover     = json_data['cover']
+        imagecut  = json_data['imagecut']
+        tag       = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')   #字符串转列表
+        actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
+
+        naming_rule  = eval(config['Name_Rule']['naming_rule'])
+        location_rule =eval(config['Name_Rule']['location_rule'])
+    except IOError as e:
+        print('[-]'+str(e))
+        print('[-]Move ' + filename + ' to failed folder')
+        shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
+        os._exit(0)
+
+    except Exception as e:
+        print('[-]'+str(e))
+        print('[-]Move ' + filename + ' to failed folder')
         shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
         os._exit(0)
-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):
+def creatFolder():
     global path
-    if not os.path.exists('failed/'): #新建failed文件夹
+    if len(actor) > 240:                    #新建成功输出文件夹
-        os.makedirs('failed/')
+        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
-        if not os.path.exists('failed/'):
+        #print(path)
-            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
     else:
-        path = 'JAV_output' + '/' + getActor(html) + '/' + number
+        path = location_rule
+        #print(path)
     if not os.path.exists(path):
         os.makedirs(path)
-    path = str(os.getcwd())+'/'+path
+#=====================资源下载部分===========================
-def imageDownload(htmlcode,filepath,number): #封面是否下载成功，否则移动到failed
+def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
-    if DownloadFileWithFilename(getCover(htmlcode),number + '.jpg', path) == 'failed':
+    config = ConfigParser()
+    config.read('proxy.ini', encoding='UTF-8')
+    proxy = str(config['proxy']['proxy'])
+    if not str(config['proxy']['proxy']) == '':
+        try:
+            if not os.path.exists(path):
+                os.makedirs(path)
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+            r = requests.get(url, headers=headers,proxies={"http": "http://" + str(proxy), "https": "https://" + str(proxy)})
+            with open(str(path) + "/" + filename, "wb") as code:
+                code.write(r.content)
+                # print(bytes(r),file=code)
+        except IOError as e:
+            print("[-]Movie not found in All website!")
+            print("[-]" + filename, e)
+            # print("[*]=====================================")
+            return "failed"
+        except Exception as e1:
+            print(e1)
+            print("[-]Download Failed2!")
+            time.sleep(3)
+            os._exit(0)
+    else:
+        try:
+            if not os.path.exists(path):
+                os.makedirs(path)
+            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+            r = requests.get(url, headers=headers)
+            with open(str(path) + "/" + filename, "wb") as code:
+                code.write(r.content)
+                # print(bytes(r),file=code)
+        except IOError as e:
+            print("[-]Movie not found in All website!")
+            print("[-]" + filename, e)
+            # print("[*]=====================================")
+            return "failed"
+        except Exception as e1:
+            print(e1)
+            print("[-]Download Failed2!")
+            time.sleep(3)
+            os._exit(0)
+def PrintFiles(path):
+    try:
+        if not os.path.exists(path):
+            os.makedirs(path)
+        with open(path + "/" + naming_rule + ".nfo", "wt", encoding='UTF-8') as code:
+            print("<movie>", file=code)
+            print(" <title>" + title + "</title>", file=code)
+            print("  <set>", file=code)
+            print("  </set>", 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>" + naming_rule + ".png</poster>", file=code)
+            print("  <thumb>" + naming_rule + ".png</thumb>", file=code)
+            print("  <fanart>"+naming_rule + '.jpg'+"</fanart>", file=code)
+            try:
+                for u in actor_list:
+                    print("  <actor>", file=code)
+                    print("   <name>" + u + "</name>", file=code)
+                    print("  </actor>", file=code)
+            except:
+                aaaa=''
+            print("  <maker>" + studio + "</maker>", file=code)
+            print("  <label>", file=code)
+            print("  </label>", 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=''
+            print("  <num>" + number + "</num>", file=code)
+            print("  <release>" + release + "</release>", file=code)
+            print("  <cover>"+cover+"</cover>", file=code)
+            print("  <website>" + "https://www.javbus.com/"+number + "</website>", file=code)
+            print("</movie>", file=code)
+            print("[+]Writeed!          "+path + "/" + naming_rule + ".nfo")
+    except IOError as e:
+        print("[-]Write Failed!")
+        print(e)
+    except Exception as e1:
+        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':
         shutil.move(filepath, 'failed/')
         os._exit(0)
-    DownloadFileWithFilename(getCover(htmlcode), number + '.jpg', path)
+    DownloadFileWithFilename(cover, naming_rule + '.jpg', path)
-    print('[+]Image Downloaded!', path +'/'+number+'.jpg')
+    print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg')
-def cutImage(number):
+def cutImage():
-    try:
+    if imagecut == 1:
-        img = Image.open(path + '/' + number + '.jpg')
+        try:
-        imgSize=img.size
+            img = Image.open(path + '/' + naming_rule + '.jpg')
-        w=img.width
+            imgSize = img.size
-        h=img.height
+            w = img.width
-        img2 = img.crop((w/1.9, 0, w, h))
+            h = img.height
-        img2.save(path + '/' + number + '.png')
+            img2 = img.crop((w / 1.9, 0, w, h))
-    except:
+            img2.save(path + '/' + naming_rule + '.png')
-        print('[-]Cover cut failed!')
+        except:
-def pasteFileToFolder(filepath, number, path): #文件路径，番号，后缀，要移动至的位置
+            print('[-]Cover cut failed!')
+    else:
+        img = Image.open(path + '/' + naming_rule + '.jpg')
+        w = img.width
+        h = img.height
+        img.save(path + '/' + naming_rule + '.png')
+def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
     houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$', filepath).group())
-    os.rename(filepath, number + houzhui)
+    os.rename(filepath, naming_rule + houzhui)
-    shutil.move(number + houzhui, path)
+    shutil.move(naming_rule + houzhui, path)
 
 if __name__ == '__main__':
     filepath=argparse_get_file() #影片的路径
-    number=getNumberFromFilename(filepath) #定义番号
+    CreatFailedFolder()
-    htmlcode=get_html_javbus(number) #获取的HTML代码
+    getNumberFromFilename(filepath) #定义番号
-    creatFolder(htmlcode,number) #创建文件夹
+    creatFolder() #创建文件夹
-    imageDownload(htmlcode,filepath,number) #creatFoder会返回番号路径
+    imageDownload(filepath) #creatFoder会返回番号路径
-    PrintFiles(htmlcode, path,number)#打印文件
+    PrintFiles(path)#打印文件
-    cutImage(number) #裁剪图
+    cutImage() #裁剪图
-    pasteFileToFolder(filepath,number,path) #移动文件
+    pasteFileToFolder(filepath,path) #移动文件

fc2fans_club.py

@@ -0,0 +1,61 @@
+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)
+    return result2
+def getStudio(htmlcode): #获取厂商
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
+    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(" ['']")
+    return result
+def getRelease(number):
+    a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
+    html=etree.fromstring(a,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
+    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())
+    result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
+    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')
+    html = etree.fromstring(a, 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
+#     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())
+#     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
+#     return result
+
+def main(number):
+    str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")
+    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': '',
+        'director': getStudio(htmlcode),
+        'actor': '',
+        'release': getRelease(number),
+        'number': 'FC2-'+number,
+        'cover': getCover(htmlcode,number),
+        'imagecut': 0,
+        'tag':" ",
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
+    return js
+
+#print(main('1104989'))

javbus.py

@@ -0,0 +1,186 @@
+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
+
+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=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(' ','-')
+    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')
+    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.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 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):
+    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),
+        '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)
+    }
+    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': getTitle(htmlcode),
+            'studio': getStudio(htmlcode),
+            'year': getYear(htmlcode),
+            'outline': getOutline(dww_htmlcode),
+            'runtime': getRuntime(htmlcode),
+            'director': getDirector(htmlcode),
+            'actor': getActor(htmlcode),
+            'release': getRelease(htmlcode),
+            'number': getNum(htmlcode),
+            'cover': getCover(htmlcode),
+            'imagecut': 1,
+            'tag': getTag(htmlcode)
+        }
+        js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        return js2
+
+    return js
+
+def main_uncensored(number):
+    htmlcode = get_html('https://www.javbus.com/' + number)
+    dic = {
+        'title': getTitle(htmlcode),
+        'studio': getStudio(htmlcode),
+        'year': getYear(htmlcode),
+        'outline': getOutline(htmlcode),
+        'runtime': getRuntime(htmlcode),
+        'director': getDirector(htmlcode),
+        'actor': getActor(htmlcode),
+        'release': getRelease(htmlcode),
+        'number': getNum(htmlcode),
+        'cover': getCover(htmlcode),
+        'tag': getTag(htmlcode),
+        'imagecut': 0,
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+
+    if getYear(htmlcode) == '' or getYear(htmlcode) == 'null':
+        number2 = number.replace('-', '_')
+        htmlcode = get_html('https://www.javbus.com/' + number2)
+        dic2 = {
+            'title': 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),
+            'tag': getTag(htmlcode),
+            'imagecut': 0,
+        }
+        js2 = json.dumps(dic2, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        return js2
+
+    return js
+
+
+# def return1():
+#     json_data=json.loads(main('ipx-292'))
+#
+#     title = str(json_data['title'])
+#     studio = str(json_data['studio'])
+#     year = str(json_data['year'])
+#     outline = str(json_data['outline'])
+#     runtime = str(json_data['runtime'])
+#     director = str(json_data['director'])
+#     actor = str(json_data['actor'])
+#     release = str(json_data['release'])
+#     number = str(json_data['number'])
+#     cover = str(json_data['cover'])
+#     tag = str(json_data['tag'])
+#
+#     print(title)
+#     print(studio)
+#     print(year)
+#     print(outline)
+#     print(runtime)
+#     print(director)
+#     print(actor)
+#     print(release)
+#     print(number)
+#     print(cover)
+#     print(tag)
+# return1()

proxy.ini

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

py to exe.bat

@@ -0,0 +1,2 @@
+pyinstaller --onefile AV_Data_Capture.py 
+pyinstaller --onefile core.py --hidden-import ADC_function.py --hidden-import fc2fans_club.py --hidden-import javbus.py --hidden-import siro.py

siro.py

@@ -0,0 +1,81 @@
+import re
+from lxml import etree
+import json
+import requests
+from bs4 import BeautifulSoup
+
+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):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
+    return result
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+    html = etree.fromstring(a, etree.HTMLParser())
+    result=str(html.xpath('//table[2]/tr[1]/td/a/text()')).strip(" ['\\n                                        ']")
+    return result
+def getStudio(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result=str(html.xpath('//table[2]/tr[2]/td/a/text()')).strip(" ['\\n                                        ']")
+    return result
+def getRuntime(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result=str(html.xpath('//table[2]/tr[3]/td/text()')).strip(" ['\\n                                        ']")
+    return result
+def getNum(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result=str(html.xpath('//table[2]/tr[4]/td/text()')).strip(" ['\\n                                        ']")
+    return result
+def getYear(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    #result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    return result
+def getRelease(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result=str(html.xpath('//table[2]/tr[5]/td/text()')).strip(" ['\\n                                        ']")
+    return result
+def getTag(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result=str(html.xpath('//table[2]/tr[9]/td/text()')).strip(" ['\\n                                        ']")
+    return result
+def getCover(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="center_column"]/div[2]/div[1]/div/div/h2/img/@src')).strip(" ['']")
+    return result
+def getDirector(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result = str(html.xpath('//table[2]/tr[7]/td/a/text()')).strip(" ['\\n                                        ']")
+    return result
+def getOutline(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
+    return result
+
+def main(number):
+    htmlcode=get_html('https://www.mgstage.com/product/product_detail/'+str(number))
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    a = str(soup.find(attrs={'class': 'detail_data'})).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,
+        'cover': getCover(htmlcode),
+        'imagecut': 0,
+        'tag':' ',
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
+    return js