0.6 更新:Javbus抓取的元数据支持标签功能，优化无码视频抓取

This is readms.md's images folder

ADC_function.py

@@ -0,0 +1,10 @@
+import requests
+
+def get_html(url):#网页请求核心
+    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
+    getweb = requests.get(str(url),timeout=5,headers=headers)
+    getweb.encoding='utf-8'
+    try:
+        return getweb.text
+    except:
+        print("[-]Connect Failed! Please check your Proxy.")

AV_Data_Capture.py

@@ -1,13 +1,60 @@
 import glob
 import os
 import time
+import re
 
-#a=glob.glob(os.getcwd()+r"\*.py")
-a=glob.glob(os.getcwd()+r"\*\**\*.mp4")
-b=glob.glob(os.getcwd()+r"\*.mp4")
-for i in b:
-    a.append(i)
+def movie_lists():
+    #MP4
+    a2 = glob.glob(os.getcwd() + r"\*.mp4")
+    # AVI
+    b2 = glob.glob(os.getcwd() + r"\*.avi")
+    # RMVB
+    c2 = glob.glob(os.getcwd() + r"\*.rmvb")
+    # WMV
+    d2 = glob.glob(os.getcwd() + r"\*.wmv")
+    # MOV
+    e2 = glob.glob(os.getcwd() + r"\*.mov")
+    # MKV
+    f2 = glob.glob(os.getcwd() + r"\*.mkv")
+    # FLV
+    g2 = glob.glob(os.getcwd() + r"\*.flv")
 
-os.chdir(os.getcwd())
-for i in a:
-    os.system('python core.py'+' "'+i+'"')
+    total = a2+b2+c2+d2+e2+f2+g2
+    return total
+
+def lists_from_test(custom_nuber): #电影列表
+
+    a=[]
+    a.append(custom_nuber)
+    return a
+
+def CEF(path):
+    files = os.listdir(path)  # 获取路径下的子文件(夹)列表
+    for file in files:
+        try: #试图删除空目录,非空目录删除会报错
+            os.removedirs(path + '/' + file)  # 删除这个空文件夹
+            print('[+]Deleting empty folder',path + '/' + file)
+        except:
+            a=''
+
+def rreplace(self, old, new, *max):
+#从右开始替换文件名中内容，源字符串，将被替换的子字符串， 新字符串，用于替换old子字符串，可选字符串, 替换不超过 max 次
+    count = len(self)
+    if max and str(max[0]).isdigit():
+        count = max[0]
+    return new.join(self.rsplit(old, count))
+
+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(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('core.exe' + ' "' + i + '"')      #选择从exe文件启动（用于EXE版程序）
+        print("[*]=====================================")
+
+    print("[!]Cleaning empty folders")
+    CEF('JAV_output')
+    print("[+]All finished!!!")
+    time.sleep(3)

README.md

@@ -1,28 +1,77 @@
-日本AV元数据抓取工具  
-========================
-**关于本软件**
+# 日本AV元数据抓取工具  （刮削器）
+
+## 关于本软件 （~路star谢谢）
+
+**#0.5重大更新：新增对FC2,259LUXU,SIRO,300MAAN系列影片抓取支持,优化对无码视频抓取**
 
 目前，我下的AV越来越多，也意味着AV要集中地管理，形成媒体库。现在有两款主流的AV元数据获取器，"EverAver"和"Javhelper"。前者的优点是元数据获取比较全，缺点是不能批量处理；后者优点是可以批量处理，但是元数据不够全。
 
-为此，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。
+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 
 
-**如何使用**
-1. 请安装requests,pyquery,lxml,Beautifulsoup,pillow模块,可在CMD逐条输入以下命令安装
-  `pip install requests`
-  `pip install pyquery`
-  `pip install lxml`
-  `pip install beautifulsoup4`
-  `pip install pillow`
-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"-"，没有多余元数据只有番号为最佳，可以让软件更好获取元数据
+**预计本周末适配DS Video，暂时只支持Kodi,EMBY**
 
-![](readme1.PNG)
+**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)
+
+![](https://i.loli.net/2019/06/02/5cf2b5d0bbecf69019.png)
+
+
+## 软件流程图
+![](https://i.loli.net/2019/06/02/5cf2bb9a9e2d997635.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
+```
+###
+```python
+pip install Beautifulsoup4
+```
+###
+```python
+pip install pillow
+```
+
+2. 你的AV在被软件管理前最好命名为番号:
+```
+COSQ-004.mp4
+```
+或者
+```
+COSQ_004.mp4
+```
+文件名中间要有下划线或者减号"_","-"，没有多余的内容只有番号为最佳，可以让软件更好获取元数据
+对于多影片重命名，可以用ReNamer来批量重命名
+软件官网:http://www.den4b.com/products/renamer
+
+![](https://i.loli.net/2019/06/02/5cf2b5cfbfe1070559.png)
 
 3. 把软件拷贝到AV的所在目录下，运行程序（中国大陆用户必须挂VPN，Shsadowsocks开全局代理）
 4. 运行AV_Data_capture.py
-5. 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。
+5. **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
+
+![](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)
+
 
-![](readme2.PNG)
-![](readme3.PNG)
-![](readme4.PNG)
 

core.py

@@ -1,186 +1,228 @@
 import re
-import requests #need install
-from pyquery import PyQuery as pq#need install
-from lxml import etree#need install
 import os
 import os.path
 import shutil
-from bs4 import BeautifulSoup#need install
-from PIL import Image#need install
+from PIL import Image
 import time
+import javbus
+import json
+import fc2fans_club
+import siro
 
-def get_html(url):
-    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),proxies={"http": "http://127.0.0.1:2334","https": "https://127.0.0.1:2334"},timeout=5,headers=headers).text
-    try:
-        return getweb
-    except Exception as e:
-        print(e)
-    except IOError as e1:
-        print(e1)
-#================================================
-def getTitle(htmlcode):
-    doc = pq(htmlcode)
-    title=str(doc('div.container h3').text()).replace(' ','-')
-    return title
-def getStudio(htmlcode):
-    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):
-    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):
-    doc = pq(htmlcode)
-    image = doc('a.bigImage')
-    return image.attr('href')
-    print(image.attr('href'))
-def getRelease(htmlcode):
-    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):
-    soup = BeautifulSoup(htmlcode, 'lxml')
-    a = soup.find(text=re.compile('分鐘'))
-    return a
-def getActor(htmlcode):
-    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):
-    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):
-    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):
-    doc = pq(htmlcode)
-    result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
-    return result
-#================================================
+#初始化全局变量
+title=''
+studio=''
+year=''
+outline=''
+runtime=''
+director=''
+actor=[]
+release=''
+number=''
+cover=''
+imagecut=''
+tag=[]
+
+#=====================资源下载部分===========================
 def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
     import requests
-    import re
     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)
-            # print('[+]Downloaded!',str(path) + "/"+str(filename))
     except IOError as e:
-        print("[-]Download Failed1!")
-        print("[-]Movie not found in Javbus.com!")
-        print("[*]=====================================")
+        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(path):
     try:
         if not os.path.exists(path):
             os.makedirs(path)
-        with open(path + "/" + getNum(html) + ".nfo", "wt", encoding='UTF-8') as code:
+        with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code:
             print("<movie>", file=code)
-            print(" <title>" + getTitle(html) + "</title>", file=code)
+            print(" <title>" + title + "</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(html_outline)+"</outline>", file=code)
-            print("  <plot>"+getOutline(html_outline)+"</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("  <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>" + number + ".png</poster>", file=code)
+            print("  <thumb>" + number + ".png</thumb>", file=code)
+            print("  <fanart>"+number + '.jpg'+"</fanart>", file=code)
+            try:
+                for u in actor:
                     print("  <actor>", file=code)
-            print("    <name>" + getActor(html) + "</name>", file=code)
+                    print("   <name>" + u + "</name>", file=code)
                     print("  </actor>", file=code)
-            print("  <maker>" + getStudio(html) + "</maker>", file=code)
+            except:
+                aaaa=''
+            print("  <maker>" + studio + "</maker>", file=code)
             print("  <label>", file=code)
             print("  </label>", file=code)
-            print("  <num>" + getNum(html) + "</num>", file=code)
-            print("  <release>" + getRelease(html) + "</release>", file=code)
-            print("  <cover>"+getCover(html)+"</cover>", file=code)
-            print("  <website>" + "https://www.javbus.com/"+getNum(html) + "</website>", file=code)
+            try:
+                for i in tag:
+                    print("  <tag>" + i + "</tag>", file=code)
+            except:
+                aaaa=''
+            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 + "/" + getNum(html) + ".nfo")
+            print("[+]Writeed!    "+path + "/" + number + ".nfo")
     except IOError as e:
         print("[-]Write Failed!")
         print(e)
     except Exception as e1:
         print(e1)
         print("[-]Write Failed!")
-#================================================
-if __name__ == '__main__':
-    #命令行处理
+
+#=====================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()
-    filename=str(os.path.basename(args.file)) #\[\d{4}(\-|\/|.)\d{1,2}\1\d{1,2}\]
-    #去除文件名中日期
-    #print(filename)
-    deldate=str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ","",filename))
-    #print(deldate)
-    number=str(re.search('\w+-\w+',deldate).group())
-    #print(number)
-    #获取网页信息
-    html = get_html("https://www.javbus.com/"+str(number))
-    html_outline=get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid="+number.replace("-",''))
-    #处理超长文件夹名称
-    if len(getActor(html)) > 240:
-        path = 'JAV_output' + '/' + '超多人' + '/' + getNum(html)
+    return args.file
+def getNumberFromFilename(filepath):
+    global title
+    global studio
+    global year
+    global outline
+    global runtime
+    global director
+    global actor
+    global release
+    global number
+    global cover
+    global imagecut
+    global tag
+
+    filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", os.path.basename(filepath)))
+    print("[!]Making Data for ["+filename+"]")
+    file_number = str(re.search('\w+-\w+', filename).group())
+    #print(a)
+    try:
+
+
+
+
+
+#================================================网站规则添加开始================================================
+
+
+        try:  #添加 需要 正则表达式的规则
+            if re.search('^\d{5,}', file_number).group() in filename:
+                json_data = json.loads(javbus.main_uncensored(file_number))
+        except: #添加 无需 正则表达式的规则
+            if 'fc2' in filename:
+                json_data = json.loads(fc2fans_club.main(file_number))
+            elif 'FC2' in filename:
+                json_data = json.loads(fc2fans_club.main(file_number))
+            elif 'siro' in filename:
+                json_data = json.loads(siro.main(file_number))
+            elif 'SIRO' in filename:
+                json_data = json.loads(siro.main(file_number))
+            elif '259luxu' in filename:
+                json_data = json.loads(siro.main(file_number))
+            elif '259LUXU' in filename:
+                json_data = json.loads(siro.main(file_number))
             else:
-        path = 'JAV_output' + '/' + getActor(html) + '/' + getNum(html)
-    if not os.path.exists(path):
-        os.makedirs(path)
-    #文件路径处理
-    #print(str(args))
-    filepath = str(args).replace("Namespace(file='",'').replace("')",'').replace('\\\\', '\\')
-    #print(filepath)
-    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|avi|rmvb|wmv|mov|mp4|mkv|flv)$',filepath).group())
-    print("[!]Making Data for ["+number+houzhui+"]")
-    #下载元数据
+                json_data = json.loads(javbus.main(file_number))
 
 
+#================================================网站规则添加结束================================================
+
+
+
+
+
+
+        title = json_data['title']
+        studio = json_data['studio']
+        year = json_data['year']
+        outline = json_data['outline']
+        runtime = json_data['runtime']
+        director = json_data['director']
+        actor = str(json_data['actor']).strip("[ ]").replace("'",'').replace(" ",'').split(',')
+        release = json_data['release']
+        number = json_data['number']
+        cover = json_data['cover']
+        imagecut = json_data['imagecut']
+        tag =   str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')
+    except:
+        print('[-]File '+filename+'`s number can not be caught')
+        print('[-]Move ' + filename + ' to failed folder')
+        if not os.path.exists('failed/'):  # 新建failed文件夹
+            os.makedirs('failed/')
             if not os.path.exists('failed/'):
+                print("[-]failed!Dirs can not be make (Please run as Administrator)")
+                time.sleep(3)
+                os._exit(0)
+        shutil.move(filepath, str(os.getcwd())+'/'+'failed/')
+        os._exit(0)
+
+path = '' #设置path为全局变量，后面移动文件要用
+
+def creatFolder():
+    actor2 = str(actor).strip("[ ]").replace("'",'').replace(" ",'')
+    global path
+    if not os.path.exists('failed/'): #新建failed文件夹
         os.makedirs('failed/')
         if not os.path.exists('failed/'):
             print("[-]failed!Dirs can not be make (Please run as Administrator)")
             os._exit(0)
-        if DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path) == 'failed':
-            shutil.move(filepath, 'failed/')
-            time.sleep(3)
-            os._exit(0)
+    if len(actor2) > 240:    #新建成功输出文件夹
+        path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录
     else:
-        if DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path) == 'failed':
+        path = 'JAV_output' + '/' + str(actor2) + '/' + str(number)
+    if not os.path.exists(path):
+        os.makedirs(path)
+    path = str(os.getcwd())+'/'+path
+
+def imageDownload(filepath): #封面是否下载成功，否则移动到failed
+    if DownloadFileWithFilename(cover,str(number) + '.jpg', path) == 'failed':
         shutil.move(filepath, 'failed/')
         os._exit(0)
-        DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path)
-        print('[+]Downloaded!', path +'/'+getNum(html)+'.jpg')
-    #切割图片做封面
+    DownloadFileWithFilename(cover, number + '.jpg', path)
+    print('[+]Image Downloaded!', path +'/'+number+'.jpg')
+def cutImage():
+    if imagecut == 1:
         try:
-        img = Image.open(path + '/' + getNum(html) + '.jpg')
-        img2 = img.crop((421, 0, 800, 538))
-        img2.save(path + '/' + getNum(html) + '.png')
+            img = Image.open(path + '/' + number + '.jpg')
+            imgSize = img.size
+            w = img.width
+            h = img.height
+            img2 = img.crop((w / 1.9, 0, w, h))
+            img2.save(path + '/' + number + '.png')
         except:
             print('[-]Cover cut failed!')
-    # 电源文件位置处理
+    else:
+        img = Image.open(path + '/' + number + '.jpg')
+        w = img.width
+        h = img.height
+        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())
     os.rename(filepath, number + houzhui)
     shutil.move(number + houzhui, path)
-    #处理元数据
-    PrintFiles(path)
-    print('[!]Finished!')
-    time.sleep(3)
+
+if __name__ == '__main__':
+    filepath=argparse_get_file() #影片的路径
+    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
+    cutImage() #裁剪图
+    pasteFileToFolder(filepath,path) #移动文件

fc2fans_club.py

@@ -0,0 +1,58 @@
+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(" ['']")
+    return result
+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': getRelease(number),
+        'outline': getOutline(htmlcode,number),
+        'runtime': '',
+        'director': getStudio(htmlcode),
+        'actor': '',
+        'release': getRelease(number),
+        'number': 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

javbus.py

@@ -0,0 +1,172 @@
+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=5,headers=headers).text
+    try:
+        return getweb
+    except:
+        print("[-]Connect Failed! Please check your Proxy.")
+
+def getTitle(htmlcode):  #获取标题
+    doc = pq(htmlcode)
+    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': 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)
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
+    return js
+
+def main_uncensored(number):
+    htmlcode = get_html('https://www.javbus.com/' + number)
+    dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+    #print('un')
+    #print('https://www.javbus.com/' + number)
+    dic = {
+        'title': getTitle(htmlcode),
+        'studio': getStudio(htmlcode),
+        'year': getYear(htmlcode),
+        'outline': getOutline(htmlcode),
+        'runtime': getRuntime(htmlcode),
+        'director': getDirector(htmlcode),
+        'actor': getActor(htmlcode),
+        'release': getRelease(htmlcode),
+        'number': getNum(htmlcode),
+        'cover': getCover(htmlcode),
+        'tag': getTag(htmlcode),
+        'imagecut': 0,
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+
+    if getYear(htmlcode) == '':
+        #print('un2')
+        number2 = number.replace('-', '_')
+        htmlcode = get_html('https://www.javbus.com/' + number2)
+        #print('https://www.javbus.com/' + number2)
+        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number2.replace("_", ''))
+        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')
+        #print(js)
+        return js
+    else:
+        bbb=''
+
+
+# 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()

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

readme/This is readms.md's images folder

@@ -0,0 +1 @@
+1

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=5,cookies=cookies,headers=headers).text
+    try:
+        return getweb
+    except:
+        print("[-]Connect Failed! Please check your Proxy.")
+
+def getTitle(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="center_column"]/div[2]/h1/text()')).strip(" ['']")
+    return result
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+    html = etree.fromstring(a, etree.HTMLParser())
+    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