Update README.md

AV_Data_Capture.py

@@ -14,7 +14,7 @@ os.chdir(os.getcwd())
 
 # ============global var===========
 
-version='1.2'
+version='1.3'
 
 config = ConfigParser()
 config.read(config_file, encoding='UTF-8')
@@ -69,9 +69,9 @@ def lists_from_test(custom_nuber): #电影列表
     a.append(custom_nuber)
     return a
 def CEF(path):
+    try:
         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:
@@ -83,30 +83,27 @@ def rreplace(self, old, new, *max):
         count = max[0]
     return new.join(self.rsplit(old, count))
 def getNumber(filepath):
+    filepath = filepath.replace('.\\','')
     try:  # 普通提取番号 主要处理包含减号-的番号
+        filepath = filepath.replace("_", "-")
+        filepath.strip('22-sht.me').strip('-HD').strip('-hd')
+        filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath))  # 去除文件名中时间
         try:
-            filepath1 = filepath.replace("_", "-")
-            filepath1.strip('22-sht.me').strip('-HD').strip('-hd')
-            filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath1))  # 去除文件名中时间
             file_number = re.search('\w+-\d+', filename).group()
-            return file_number
+        except:  # 提取类似mkbd-s120番号
-        except:
+            file_number = re.search('\w+-\w+\d+', filename).group()
-            filepath1 = filepath.replace("_", "-")
-            filepath1.strip('22-sht.me').strip('-HD').strip('-hd')
-            filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath1))  # 去除文件名中时间
-            file_number = re.search('\w+-\w+', filename).group()
         return file_number
     except:  # 提取不含减号-的番号
         try:
-            filename1 = str(re.sub("ts6\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
+            filename = str(re.sub("ts6\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
-            filename0 = str(re.sub(".*?\.com-\d+", "", filename1)).strip('_')
+            filename = str(re.sub(".*?\.com-\d+", "", filename)).replace('_', '')
-            file_number = str(re.search('\w+\d{4}', filename0).group(0))
+            file_number = str(re.search('\w+\d{4}', filename).group(0))
             return file_number
         except:  # 提取无减号番号
-            filename1 = str(re.sub("ts6\d", "", filepath))  # 去除ts64/265
+            filename = str(re.sub("ts6\d", "", filepath))  # 去除ts64/265
-            filename0 = str(re.sub(".*?\.com-\d+", "", filename1))
+            filename = str(re.sub(".*?\.com-\d+", "", filename))
-            file_number2 = str(re.match('\w+', filename0).group())
+            file_number = str(re.match('\w+', filename).group())
-            file_number = str(file_number2.replace(re.match("^[A-Za-z]+", file_number2).group(),re.match("^[A-Za-z]+", file_number2).group() + '-'))
+            file_number = str(file_number.replace(re.match("^[A-Za-z]+", file_number).group(),re.match("^[A-Za-z]+", file_number).group() + '-'))
             return file_number
 
 def RunCore():

README.md

@@ -30,10 +30,11 @@
 * [写在后面](#9写在后面)
 
 # 免责声明
-1.本软件仅供**技术交流，学术交流**使用，本项目旨在学习 Python3<br>
+* 本软件仅供**技术交流，学术交流**使用，本项目旨在学习 Python3<br>
-2.本软件禁止用于任何非法用途<br>
+* 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>
+* 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.不可使用于商业和个人其他意图<br>
+* 不可使用于商业和个人其他意图<br>
+* 使用该软件前，请自觉遵守当地法律法规
 
 # 注意
 **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>
@@ -163,12 +164,18 @@ config.ini
 可选择emby, plex<br>
 如果是PLEX，请安装插件：```XBMCnfoMoviesImporter```
 
+---
+#### 调试模式
+>[debug_mode]<br>switch=1<br>
+
+如要开启调试模式，请手动输入以上代码到```config.ini```中，开启后可在抓取中显示影片元数据
+
 ---
 #### 抓取目录选择
 >[directory_capture]<br>
 >directory=<br>
 如果directory后面为空，则抓取和程序同一目录下的影片，设置为``` * ```可抓取软件所在目录下的所有子目录中的影片
-## 3.(可选)设置自定义目录和影片重命名规则
+### 3.(可选)设置自定义目录和影片重命名规则
 >[Name_Rule]<br>
 >location_rule=actor+'/'+number<br>
 >naming_rule=number+'-'+title<br>
@@ -196,10 +203,10 @@ config.ini
 目录结构规则：默认 ```location_rule=actor+'/'+number```<br> **不推荐修改时在这里添加title**，有时title过长，因为Windows API问题，抓取数据时新建文件夹容易出错。<br>
 影片命名规则：默认 ```naming_rule=number+'-'+title```<br> **在EMBY,KODI等本地媒体库显示的标题，不影响目录结构下影片文件的命名**，依旧是 番号+后缀。
 
----
 ### 更新开关
 >[update]<br>update_check=1<br>
 1为开，0为关
+
 ## 4.建议把软件拷贝和电影的统一目录下
 如果```config.ini```中```directory=```后面为空的情况下
 ## 5.运行 ```AV_Data_capture.py/.exe```

core.py

@@ -96,6 +96,7 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     global website
     global actor_photo
     global cover_small
+    global json_data
 
     global naming_rule
     global location_rule
@@ -115,8 +116,7 @@ def getDataFromJSON(file_number): #从JSON返回元数据
             json_data = json.loads(javdb.main(file_number))
     # ==
     elif 'fc2' in file_number or 'FC2' in file_number:
-        json_data = json.loads(fc2fans_club.main(
+        json_data = json.loads(fc2fans_club.main(file_number))
-            file_number))
     # ==
     elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
         json_data = json.loads(avsox.main(file_number))
@@ -163,23 +163,14 @@ def getDataFromJSON(file_number): #从JSON返回元数据
 
 
     # ====================处理异常字符====================== #\/:*?"<>|
-    if '\\' in title:
     title = title.replace('\\', '')
-    elif r'/' in title:
+    title = title.replace('/', '')
-        title=title.replace(r'/', '')
-    elif ':' in title:
     title = title.replace(':', '')
-    elif '*' in title:
     title = title.replace('*', '')
-    elif '?' in title:
     title = title.replace('?', '')
-    elif '"' in title:
     title = title.replace('"', '')
-    elif '<' in title:
     title = title.replace('<', '')
-    elif '>' in title:
     title = title.replace('>', '')
-    elif '|' in title:
     title = title.replace('|', '')
     # ====================处理异常字符 END================== #\/:*?"<>|
 
@@ -205,9 +196,8 @@ def smallCoverCheck():
 def creatFolder(): #创建文件夹
     global actor
     global path
-    if len(actor) > 240:                    #新建成功输出文件夹
+    if len(os.getcwd()+path) > 240:                    #新建成功输出文件夹
         path = success_folder+'/'+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
-        #print(path)
     else:
         path = success_folder+'/'+location_rule
         #print(path)
@@ -286,10 +276,6 @@ def imageDownload(filepath): #封面是否下载成功，否则移动到failed
         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)
@@ -437,15 +423,8 @@ def pasteFileToFolder(filepath, path): #文件路径，番号，后缀，要移
         print('[-]File Exists! Please check your movie!')
         print('[-]move to the root folder of the program.')
         os._exit(0)
-def pasteFileToFolder_mode2(filepath, path): #文件路径，番号，后缀，要移动至的位置
+    except PermissionError:
-    global houzhui
+        print('[-]Error! Please run as administrator!')
-    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|avi|rmvb|wmv|mov|mp4|mkv|flv|ts)$', filepath).group())
-    try:
-        os.rename(filepath, path + houzhui)
-        print('[+]Movie ' + number + ' move to target folder Finished!')
-    except:
-        print('[-]File Exists! Please check your movie!')
-        print('[-]move to the root folder of the program.')
         os._exit(0)
 def renameJpgToBackdrop_copy():
     if option == 'plex':
@@ -453,7 +432,6 @@ def renameJpgToBackdrop_copy():
         shutil.copy(path + '/poster.png', path + '/thumb.png')
     if option == 'emby':
         shutil.copy(path + '/' + number + '.jpg', path + '/Backdrop.jpg')
-
 def renameBackdropToJpg_copy():
     if option == 'plex':
         shutil.copy(path + '/fanart.jpg', path + '/Backdrop.jpg')
@@ -468,6 +446,20 @@ def get_part(filepath):
     except:
         print("[-]failed!Please rename the filename again!")
         moveFailedFolder()
+def debug_mode():
+    try:
+        if config['debug_mode']['switch'] == '1':
+            print('[+] ---Debug info---')
+            for i, v in json_data.items():
+                if i == 'outline':
+                    print('[+] -', i, ':', len(v), 'characters')
+                    continue
+                if i == 'actor_photo' or i == 'year':
+                    continue
+                print('[+] -', i, ':', v)
+            print('[+] ---Debug info---')
+    except:
+        aaa=''
 if __name__ == '__main__':
     filepath=argparse_get_file()[0] #影片的路径
 
@@ -488,14 +480,15 @@ if __name__ == '__main__':
         number = argparse_get_file()[1]
     CreatFailedFolder()
     getDataFromJSON(number)  # 定义番号
+    debug_mode()
     creatFolder()  # 创建文件夹
     if program_mode == '1':
         if part == '-CD1' or multi_part == 0:
+            smallCoverCheck()
             imageDownload(filepath)  # creatFoder会返回番号路径
             if multi_part == 1:
                 number += part
             PrintFiles(filepath)  # 打印文件
-            smallCoverCheck()
             cutImage()  # 裁剪图
             renameJpgToBackdrop_copy()
         else:
@@ -503,4 +496,4 @@ if __name__ == '__main__':
             renameBackdropToJpg_copy()
         pasteFileToFolder(filepath, path)  # 移动文件
     elif program_mode == '2':
-        pasteFileToFolder_mode2(filepath, path)  # 移动文件
+        pasteFileToFolder(filepath, path)  # 移动文件

fc2fans_club.py

@@ -4,10 +4,8 @@ import json
 import ADC_function
 
 def getTitle(htmlcode): #获取厂商
-    #print(htmlcode)
     html = etree.fromstring(htmlcode,etree.HTMLParser())
     result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/h2/text()')).strip(" ['']")
-    #print(result2)
     return result
 def getActor(htmlcode):
     try:
@@ -26,21 +24,14 @@ def getStudio(htmlcode): #获取厂商
 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(" ['']")
-    #print(result)
     return result
 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(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(" ['']")
-    # if result == '':
-    #     html = etree.fromstring(htmlcode, etree.HTMLParser())
-    #     result2 = str(html.xpath('//*[@id="slider"]/ul[1]/li[1]/img/@src')).strip(" ['']")
-    #     return result2
     return 'http:' + result
 def getOutline(htmlcode2):     #获取番号 #
     html = etree.fromstring(htmlcode2, etree.HTMLParser())
@@ -58,7 +49,7 @@ def getYear(release):
         return ''
 
 def main(number):
-    number=number.replace('PPV','').replace('ppv','').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-')
+    number=number.replace('PPV','').replace('ppv','').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').replace('fc2ppv-','').replace('FC2PPV-','')
     htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+str(number).lstrip("FC2-").lstrip("fc2-").lstrip("fc2_").lstrip("fc2-")+'')
     #htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
     dic = {

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "1.2",
+	"version": "1.3",
-	"version_show":"Beta 1.2",
+	"version_show":"1.3",
 	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
 }