Update README.md

AV_Data_Capture-1.1（支持分集）

ADC_function.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 
 import requests
@@ -18,18 +19,13 @@ if os.path.exists(config_file):
 else:
     print('[+]config.ini: not found, creating...')
     with open("config.ini", "wt", encoding='UTF-8') as code:
-        print("[common]", file=code)
-        print("main_mode=1", file=code)
-        print("failed_output_folder=failed", file=code)
-        print("success_output_folder=JAV_output", file=code)
-        print("", file=code)
         print("[proxy]",file=code)
         print("proxy=127.0.0.1:1080",file=code)
         print("timeout=10", file=code)
         print("retry=3", file=code)
         print("", file=code)
         print("[Name_Rule]", file=code)
-        print("location_rule=actor+'/'+number",file=code)
+        print("location_rule='JAV_output/'+actor+'/'+number",file=code)
         print("naming_rule=number+'-'+title",file=code)
         print("", file=code)
         print("[update]",file=code)
@@ -41,8 +37,10 @@ else:
         print("#plex only test!", file=code)
         print("", file=code)
         print("[directory_capture]", file=code)
+        print("switch=0", file=code)
         print("directory=", file=code)
         print("", file=code)
+        print("everyone switch:1=on, 0=off", file=code)
     time.sleep(2)
     print('[+]config.ini: created!')
     try:

AV_Data_Capture.py

@@ -14,7 +14,7 @@ os.chdir(os.getcwd())
 
 # ============global var===========
 
-version='1.1'
+version='1.3'
 
 config = ConfigParser()
 config.read(config_file, encoding='UTF-8')
@@ -36,36 +36,26 @@ def UpdateCheck():
     else:
         print('[+]Update Check disabled!')
 def movie_lists():
+    global exclude_directory_1
+    global exclude_directory_2
     directory = config['directory_capture']['directory']
-    mp4=[]
+    total=[]
-    avi=[]
+    file_type = ['mp4','avi','rmvb','wmv','mov','mkv','flv','ts']
-    rmvb=[]
+    exclude_directory_1 = config['common']['failed_output_folder']
-    wmv=[]
+    exclude_directory_2 = config['common']['success_output_folder']
-    mov=[]
-    mkv=[]
-    flv=[]
-    ts=[]
     if directory=='*':
+        remove_total = []
+        for o in file_type:
+            remove_total += glob.glob(r"./" + exclude_directory_1 + "/*." + o)
+            remove_total += glob.glob(r"./" + exclude_directory_2 + "/*." + o)
         for i in os.listdir(os.getcwd()):
-            mp4 += glob.glob(r"./" + i + "/*.mp4")
+            for a in file_type:
-            avi += glob.glob(r"./" + i + "/*.avi")
+                total += glob.glob(r"./" + i + "/*." + a)
-            rmvb += glob.glob(r"./" + i + "/*.rmvb")
+        for b in remove_total:
-            wmv += glob.glob(r"./" + i + "/*.wmv")
+            total.remove(b)
-            mov += glob.glob(r"./" + i + "/*.mov")
-            mkv += glob.glob(r"./" + i + "/*.mkv")
-            flv += glob.glob(r"./" + i + "/*.flv")
-            ts += glob.glob(r"./" + i + "/*.ts")
-        total = mp4 + avi + rmvb + wmv + mov + mkv + flv + ts
         return total
-    mp4 = glob.glob(r"./" + directory + "/*.mp4")
+    for a in file_type:
-    avi = glob.glob(r"./" + directory + "/*.avi")
+        total += glob.glob(r"./" + directory + "/*." + a)
-    rmvb = glob.glob(r"./" + directory + "/*.rmvb")
-    wmv = glob.glob(r"./" + directory + "/*.wmv")
-    mov = glob.glob(r"./" + directory + "/*.mov")
-    mkv = glob.glob(r"./" + directory + "/*.mkv")
-    flv = glob.glob(r"./" + directory + "/*.flv")
-    ts = glob.glob(r"./" + directory + "/*.ts")
-    total = mp4 + avi + rmvb + wmv + mov + mkv + flv + ts
     return total
 def CreatFailedFolder():
     if not os.path.exists('failed/'):  # 新建failed文件夹
@@ -79,13 +69,13 @@ def lists_from_test(custom_nuber): #电影列表
     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
+    try:
-    for file in files:
+        files = os.listdir(path)  # 获取路径下的子文件(夹)列表
-        try: #试图删除空目录,非空目录删除会报错
+        for file in files:
             os.removedirs(path + '/' + file)  # 删除这个空文件夹
-            print('[+]Deleting empty folder',path + '/' + file)
+            print('[+]Deleting empty folder', path + '/' + file)
-        except:
+    except:
-            a=''
+        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)
@@ -93,30 +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("_", "-")
+        return file_number
-            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():
@@ -160,7 +147,7 @@ if __name__ =='__main__':
             shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
             continue
 
-
+    CEF(exclude_directory_1)
-    CEF('JAV_output')
+    CEF(exclude_directory_2)
     print("[+]All finished!!!")
     input("[+][+]Press enter key exit, you can check the error messge before you exit.\n[+][+]按回车键结束，你可以在结束之前查看和错误信息。")

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

@@ -18,14 +18,13 @@ import javbus
 import javdb
 #=========website========
 
+#初始化全局变量
 Config = ConfigParser()
 Config.read(config_file, encoding='UTF-8')
 try:
     option = ReadMediaWarehouse()
 except:
     print('[-]Config media_warehouse read failed!')
-
-#初始化全局变量
 title=''
 studio=''
 year=''
@@ -40,6 +39,8 @@ cover=''
 imagecut=''
 tag=[]
 cn_sub=''
+multi_part=0
+part=''
 path=''
 houzhui=''
 website=''
@@ -48,10 +49,11 @@ actor_photo={}
 cover_small=''
 naming_rule  =''#eval(config['Name_Rule']['naming_rule'])
 location_rule=''#eval(config['Name_Rule']['location_rule'])
-program_mode = Config['common']['main_mode']
+program_mode   = Config['common']['main_mode']
-failed_folder= Config['common']['failed_output_folder']
+failed_folder  = Config['common']['failed_output_folder']
-success_folder=Config['common']['success_output_folder']
+success_folder = Config['common']['success_output_folder']
 #=====================本地文件处理===========================
+
 def moveFailedFolder():
     global filepath
     print('[-]Move to Failed output folder')
@@ -94,41 +96,40 @@ 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
 
-
     # ================================================网站规则添加开始================================================
 
-    try:    # 添加 需要 正则表达式的规则
+    if re.match('^\d{5,}', file_number):
-        if re.search('^\d{5,}', file_number).group() in file_number:
+        json_data = json.loads(avsox.main(file_number))
-            json_data = json.loads(avsox.main(file_number))
+        if getDataState(json_data) == 0:  # 如果元数据获取失败，请求番号至其他网站抓取
-            if getDataState(json_data) == 0:    #如果元数据获取失败，请求番号至其他网站抓取
+            json_data = json.loads(javdb.main(file_number))
-                json_data = json.loads(javdb.main(file_number))
+    #==
-
+    elif re.match('\d+\D+', file_number):
-        elif re.search('\d+\D+', file_number).group() in file_number:
+        json_data = json.loads(siro.main(file_number))
-            json_data = json.loads(siro.main(file_number))
+        if getDataState(json_data) == 0:  # 如果元数据获取失败，请求番号至其他网站抓取
-            if getDataState(json_data) == 0:    #如果元数据获取失败，请求番号至其他网站抓取
-                json_data = json.loads(javbus.main(file_number))
-            elif getDataState(json_data) == 0:  #如果元数据获取失败，请求番号至其他网站抓取
-                json_data = json.loads(javdb.main(file_number))
-
-    except:  # 添加 无需 正则表达式的规则
-        if 'fc2' in file_number:
-            json_data = json.loads(fc2fans_club.main(file_number.strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-').strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-')))
-        elif 'FC2' in file_number:
-            json_data = json.loads(fc2fans_club.main(file_number.strip('FC2_').strip('FC2-').strip('ppv-').strip('PPV-').strip('fc2_').strip('fc2-').strip('ppv-').strip('PPV-')))
-        elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
-            json_data = json.loads(avsox.main(file_number))
-        elif 'siro' in file_number or 'SIRO' in file_number or 'Siro' in file_number:
-            json_data = json.loads(siro.main(file_number))
-        else:
             json_data = json.loads(javbus.main(file_number))
-            if getDataState(json_data) == 0:    #如果元数据获取失败，请求番号至其他网站抓取
+        elif getDataState(json_data) == 0:  # 如果元数据获取失败，请求番号至其他网站抓取
-                json_data = json.loads(avsox.main(file_number))
+            json_data = json.loads(javdb.main(file_number))
-            elif getDataState(json_data) == 0:  #如果元数据获取失败，请求番号至其他网站抓取
+    # ==
-                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(file_number))
+    # ==
+    elif 'HEYZO' in number or 'heyzo' in number or 'Heyzo' in number:
+        json_data = json.loads(avsox.main(file_number))
+    # ==
+    elif 'siro' in file_number or 'SIRO' in file_number or 'Siro' in file_number:
+        json_data = json.loads(siro.main(file_number))
+    # ==
+    else:
+        json_data = json.loads(javbus.main(file_number))
+        if getDataState(json_data) == 0:  # 如果元数据获取失败，请求番号至其他网站抓取
+            json_data = json.loads(avsox.main(file_number))
+        elif getDataState(json_data) == 0:  # 如果元数据获取失败，请求番号至其他网站抓取
+            json_data = json.loads(javdb.main(file_number))
 
     # ================================================网站规则添加结束================================================
 
@@ -145,9 +146,9 @@ def getDataFromJSON(file_number): #从JSON返回元数据
     try:
         cover_small = json_data['cover_small']
     except:
-        aaaaaaa=''
+        cover_small=''
     imagecut    =     json_data['imagecut']
-    tag         = str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',')  # 字符串转列表
+    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']
@@ -162,24 +163,15 @@ def getDataFromJSON(file_number): #从JSON返回元数据
 
 
     # ====================处理异常字符====================== #\/:*?"<>|
-    if '\\' in title:
+    title = title.replace('\\', '')
-        title=title.replace('\\', ' ')
+    title = title.replace('/', '')
-    elif r'/' in title:
+    title = title.replace(':', '')
-        title=title.replace(r'/', '')
+    title = title.replace('*', '')
-    elif ':' in title:
+    title = title.replace('?', '')
-        title=title.replace(':', '')
+    title = title.replace('"', '')
-    elif '*' in title:
+    title = title.replace('<', '')
-        title=title.replace('*', '')
+    title = title.replace('>', '')
-    elif '?' in title:
+    title = title.replace('|', '')
-        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================== #\/:*?"<>|
 
     naming_rule   = eval(config['Name_Rule']['naming_rule'])
@@ -204,9 +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)
@@ -272,17 +263,19 @@ def imageDownload(filepath): #封面是否下载成功，否则移动到failed
         if DownloadFileWithFilename(cover, number + '.jpg', path) == 'failed':
             moveFailedFolder()
         DownloadFileWithFilename(cover, number + '.jpg', path)
-        print('[+]Image Downloaded!', path + '/' + number + '.jpg')
+        if multi_part == 1:
+            old_name = os.path.join(path, number + '.jpg')
+            new_name = os.path.join(path, number + part + '.jpg')
+            os.rename(old_name, new_name)
+            print('[+]Image Downloaded!', path + '/' + number + part + '.jpg')
+        else:
+            print('[+]Image Downloaded!', path + '/' + number + '.jpg')
     elif option == 'plex':
         if DownloadFileWithFilename(cover, 'fanart.jpg', path) == 'failed':
             moveFailedFolder()
         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)
@@ -316,12 +309,12 @@ def PrintFiles(filepath):
                 if cn_sub == '1':
                     print("  <tag>中文字幕</tag>", file=code)
                 try:
-                    for i in tag:
+                    for i in str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(','):
                         print("  <tag>" + i + "</tag>", file=code)
                 except:
                     aaaaa = ''
                 try:
-                    for i in tag:
+                    for i in str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(','):
                         print("  <genre>" + i + "</genre>", file=code)
                 except:
                     aaaaaaaa = ''
@@ -430,15 +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':
@@ -446,10 +432,40 @@ 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')
+        shutil.copy(path + '/poster.png', path + '/thumb.png')
+    if option == 'emby':
+        shutil.copy(path + '/Backdrop.jpg', path + '/' + number + '.jpg')
+        print('[+]Image Downloaded!', path + '/' + number + '.jpg')
+def get_part(filepath):
+    try:
+        if re.search('-CD\d+', filepath):
+            return re.findall('-CD\d+', filepath)[0]
+    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
 
+    if '-CD' in filepath or '-cd' in filepath:
+        multi_part = 1
+    part = get_part(filepath)
     if '-c.' in filepath or '-C.' in filepath or '中文' in filepath or '字幕' in filepath:
         cn_sub='1'
 
@@ -464,13 +480,20 @@ 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':
-        imageDownload(filepath)  # creatFoder会返回番号路径
+        if part == '-CD1' or multi_part == 0:
-        PrintFiles(filepath)  # 打印文件
+            smallCoverCheck()
-        smallCoverCheck()
+            imageDownload(filepath)  # creatFoder会返回番号路径
-        cutImage()  # 裁剪图
+            if multi_part == 1:
+                number += part
+            PrintFiles(filepath)  # 打印文件
+            cutImage()  # 裁剪图
+            renameJpgToBackdrop_copy()
+        else:
+            number += part
+            renameBackdropToJpg_copy()
         pasteFileToFolder(filepath, path)  # 移动文件
-        renameJpgToBackdrop_copy()
     elif program_mode == '2':
-        pasteFileToFolder_mode2(filepath, path)  # 移动文件
+        pasteFileToFolder(filepath, path)  # 移动文件

fc2fans_club.py

@@ -4,51 +4,43 @@ 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(" ['']")
+    result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/h2/text()')).strip(" ['']")
-    result2 = str(re.sub('\D{2}2-\d+','',result)).replace(' ','',1)
+    return result
-    #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(" ['']")
+        result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[5]/a/text()')).strip(" ['']")
         return result
     except:
         return ''
 def getStudio(htmlcode): #获取厂商
-    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    try:
-    result = str(html.xpath('/html/body/div[2]/div/div[1]/h5[3]/a[1]/text()')).strip(" ['']")
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
-    return result
+        result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[1]/div/div[2]/dl/dd[5]/a/text()')).strip(" ['']")
+        return result
+    except:
+        return ''
 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(htmlcode,number,htmlcode2): #获取厂商 #
+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 'http://fc2fans.club' +  result2
     return 'http:' + result
-def getOutline(htmlcode2,number):     #获取番号 #
+def getOutline(htmlcode2):     #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)
+    result = str(html.xpath('//*[@id="container"]/div[1]/div/article/section[4]/p/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip('  ').replace('。,',',')
     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()'))
+    result = html.xpath('//*[@id="container"]/div[1]/div/article/section[6]/ul/li/a/text()')
-    return result.strip(" ['']").replace("'",'').replace(' ','')
+    return result
 def getYear(release):
     try:
         result = re.search('\d{4}',release).group()
@@ -56,30 +48,28 @@ def getYear(release):
     except:
         return ''
 
-def main(number2):
+def main(number):
-    number=number2.replace('PPV','').replace('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-")+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
+    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')
+    #htmlcode = ADC_function.get_html('http://fc2fans.club/html/FC2-' + number + '.html')
     dic = {
-        'title':    getTitle(htmlcode),
+        'title':    getTitle(htmlcode2),
-        'studio':   getStudio(htmlcode),
+        'studio':   getStudio(htmlcode2),
-        'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
+        'year':     getYear(getRelease(htmlcode2)),
-        'outline':  getOutline(htmlcode,number),
+        'outline':  getOutline(htmlcode2),
-        'runtime':  getYear(getRelease(htmlcode)),
+        'runtime':  getYear(getRelease(htmlcode2)),
-        'director': getStudio(htmlcode),
+        'director': getStudio(htmlcode2),
-        'actor':    getActor(htmlcode),
+        'actor':    getStudio(htmlcode2),
-        'release':  getRelease(number),
+        'release':  getRelease(htmlcode2),
         'number':  'FC2-'+number,
-        'cover':    getCover(htmlcode,number,htmlcode2),
+        'cover':    getCover(htmlcode2),
         'imagecut': 0,
-        'tag':      getTag(htmlcode),
+        'tag':      getTag(htmlcode2),
         'actor_photo':'',
-        'website':  'http://fc2fans.club/html/FC2-' + number + '.html',
+        'website':  'http://adult.contents.fc2.com/article_search.php?id=' + number,
         'source': 'fc2fans_club.py',
     }
-    #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('1051725'))
+#print(main('1145465'))

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "1.1",
+	"version": "1.3",
-	"version_show":"Beta 1.1",
+	"version_show":"1.3",
 	"download": "https://github.com/wenead99/AV_Data_Capture/releases"
 }