Beta 0.15 更新

AV_Data_Capture.py

@@ -6,7 +6,7 @@ import sys
 from ADC_function import *
 import json
 
-version='0.10.3'
+version='0.10.4'
 
 def UpdateCheck():
     html2 = get_html('https://raw.githubusercontent.com/wenead99/AV_Data_Capture/master/update_check.json')

README.md

@@ -1,3 +1,10 @@
+# AV Data Capture 日本AV元数据刮削器
+# 目录
+* [前言](#前言)
+* [捐助二维码](#捐助二维码)
+* [免责声明](#免责声明)
+* [如何使用](#如何使用)
+* [简明教程](#简要教程)
 # 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。
@@ -8,8 +15,8 @@
 ![](https://i.loli.net/2019/06/02/5cf2b5d0bbecf69019.png)
 
 # 捐助二维码
-如果你觉得本软件好用，可以考虑捐助作者，你的支持就是我的动力，非常感谢您的捐助
-![](https://i.loli.net/2019/06/21/5d0c3dcdc95c979755.png)
+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)
 
 # 免责声明
 1.本软件仅供技术交流，学术交流使用<br>
@@ -21,7 +28,7 @@
 release的程序可脱离python环境运行，可跳过第一步<br>
 下载地址(仅限Windows):https://github.com/wenead99/AV_Data_Capture/releases
 ### 简要教程:<br>
-**1.把软件拉到和电影的同一目录<br>2.设置ini文件的代理<br>3.运行软件等待完成<br>4.把JAV_output导入至KODI,EMBY中。<br>详细请看以下教程**
+**1.把软件拉到和电影的同一目录<br>2.设置ini文件的代理（路由器拥有自动代理功能的可以把proxy=后面内容去掉）<br>3.运行软件等待完成<br>4.把JAV_output导入至KODI,EMBY中。<br>详细请看以下教程**
 
 ## 1.请安装模块,在CMD/终端逐条输入以下命令安装
 ```python
@@ -45,7 +52,7 @@ pip install pillow
 ```
 ###
 
-## 2. 配置
+## 2.配置
 #### 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>
@@ -70,7 +77,7 @@ pip install pillow
 >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
+## 3.关于番号提取失败或者异常
 **目前可以提取元素的影片:JAVBUS上有元数据的电影，素人系列(需要日本代理):300Maan,259luxu,siro等,FC2系列**<br>
 >下一张图片来自Pockies的blog:https://pockies.github.io/2019/03/25/everaver-emby-kodi/ 原作者已授权<br>
 
@@ -85,13 +92,13 @@ 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](http://www.den4b.com/products/renamer)来批量重命名
 
-## 4. 把软件拷贝和AV的统一目录下
-## 5. 运行 ```AV_Data_capture.py/.exe```
+## 4.把软件拷贝和AV的统一目录下
+## 5.运行 ```AV_Data_capture.py/.exe```
 你也可以把单个影片拖动到core程序<br>
 ![](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
+## 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)

core.py

@@ -136,6 +136,10 @@ def getNumberFromFilename(filepath):
         tag       = str(json_data['tag']).strip("[ ]").replace("'",'').replace(" ",'').split(',')   #字符串转列表
         actor = str(actor_list).strip("[ ]").replace("'",'').replace(" ",'')
 
+        #====================处理异常字符====================== #\/:*?"<>|
+        #if "\\" in title or "/" in title or ":" in title or "*" in title or "?" in title or '"' in title or '<' in title or ">" in title or "|" in title or len(title) > 200:
+        #    title = title.
+
         naming_rule  = eval(config['Name_Rule']['naming_rule'])
         location_rule =eval(config['Name_Rule']['location_rule'])
     except IOError as e:
@@ -204,13 +208,14 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
             print("[-]Download Failed2!")
             time.sleep(3)
             os._exit(0)
-def PrintFiles(path):
+def PrintFiles(path,naming_rule):
+    global title
     try:
         if not os.path.exists(path):
             os.makedirs(path)
-        with open(path + "/" + naming_rule + ".nfo", "wt", encoding='UTF-8') as code:
+        with open(path + "/" + number + ".nfo", "wt", encoding='UTF-8') as code:
             print("<movie>", file=code)
-            print(" <title>" + title + "</title>", file=code)
+            print(" <title>" + naming_rule + "</title>", file=code)
             print("  <set>", file=code)
             print("  </set>", file=code)
             print("  <studio>" + studio + "+</studio>", file=code)
@@ -247,7 +252,7 @@ def PrintFiles(path):
             print("  <cover>"+cover+"</cover>", file=code)
             print("  <website>" + "https://www.javbus.com/"+number + "</website>", file=code)
             print("</movie>", file=code)
-            print("[+]Writeed!          "+path + "/" + naming_rule + ".nfo")
+            print("[+]Writeed!          "+path + "/" + number + ".nfo")
     except IOError as e:
         print("[-]Write Failed!")
         print(e)
@@ -255,31 +260,31 @@ def PrintFiles(path):
         print(e1)
         print("[-]Write Failed!")
 def imageDownload(filepath): #封面是否下载成功，否则移动到failed
-    if DownloadFileWithFilename(cover,naming_rule+ '.jpg', path) == 'failed':
+    if DownloadFileWithFilename(cover,'Backdrop.jpg', path) == 'failed':
         shutil.move(filepath, 'failed/')
         os._exit(0)
-    DownloadFileWithFilename(cover, naming_rule + '.jpg', path)
-    print('[+]Image Downloaded!', path +'/'+naming_rule+'.jpg')
+    DownloadFileWithFilename(cover, 'Backdrop.jpg', path)
+    print('[+]Image Downloaded!', path +'/'+'Backdrop.jpg')
 def cutImage():
     if imagecut == 1:
         try:
-            img = Image.open(path + '/' + naming_rule + '.jpg')
+            img = Image.open(path + '/' + 'Backdrop' + '.jpg')
             imgSize = img.size
             w = img.width
             h = img.height
             img2 = img.crop((w / 1.9, 0, w, h))
-            img2.save(path + '/' + naming_rule + '.png')
+            img2.save(path + '/' + number + '.png')
         except:
             print('[-]Cover cut failed!')
     else:
-        img = Image.open(path + '/' + naming_rule + '.jpg')
+        img = Image.open(path + '/' + 'Backdrop' + '.jpg')
         w = img.width
         h = img.height
-        img.save(path + '/' + naming_rule + '.png')
+        img.save(path + '/' + number + '.png')
 def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移动至的位置
     houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|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)
 
 if __name__ == '__main__':
     filepath=argparse_get_file() #影片的路径
@@ -287,6 +292,6 @@ if __name__ == '__main__':
     getNumberFromFilename(filepath) #定义番号
     creatFolder() #创建文件夹
     imageDownload(filepath) #creatFoder会返回番号路径
-    PrintFiles(path)#打印文件
+    PrintFiles(path,naming_rule)#打印文件
     cutImage() #裁剪图
     pasteFileToFolder(filepath,path) #移动文件

fc2fans_club.py

@@ -10,6 +10,14 @@ def getTitle(htmlcode): #获取厂商
     result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
     #print(result2)
     return result2
+def getActor(htmlcode):
+    try:
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[5]/a/text()')).strip(" ['']")
+        return result
+    except:
+        return ''
+
 def getStudio(htmlcode): #获取厂商
     html = etree.fromstring(htmlcode,etree.HTMLParser())
     result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
@@ -19,47 +27,58 @@ def getNum(htmlcode):     #获取番号
     result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
     #print(result)
     return result
-def getRelease(number):
-    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())
+def getRelease(htmlcode2): #
+    #a=ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
+    html=etree.fromstring(htmlcode2,etree.HTMLParser())
     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[4]/text()')).strip(" ['']")
     return result
-def getCover(htmlcode,number): #获取厂商
-    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())
+def getCover(htmlcode,number,htmlcode2): #获取厂商 #
+    #a = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id=' + str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-") + '&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
+    html = etree.fromstring(htmlcode2, etree.HTMLParser())
     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[1]/a/img/@src')).strip(" ['']")
-    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())
+    if result == '':
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
+        return 'http://fc2fans.club' +  result2
+    return 'http:' + result
+
+def getOutline(htmlcode2,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(htmlcode2, etree.HTMLParser())
     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).replace("\\n",'',10000).strip(" ['']").replace("'",'',10000)
     return result
-# def getTag(htmlcode,number):     #获取番号
-#     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):     #获取番号
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[4]/a/text()'))
+    return result.strip(" ['']").replace("'",'').replace(' ','')
+def getYear(release):
+    try:
+        result = re.search('\d{4}',release).group()
+        return result
+    except:
+        return ''
 
 def main(number2):
     number=number2.replace('PPV','').replace('ppv','')
+    htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
     htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
     dic = {
         'title': getTitle(htmlcode),
         'studio': getStudio(htmlcode),
-        'year': str(re.search('\d{4}',getRelease(number)).group()),
+        'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
         'outline': getOutline(htmlcode,number),
-        'runtime': '',
+        'runtime': getYear(getRelease(htmlcode)),
         'director': getStudio(htmlcode),
-        'actor': '',
+        'actor': getActor(htmlcode),
         'release': getRelease(number),
         'number': 'FC2-'+number,
-        'cover': getCover(htmlcode,number),
+        'cover': getCover(htmlcode,number,htmlcode2),
         'imagecut': 0,
-        'tag':" ",
+        'tag':getTag(htmlcode),
     }
     #print(getTitle(htmlcode))
     #print(getNum(htmlcode))
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
     return js
 
-#print(main('1104989'))
+#print(main('1051725'))

javbus.py

@@ -15,7 +15,11 @@ import siro
 def getTitle(htmlcode):  #获取标题
     doc = pq(htmlcode)
     title=str(doc('div.container h3').text()).replace(' ','-')
-    return title
+    try:
+        title2 = re.sub('n\d+-','',title)
+        return title2
+    except:
+        return title
 def getStudio(htmlcode): #获取厂商
     html = etree.fromstring(htmlcode,etree.HTMLParser())
     result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
@@ -121,7 +125,7 @@ def main_uncensored(number):
     htmlcode = get_html('https://www.javbus.com/' + number)
     dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
     dic = {
-        'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
+        'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
         'studio': getStudio(htmlcode),
         'year': getYear(htmlcode),
         'outline': getOutline(dww_htmlcode),
@@ -141,7 +145,7 @@ def main_uncensored(number):
         number2 = number.replace('-', '_')
         htmlcode = get_html('https://www.javbus.com/' + number2)
         dic2 = {
-            'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))),
+            'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
             'studio': getStudio(htmlcode),
             'year': getYear(htmlcode),
             'outline': '',
@@ -160,8 +164,6 @@ def main_uncensored(number):
 
     return js
 
-#print(main('SIRO-3821'))
-
 
 # def return1():
 #     json_data=json.loads(main('ipx-292'))

proxy.ini

@@ -2,5 +2,5 @@
 proxy=127.0.0.1:1080
 
 [Name_Rule]
-location_rule='JAV_output/'+actor+'/'+'['+number+']-'+title
-naming_rule=number
+location_rule='JAV_output/'+actor+'/'+number+'-'+title
+naming_rule=number+'-'+title

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "0.10.3",
-	"version_show":"Beta 10.3",
+	"version": "0.10.4",
+	"version_show":"Beta 10.4",
 	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
 }