0.3.2 Beta 完善错误提示

This is readms.md's images folder

AV_Data_Capture.py

@@ -2,12 +2,44 @@ import glob
 import os
 import time
 
-#a=glob.glob(os.getcwd()+r"\*.py")
+def movie_lists():
-a=glob.glob(os.getcwd()+r"\*\**\*.mp4")
+    #MP4
-b=glob.glob(os.getcwd()+r"\*.mp4")
+    a2 = glob.glob(os.getcwd() + r"\*.mp4")
-for i in b:
+    # AVI
-    a.append(i)
+    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())
+    total = a2+b2+c2+d2+e2+f2+g2
-for i in a:
+    return total
-    os.system('python core.py'+' "'+i+'"')
+
+def lists_from_test(custom_nuber):
+    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=''
+
+if __name__ =='__main__':
+    os.chdir(os.getcwd())
+    for i in movie_lists():
+        os.system('python core.py' + ' "' + i + '"')
+    print("[!]Cleaning empty folders")
+    CEF('JAV_output')
+    print("[+]All finished!!!")
+    time.sleep(3)

README.md

@@ -1,14 +1,27 @@
-# 日本AV元数据抓取工具  
+# 日本AV元数据抓取工具  （刮削器）
 
-## 关于本软件
+## 关于本软件 （~路star谢谢）
 
 目前，我下的AV越来越多，也意味着AV要集中地管理，形成媒体库。现在有两款主流的AV元数据获取器，"EverAver"和"Javhelper"。前者的优点是元数据获取比较全，缺点是不能批量处理；后者优点是可以批量处理，但是元数据不够全。
 
-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 
-## 软件流程图   (下下一个为使用教程)
-![](flow_chart.jpg)
 
-## 如何使用 (如果使用release的程序可跳过第一步)
+**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
@@ -35,14 +48,22 @@ pip install pillow
 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
 
-![](readme1.PNG)
+![](readme/readme1.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**
+
+![](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。
+
+![](readme/readme2.PNG)
+![](readme/readme3.PNG)
+![](readme/readme4.PNG)
+
 
-![](readme2.PNG)
-![](readme3.PNG)
-![](readme4.PNG)
 

core.py

@@ -9,74 +9,72 @@ from bs4 import BeautifulSoup#need install
 from PIL import Image#need install
 import time
 
-def get_html(url):
+#=====================爬虫核心部分==========================
+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),proxies={"http": "http://127.0.0.1:2334","https": "https://127.0.0.1:2334"},timeout=5,headers=headers).text
+    getweb = requests.get(str(url),timeout=5,headers=headers).text
     try:
         return getweb
-    except Exception as e:
+    except:
-        print(e)
+        print("[-]Connect Failed! Please check your Proxy.")
-    except IOError as e1:
+
-        print(e1)
+def getTitle(htmlcode):  #获取标题
-#================================================
-def getTitle(htmlcode):
     doc = pq(htmlcode)
     title=str(doc('div.container h3').text()).replace(' ','-')
     return title
-def getStudio(htmlcode):
+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):
+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):
+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):
+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):
+def getRuntime(htmlcode): #获取分钟
     soup = BeautifulSoup(htmlcode, 'lxml')
     a = soup.find(text=re.compile('分鐘'))
     return a
-def getActor(htmlcode):
+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):
+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):
+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):
+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
-    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("[-]Error:"+str(e))
         print("[-]Movie not found in Javbus.com!")
         print("[*]=====================================")
         return "failed"
@@ -85,8 +83,7 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
         print("[-]Download Failed2!")
         time.sleep(3)
         os._exit(0)
-
+def PrintFiles(html,path,number):
-def PrintFiles(path):
     try:
         if not os.path.exists(path):
             os.makedirs(path)
@@ -97,8 +94,8 @@ def PrintFiles(path):
             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("  <outline>"+getOutline(get_html_dww(number))+"</outline>", file=code)
-            print("  <plot>"+getOutline(html_outline)+"</plot>", 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)
@@ -122,65 +119,81 @@ def PrintFiles(path):
     except Exception as e1:
         print(e1)
         print("[-]Write Failed!")
-#================================================
+
-if __name__ == '__main__':
+#=====================本地文件处理===========================
-    #命令行处理
+
+
+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)) #\[\d{4}(\-|\/|.)\d{1,2}\1\d{1,2}\]
+    return args.file
-    #去除文件名中日期
+def getNumberFromFilename(filepath):
-    #print(filename)
+    filename = str(os.path.basename(filepath)) #电影文件名
-    deldate=str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ","",filename))
+    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)
-    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
 
-
+    print("[!]Making Data for ["+filename+"]")
-    if not os.path.exists('failed/'):
+    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/'):
+                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)
+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):
+    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':
+    if len(getActor(html)) > 240:    #新建成功输出文件夹
-            shutil.move(filepath, 'failed/')
+        path = 'JAV_output' + '/' + '超多人' + '/' + number #path为影片+元数据所在目录
-            time.sleep(3)
-            os._exit(0)
     else:
-        if DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path) == 'failed':
+        path = 'JAV_output' + '/' + getActor(html) + '/' + number
-            shutil.move(filepath, 'failed/')
+    if not os.path.exists(path):
-            os._exit(0)
+        os.makedirs(path)
-        DownloadFileWithFilename(getCover(html), getNum(html) + '.jpg', path)
+    path = str(os.getcwd())+'/'+path
-        print('[+]Downloaded!', path +'/'+getNum(html)+'.jpg')
+def imageDownload(htmlcode,filepath,number): #封面是否下载成功，否则移动到failed
-    #切割图片做封面
+    if DownloadFileWithFilename(getCover(htmlcode),number + '.jpg', path) == 'failed':
+        shutil.move(filepath, 'failed/')
+        os._exit(0)
+    DownloadFileWithFilename(getCover(htmlcode), number + '.jpg', path)
+    print('[+]Image Downloaded!', path +'/'+number+'.jpg')
+def cutImage(number):
     try:
-        img = Image.open(path + '/' + getNum(html) + '.jpg')
+        img = Image.open(path + '/' + number + '.jpg')
-        img2 = img.crop((421, 0, 800, 538))
+        imgSize=img.size
-        img2.save(path + '/' + getNum(html) + '.png')
+        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
+def pasteFileToFolder(filepath, number, 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)
+if __name__ == '__main__':
-    print('[!]Finished!')
+    filepath=argparse_get_file() #影片的路径
-    time.sleep(3)
+    number=getNumberFromFilename(filepath) #定义番号
+    htmlcode=get_html_javbus(number) #获取的HTML代码
+    creatFolder(htmlcode,number) #创建文件夹
+    imageDownload(htmlcode,filepath,number) #creatFoder会返回番号路径
+    PrintFiles(htmlcode, path,number)#打印文件
+    cutImage(number) #裁剪图
+    pasteFileToFolder(filepath,number,path) #移动文件

readme/This is readms.md's images folder

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