Delete proxy.ini

ADC_function.py

@@ -5,17 +5,17 @@ import re
 from retrying import retry
 import sys
 
-# content = open('proxy.ini').read()
+# content = open('config.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')
+if os.path.exists('config.ini'):
+    config.read('config.ini', encoding='UTF-8')
 else:
-    with open("proxy.ini", "wt", encoding='UTF-8') as code:
+    with open("config.ini", "wt", encoding='UTF-8') as code:
         print("[proxy]",file=code)
         print("proxy=127.0.0.1:1080",file=code)
         print("timeout=10", file=code)

AV_Data_Capture.py

@@ -7,7 +7,7 @@ import ADC_function
 import json
 import shutil
 
-version='0.11.1'
+version='0.11.4'
 os.chdir(os.getcwd())
 
 def UpdateCheck():
@@ -102,12 +102,20 @@ def getNumber(filepath):
         print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
         print('[-]' + str(os.path.basename(filepath)) + ' :', e)
         print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
+
         shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
     except IOError as e2:
         print('[-]' + str(os.path.basename(filepath)) + ' Cannot catch the number :')
         print('[-]' + str(os.path.basename(filepath)) + ' :', e2)
         print('[-]Move ' + os.path.basename(filepath) + ' to failed folder')
         shutil.move(filepath, str(os.getcwd()) + '/' + 'failed/')
+def RunCore():
+    if os.path.exists('core.py'):
+        os.system('python core.py' + '   "' + i + '" --number "'+getNumber(i)+'"') #选择从py文件启动  （用于源码py）
+    elif os.path.exists('core.exe'):
+        os.system('core.exe' + '   "' + i + '" --number "'+getNumber(i)+'"')      #选择从exe文件启动（用于EXE版程序:
+    elif os.path.exists('core.py') and os.path.exists('core.exe'):
+        os.system('python core.py' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 选择从py文件启动  （用于源码py）
 
 if __name__ =='__main__':
     print('[*]===========AV Data Capture===========')
@@ -124,9 +132,7 @@ if __name__ =='__main__':
         percentage = str(count/int(count_all)*100)[:4]+'%'
         print('[!] - '+percentage+' ['+str(count)+'/'+count_all+'] -')
         print("[!]Making Data for   [" + i + "],the number is [" + getNumber(i) + "]")
-        os.system('python core.py' + '   "' + i + '" --number "'+getNumber(i)+'"') #选择从py文件启动  （用于源码py）
-        #print('core.exe' + '   "' + i + '" --number "'+getNumber(i)+'"')      #选择从exe文件启动（用于EXE版程序
-        #print()
+        RunCore()
         print("[*]=====================================")
 
     CEF('JAV_output')

README.md

@@ -1,23 +1,21 @@
-# AV Data Capture 日本AV元数据刮削器
+# AV Data Capture 日本电影元数据抓取工具（刮削器）
 
 
 <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)
+![](https://img.shields.io/github/downloads/yoshiko2/av_data_capture/total.svg?style=flat-square)<br>
+![](https://img.shields.io/github/languages/code-size/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/issues/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/license/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/release/yoshiko2/av_data_capture.svg?style=flat-square)<br>
+![](https://img.shields.io/github/forks/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/stars/yoshiko2/av_data_capture.svg?style=flat-square)
+![](https://img.shields.io/github/watchers/yoshiko2/av_data_capture.svg?style=flat-square)
 
 
 
 # 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)
@@ -29,22 +27,25 @@
 * [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)
+* [写在后面](#8写在后面)
 
 # 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;目前，我下的日本电影越来越多，也意味着日本电影要**集中地管理**，形成本地媒体库。现在有两款主流的日本电影元数据获取器，"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日本电影，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>
+**推荐用法: 使用该软件后，对于不能正常获取元数据的电影可以用 Everaver 来补救**<br>
 暂不支持多P电影<br>
 [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>
+# 郑重声明
+1.本软件仅供**技术交流，学术交流**使用<br>
+2.本软件禁止用于任何非法用途<br>
+3.使用者使用该软件产生的一切法律后果由使用者承担<br>
+4.本软件禁止任何商用行为<br>
+[回到目录](#目录)
 
 # 效果图
 **由于法律因素，图片必须经马赛克处理**<br>
@@ -52,18 +53,6 @@
 ![](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)
-
-# 免责声明
-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 [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**):[点击前往](https://github.com/wenead99/AV_Data_Capture/releases)<br>
@@ -121,14 +110,18 @@ proxy.ini
 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>
-##### 连接超时重试设置
->timeout=10
+#### 连接超时重试设置
+>[proxy]<br>
+>timeout=10<br>
+
 10为超时重试时间 单位：秒
-##### 连接重试次数设置
->retry=3
+#### 连接重试次数设置
+>[proxy]<br>
+>retry=3<br>
+
 3即为重试次数
 
-### 2.（可选）设置自定义目录和影片重命名规则
+### (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>
@@ -170,7 +163,7 @@ COSQ-004.mp4
 ```
 
 针对**野鸡番号**，你需要把文件名命名为与抓取网站提供的番号一致（文件拓展名除外），然后把文件拖拽至core.exe/.py<br>
-**野鸡番号**:比如 DCL-001-1这种野鸡三段式番号，在javbus等资料库存在的作品。
+**野鸡番号**:比如 DCL-001-1这种野鸡三段式番号，在javbus等资料库存在的作品。<br>（除了SSNI-XXX-C，后面这种-C的是指电影有中文字幕！）
 ![](https://i.loli.net/2019/06/02/5cf2b5d03640e73201.gif)<br>
 条件：文件名中间要有下划线或者减号"_","-"，没有多余的内容只有番号为最佳，可以让软件更好获取元数据
 对于多影片重命名，可以用[ReNamer](http://www.den4b.com/products/renamer)来批量重命名<br>
@@ -182,14 +175,8 @@ COSQ-004.mp4
 ## 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)<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>
+## 8.写在后面
+怎么样，看着自己的日本电影被这样完美地管理，是不是感觉成就感爆棚呢?<br>
 [回到目录](#目录)
 
 

core.py

@@ -30,6 +30,9 @@ tag=[]
 cn_sub=''
 path=''
 houzhui=''
+website=''
+json_data={}
+actor_photo={}
 naming_rule  =''#eval(config['Name_Rule']['naming_rule'])
 location_rule=''#eval(config['Name_Rule']['location_rule'])
 
@@ -63,6 +66,8 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     global tag
     global image_main
     global cn_sub
+    global website
+    global actor_photo
 
     global naming_rule
     global location_rule
@@ -70,7 +75,7 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     try:    # 添加 需要 正则表达式的规则
         # =======================javdb.py=======================
         if re.search('^\d{5,}', file_number).group() in file_number:
-            json_data = json.loads(javdb.main(file_number))
+            json_data = json.loads(javbus.main_uncensored(file_number))
     except:  # 添加 无需 正则表达式的规则
         # ====================fc2fans_club.py====================
         if 'fc2' in file_number:
@@ -99,6 +104,8 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     imagecut =       json_data['imagecut']
     tag =        str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',')  # 字符串转列表
     actor =      str(actor_list).strip("[ ]").replace("'", '').replace(" ", '')
+    actor_photo =    json_data['actor_photo']
+    website =        json_data['website']
 
     # ====================处理异常字符====================== #\/:*?"<>|
     if '\\' in title:
@@ -142,7 +149,7 @@ def creatFolder(): #创建文件夹
 #=====================资源下载部分===========================
 def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in the Project Folder!
     config = ConfigParser()
-    config.read('proxy.ini', encoding='UTF-8')
+    config.read('config.ini', encoding='UTF-8')
     proxy       = str(config['proxy']['proxy'])
     timeout     = int(config['proxy']['timeout'])
     retry_count = int(config['proxy']['retry'])
@@ -184,19 +191,20 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
             print('[-]Image Download :  Connect retry '+str(i)+'/'+str(retry_count))
 def imageDownload(filepath): #封面是否下载成功，否则移动到failed
     global path
-    if DownloadFileWithFilename(cover,naming_rule+'.jpg', path) == 'failed':
+    if DownloadFileWithFilename(cover,'fanart.jpg', path) == 'failed':
         shutil.move(filepath, 'failed/')
         os._exit(0)
-    DownloadFileWithFilename(cover, naming_rule+'.jpg', path)
-    print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg')
+    DownloadFileWithFilename(cover, 'fanart.jpg', path)
+    print('[+]Image Downloaded!', path +'/fanart.jpg')
 def PrintFiles(filepath):
     #global path
     global title
     global cn_sub
+    global actor_photo
     try:
         if not os.path.exists(path):
             os.makedirs(path)
-        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>" + naming_rule + "</title>", file=code)
             print("  <set>", file=code)
@@ -207,13 +215,15 @@ def PrintFiles(filepath):
             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)
+            print("  <poster>poster.png</poster>", file=code)
+            print("  <thumb>thumb.png</thumb>", file=code)
+            print("  <fanart>fanart.jpg</fanart>", file=code)
             try:
-                for u in actor_list:
+                for key, value in actor_photo.items():
                     print("  <actor>", file=code)
-                    print("   <name>" + u + "</name>", file=code)
+                    print("   <name>" + key + "</name>", file=code)
+                    if not actor_photo == '':  # or actor_photo == []:
+                        print("   <thumb>" + value + "</thumb>", file=code)
                     print("  </actor>", file=code)
             except:
                 aaaa=''
@@ -237,9 +247,9 @@ def PrintFiles(filepath):
             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("  <website>" + website + "</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)
@@ -253,31 +263,32 @@ def PrintFiles(filepath):
 def cutImage():
     if imagecut == 1:
         try:
-            img = Image.open(path + '/' + naming_rule + '.jpg')
+            img = Image.open(path + '/fanart.jpg')
             imgSize = img.size
             w = img.width
             h = img.height
             img2 = img.crop((w / 1.9, 0, w, h))
-            img2.save(path + '/' + naming_rule + '.png')
+            img2.save(path + '/poster.png')
         except:
             print('[-]Cover cut failed!')
     else:
-        img = Image.open(path + '/' + naming_rule + '.jpg')
+        img = Image.open(path + '/fanart.jpg')
         w = img.width
         h = img.height
-        img.save(path + '/' + naming_rule + '.png')
+        img.save(path + '/poster.png')
 def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
     global houzhui
     houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
-    os.rename(filepath, naming_rule + houzhui)
-    shutil.move(naming_rule + houzhui, path)
+    os.rename(filepath, number + houzhui)
+    shutil.move(number + houzhui, path)
 def renameJpgToBackdrop_copy():
-    shutil.copy(path+'/'+naming_rule + '.jpg', path+'/Backdrop.jpg')
+    shutil.copy(path+'/fanart.jpg', path+'/Backdrop.jpg')
+    shutil.copy(path + '/poster.png', path + '/thumb.png')
 
 if __name__ == '__main__':
     filepath=argparse_get_file()[0] #影片的路径
 
-    if '-c.' in filepath or '-C.' in filepath:
+    if '-c.' in filepath or '-C.' in filepath or '中文' in filepath or '字幕' in filepath:
         cn_sub='1'
 
     if argparse_get_file()[1] == '':    #获取手动拉去影片获取的番号

fc2fans_club.py

@@ -72,7 +72,9 @@ def main(number2):
         'number':  'FC2-'+number,
         'cover':    getCover(htmlcode,number,htmlcode2),
         'imagecut': 0,
-        'tag':getTag(htmlcode),
+        'tag':      getTag(htmlcode),
+        'actor_photo':'',
+        'website':  'http://fc2fans.club/html/FC2-' + number + '.html',
     }
     #print(getTitle(htmlcode))
     #print(getNum(htmlcode))

javbus.py

@@ -13,6 +13,18 @@ from ADC_function import *
 import javdb
 import siro
 
+def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    a = soup.find_all(attrs={'class': 'star-name'})
+    d={}
+    for i in a:
+        l=i.a['href']
+        t=i.get_text()
+        html = etree.fromstring(get_html(l), etree.HTMLParser())
+        p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
+        p2={t:p}
+        d.update(p2)
+    return d
 def getTitle(htmlcode):  #获取标题
     doc = pq(htmlcode)
     title=str(doc('div.container h3').text()).replace(' ','-')
@@ -100,17 +112,18 @@ def main(number):
             'imagecut': 1,
             'tag': getTag(htmlcode),
             'label': getSerise(htmlcode),
+            'actor_photo': getActorPhoto(htmlcode),
+            'website': 'https://www.javbus.com/' + number,
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
-
         if 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
             htmlcode = get_html('https://www.javbus.com/' + number)
-            dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+            #dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
             dic = {
                 'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
                 'studio': getStudio(htmlcode),
                 'year': getYear(htmlcode),
-                'outline': getOutline(dww_htmlcode),
+                'outline': '',
                 'runtime': getRuntime(htmlcode),
                 'director': getDirector(htmlcode),
                 'actor': getActor(htmlcode),
@@ -120,6 +133,8 @@ def main(number):
                 'imagecut': 1,
                 'tag': getTag(htmlcode),
                 'label': getSerise(htmlcode),
+                'actor_photo': getActorPhoto(htmlcode),
+                'website': 'https://www.javbus.com/' + number,
             }
             js2 = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,
                              separators=(',', ':'), )  # .encode('UTF-8')
@@ -132,6 +147,9 @@ def main(number):
 def main_uncensored(number):
     htmlcode = get_html('https://www.javbus.com/' + number)
     dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+    if getTitle(htmlcode) == '':
+        htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
+        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
     dic = {
         'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
         'studio': getStudio(htmlcode),
@@ -146,6 +164,8 @@ def main_uncensored(number):
         'tag': getTag(htmlcode),
         'label': getSerise(htmlcode),
         'imagecut': 0,
+        'actor_photo': '',
+        'website': 'https://www.javbus.com/' + number,
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
 

javdb.py

@@ -56,6 +56,8 @@ def getTag(a):
 def getCover(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']")
+    if result == '':
+        result = str(html.xpath('/html/body/section/div/div[3]/div[1]/a/img/@src')).strip(" ['']")
     return result
 def getDirector(a):
     html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
@@ -68,11 +70,11 @@ def getOutline(htmlcode):
     return result
 def main(number):
     try:
-        try:
-            a = get_html('https://javdb1.com/search?q=' + number + '&f=all')
+        a = get_html('https://javdb.com/search?q=' + number + '&f=all')
         html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        except:
-            a = get_html('https://javdb1.com/search?q=' + number.replace('-', '_') + '&f=all')
+        result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+        if result1 == '':
+            a = get_html('https://javdb.com/search?q=' + number.replace('-', '_') + '&f=all')
             html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
             result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
         b = get_html('https://javdb1.com' + result1)
@@ -95,17 +97,20 @@ def main(number):
             'tag': getTag(a),
             'label': getLabel(a),
             'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+            'actor_photo': '',
+            'website': 'https://javdb1.com' + result1,
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
         return js
     except:
-        try:
         a = get_html('https://javdb.com/search?q=' + number + '&f=all')
         html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        except:
+        result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+        if result1 == '':
             a = get_html('https://javdb.com/search?q=' + number.replace('-', '_') + '&f=all')
             html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
             result1 = str(html.xpath('//*[@id="videos"]/div/div/a/@href')).strip(" ['']")
+
         b = get_html('https://javdb.com' + result1)
         soup = BeautifulSoup(b, 'lxml')
 
@@ -126,6 +131,8 @@ def main(number):
             'tag': getTag(a),
             'label': getLabel(a),
             'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+            'actor_photo': '',
+            'website':'https://javdb.com' + result1,
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
         return js

siro.py

@@ -95,6 +95,8 @@ def main(number2):
         'tag': getTag(a),
         'label':getLabel(a),
         'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+        'actor_photo': '',
+        'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
     return js

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "0.11.1",
-	"version_show":"Beta 11.1",
+	"version": "0.11.4",
+	"version_show":"Beta 11.4",
 	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
 }