优化正则等，修改逻辑，避免被覆盖

to learn goupby

learn pandas groupby

groupby

learn pandas groupby

优化正则提取番号和集数

待理解下载图片逻辑

还有剪裁+背景图逻辑

修改所有config[

将整理生成nfo的代码

可缓存番号信息和缩略图和海报

可以识别番号后集数和尾部集数,赞不能分辨-C中文字幕片

改正一个错误

嵌套字典存储数据

整理函数

修正匹配时间正则

pipenv 添加依赖

修改优先取三位数字的规则：heyzo四位数除外

添加了依赖 和 有番号的优化

修改了啥 我也记不得了

.gitattributes

@@ -0,0 +1 @@
+*.py text=auto eol=lf

.gitignore

@@ -1,3 +1,4 @@
+*.DS_Store
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

.idea/.gitignore

@@ -0,0 +1,2 @@
+# Default ignored files
+/workspace.xml

.idea/AV_Data_Capture.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.8 (AV_Data_Capture)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/dictionaries/tanpengsccd.xml

@@ -0,0 +1,19 @@
+<component name="ProjectDictionaryState">
+  <dictionary name="tanpengsccd">
+    <words>
+      <w>avsox</w>
+      <w>emby</w>
+      <w>fanart</w>
+      <w>fanza</w>
+      <w>javbus</w>
+      <w>javdb</w>
+      <w>jellyfin</w>
+      <w>khtml</w>
+      <w>kodi</w>
+      <w>mgstage</w>
+      <w>plex</w>
+      <w>pondo</w>
+      <w>rmvb</w>
+    </words>
+  </dictionary>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="JavaScriptSettings">
+    <option name="languageLevel" value="ES6" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (AV_Data_Capture)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/AV_Data_Capture.iml" filepath="$PROJECT_DIR$/.idea/AV_Data_Capture.iml" />
+    </modules>
+  </component>
+</project>

.idea/other.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="PySciProjectComponent">
+    <option name="PY_SCI_VIEW_SUGGESTED" value="true" />
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

ADC_function.py

@@ -1,115 +1,127 @@
-#!/usr/bin/env python3
+#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
-
+
-import requests
+import requests
-from configparser import ConfigParser
+from configparser import ConfigParser
-import os
+import os
-import re
+import re
-import time
+import time
-import sys
+import sys
-from lxml import etree
+from lxml import etree
-import sys
+import sys
-import io
+import io
-# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
+from ConfigApp import ConfigApp
-# sys.setdefaultencoding('utf-8')
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
-
+# sys.setdefaultencoding('utf-8')
-config_file='config.ini'
+
-config = ConfigParser()
+# config_file='config.ini'
-
+# config = ConfigParser()
-if os.path.exists(config_file):
+
-    try:
+# if os.path.exists(config_file):
-        config.read(config_file, encoding='UTF-8')
+#     try:
-    except:
+#         config.read(config_file, encoding='UTF-8')
-        print('[-]Config.ini read failed! Please use the offical file!')
+#     except:
-else:
+#         print('[-]Config.ini read failed! Please use the offical file!')
-    print('[+]config.ini: not found, creating...',end='')
+# else:
-    with open("config.ini", "wt", encoding='UTF-8') as code:
+#     print('[+]config.ini: not found, creating...',end='')
-        print("[common]", file=code)
+#     with open("config.ini", "wt", encoding='UTF-8') as code:
-        print("main_mode = 1", file=code)
+#         print("[common]", file=code)
-        print("failed_output_folder = failed", file=code)
+#         print("main_mode = 1", file=code)
-        print("success_output_folder = JAV_output", file=code)
+#         print("failed_output_folder = failed", file=code)
-        print("", file=code)
+#         print("success_output_folder = JAV_output", file=code)
-        print("[proxy]",file=code)
+#         print("", file=code)
-        print("proxy=127.0.0.1:1081",file=code)
+#         print("[proxy]",file=code)
-        print("timeout=10", file=code)
+#         print("proxy=127.0.0.1:1081",file=code)
-        print("retry=3", file=code)
+#         print("timeout=10", file=code)
-        print("", file=code)
+#         print("retry=3", file=code)
-        print("[Name_Rule]", file=code)
+#         print("", file=code)
-        print("location_rule=actor+'/'+number",file=code)
+#         print("[Name_Rule]", file=code)
-        print("naming_rule=number+'-'+title",file=code)
+#         print("location_rule=actor+'/'+number",file=code)
-        print("", file=code)
+#         print("naming_rule=number+'-'+title",file=code)
-        print("[update]",file=code)
+#         print("", file=code)
-        print("update_check=1",file=code)
+#         print("[update]",file=code)
-        print("", file=code)
+#         print("update_check=1",file=code)
-        print("[media]", file=code)
+#         print("", file=code)
-        print("media_warehouse=emby", file=code)
+#         print("[media]", file=code)
-        print("#emby plex kodi", file=code)
+#         print("media_warehouse=emby", file=code)
-        print("", file=code)
+#         print("#emby plex kodi", file=code)
-        print("[escape]", file=code)
+#         print("", file=code)
-        print("literals=\\", file=code)
+#         print("[escape]", file=code)
-        print("", file=code)
+#         print("literals=\\", file=code)
-        print("[movie_location]", file=code)
+#         print("", file=code)
-        print("path=", file=code)
+#         print("[movie_location]", file=code)
-        print("", file=code)
+#         print("path=", file=code)
-        print('.',end='')
+#         print("", file=code)
-    time.sleep(2)
+#         print('.',end='')
-    print('.')
+#     time.sleep(2)
-    print('[+]config.ini: created!')
+#     print('.')
-    print('[+]Please restart the program!')
+#     print('[+]config.ini: created!')
-    time.sleep(4)
+#     print('[+]Please restart the program!')
-    os._exit(0)
+#     time.sleep(4)
-    try:
+#     os._exit(0)
-        config.read(config_file, encoding='UTF-8')
+#     try:
-    except:
+#         config.read(config_file, encoding='UTF-8')
-        print('[-]Config.ini read failed! Please use the offical file!')
+#     except:
-
+#         print('[-]Config.ini read failed! Please use the offical file!')
-def getDataState(json_data):  # 元数据获取失败检测
+
-    if json_data['title'] == '' or json_data['title'] == 'None' or json_data['title'] == 'null':
+config = ConfigApp()
-        return 0
+
-    else:
+
-        return 1
+def get_network_settings():
-
+    try:
-def ReadMediaWarehouse():
+        proxy = config.proxy
-    return config['media']['media_warehouse']
+        timeout = int(config.timeout)
-
+        retry_count = int(config.retry)
-def UpdateCheckSwitch():
+        assert timeout > 0
-    check=str(config['update']['update_check'])
+        assert retry_count > 0
-    if check == '1':
+    except:
-        return '1'
+        raise ValueError("[-]Proxy config error! Please check the config.")
-    elif check == '0':
+    return proxy, timeout, retry_count
-        return '0'
+
-    elif check == '':
+def getDataState(json_data):  # 元数据获取失败检测
-        return '0'
+    if json_data['title'] == '' or json_data['title'] == 'None' or json_data['title'] == 'null':
-
+        return 0
-def getXpathSingle(htmlcode,xpath):
+    else:
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+        return 1
-    result1 = str(html.xpath(xpath)).strip(" ['']")
+
-    return result1
+def ReadMediaWarehouse():
-
+    return config.media_server
-def get_html(url,cookies = None):#网页请求核心
+
-    try:
+def UpdateCheckSwitch():
-        proxy = config['proxy']['proxy']
+    check=str(config.update_check)
-        timeout = int(config['proxy']['timeout'])
+    if check == '1':
-        retry_count = int(config['proxy']['retry'])
+        return '1'
-    except:
+    elif check == '0':
-        print('[-]Proxy config error! Please check the config.')
+        return '0'
-    i = 0
+    elif check == '':
-    while i < retry_count:
+        return '0'
-        try:
+
-            if not str(config['proxy']['proxy']) == '':
+def getXpathSingle(htmlcode,xpath):
-                proxies = {"http": "http://" + proxy,"https": "https://" + proxy}
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-                headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
+    result1 = str(html.xpath(xpath)).strip(" ['']")
-                getweb = requests.get(str(url), headers=headers, timeout=timeout,proxies=proxies, cookies=cookies)
+    return result1
-                getweb.encoding = 'utf-8'
+
-                return getweb.text
+def get_html(url,cookies = None):#网页请求核心
-            else:
+    proxy, timeout, retry_count = get_network_settings()
-                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'}
+    i = 0
-                getweb = requests.get(str(url), headers=headers, timeout=timeout, cookies=cookies)
+    print(url)
-                getweb.encoding = 'utf-8'
+    while i < retry_count:
-                return getweb.text
+        try:
-        except:
+            if not proxy == '':
-            i += 1
+                proxies = {"http": proxy, "https": proxy}
-            print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+                headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3100.0 Safari/537.36'}
-    print('[-]Connect Failed! Please check your Proxy or Network!')
+                getweb = requests.get(str(url), headers=headers, timeout=timeout, proxies=proxies, cookies=cookies)
-
+                getweb.encoding = 'utf-8'
-
+                return getweb.text
+            else:
+                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), headers=headers, timeout=timeout, cookies=cookies)
+                getweb.encoding = 'utf-8'
+                return getweb.text
+        except Exception as e:
+            print(e)
+            i += 1
+            print('[-]Connect retry '+str(i)+'/'+str(retry_count))
+    print('[-]Connect Failed! Please check your Proxy or Network!')
+
+

AV_Data_Capture.py

@@ -1,164 +1,416 @@
-#!/usr/bin/env python3
+#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
-
+
-import glob
+import glob
-import os
+import os
-import time
+import time
-import re
+import fuckit
-from ADC_function import *
+from tenacity import retry, stop_after_delay, wait_fixed
-import json
+import json
-import shutil
+import shutil
-import fnmatch
+import itertools
-from configparser import ConfigParser
+import argparse
-os.chdir(os.getcwd())
+from pathlib import Path
-
+
-# ============global var===========
+from core import *
-
+from ConfigApp import ConfigApp
-version='2.1'
+from PathNameProcessor import PathNameProcessor
-
+
-config = ConfigParser()
+# TODO 封装聚合解耦：CORE
-config.read(config_file, encoding='UTF-8')
+# TODO （学习）统一依赖管理工具
-
+# TODO 不同媒体服务器尽量兼容统一一种元数据 如nfo 海报等（emby，jellyfin，plex）
-Platform = sys.platform
+# TODO 字幕整理功能 文件夹中读取所有字幕 并提番号放入对应缓存文件夹中TEMP
-
+
-# ==========global var end=========
+config = ConfigApp()
-
+
-def moveMovies():
+
-    movieFiles = []
+def safe_list_get(list_in, idx, default=None):
-    fromPath = config['movie_location']['path']
+    """
-    if Platform == 'win32':
+    数组安全取值
-        movieFormat = ["avi", "rmvb", "wmv", "mov", "mp4", "mkv", "flv", "ts"]
+    :param list_in:
-    else:
+    :param idx:
-        movieFormat = ["AVI", "RMVB", "WMV", "MOV", "MP4", "MKV", "FLV", "TS","avi", "rmvb", "wmv", "mov", "mp4", "mkv", "flv", "ts"]
+    :param default:
-    for fm in movieFormat:
+    :return:
-        movieFiles = movieFiles + [os.path.join(dirpath, f)
+    """
-            for dirpath, dirnames, files in os.walk(fromPath)
+    try:
-            for f in fnmatch.filter(files, '*.' + fm)]
+        return list_in[idx]
-    for movie in movieFiles:
+    except IndexError:
-        print("Move file " + movie)
+        return default
-        shutil.move(movie, os.path.curdir)
+
-def UpdateCheck():
+
-    if UpdateCheckSwitch() == '1':
+def UpdateCheck(version):
-        html2 = get_html('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/update_check.json')
+    if UpdateCheckSwitch() == '1':
-        html = json.loads(str(html2))
+        html2 = get_html('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/update_check.json')
-
+        html = json.loads(str(html2))
-        if not version == html['version']:
+
-            print('[*]                  * New update ' + html['version'] + ' *')
+        if not version == html['version']:
-            print('[*]                     ↓ Download ↓')
+            print('[*]                  * New update ' + html['version'] + ' *')
-            print('[*] ' + html['download'])
+            print('[*]                     ↓ Download ↓')
-            print('[*]======================================================')
+            print('[*] ' + html['download'])
-    else:
+            print('[*]======================================================')
-        print('[+]Update Check disabled!')
+    else:
-def movie_lists():
+        print('[+]Update Check disabled!')
-    global exclude_directory_1
+
-    global exclude_directory_2
+
-    total=[]
+def argparse_get_file():
-    file_type = ['mp4','avi','rmvb','wmv','mov','mkv','flv','ts']
+    parser = argparse.ArgumentParser()
-    exclude_directory_1 = config['common']['failed_output_folder']
+    parser.add_argument("file", default='', nargs='?', help="Write the file path on here")
-    exclude_directory_2 = config['common']['success_output_folder']
+    args = parser.parse_args()
-    for a in file_type:
+    if args.file == '':
-        total += glob.glob(r"./*." + a)
+        return ''
-    return total
+    else:
-def CreatFailedFolder():
+        return args.file
-    if not os.path.exists('failed/'):  # 新建failed文件夹
+
-        try:
+
-            os.makedirs('failed/')
+def movie_lists(escape_folders):
-        except:
+    escape_folders = re.split('[,，]', escape_folders)
-            print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
+    total = []
-            os._exit(0)
+
-def lists_from_test(custom_nuber): #电影列表
+    for root, dirs, files in os.walk(config.search_folder):
-    a=[]
+        if root in escape_folders:
-    a.append(custom_nuber)
+            continue
-    return a
+        for file in files:
-def CEF(path):
+            if re.search(PathNameProcessor.pattern_of_file_name_suffixes, file, re.IGNORECASE):
-    try:
+                path = os.path.join(root, file)
-        files = os.listdir(path)  # 获取路径下的子文件(夹)列表
+                total.append(path)
-        for file in files:
+    return total
-            os.removedirs(path + '/' + file)  # 删除这个空文件夹
+
-            print('[+]Deleting empty folder', path + '/' + file)
+
-    except:
+# def CEF(path):
-        a=''
+#     try:
-def rreplace(self, old, new, *max):
+#         files = os.listdir(path)  # 获取路径下的子文件(夹)列表
-#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
+#         for file in files:
-    count = len(self)
+#             os.removedirs(path + '/' + file)  # 删除这个空文件夹
-    if max and str(max[0]).isdigit():
+#             print('[+]Deleting empty folder', path + '/' + file)
-        count = max[0]
+#     except:
-    return new.join(self.rsplit(old, count))
+#         a = ''
-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("_", "-")
+def get_numbers(paths):
-        filepath.strip('22-sht.me').strip('-HD').strip('-hd')
+    """提取对应路径的番号+集数"""
-        filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath))  # 去除文件名中时间
+
-        if 'FC2' or 'fc2' in filename:
+    def get_number(filepath, absolute_path=False):
-            filename=filename.replace('-PPV','').replace('PPV-','')
+        """
-        try:
+        获取番号，集数
-            file_number = re.search('\w+-\d+', filename).group()
+        :param filepath:
-        except:  # 提取类似mkbd-s120番号
+        :param absolute_path:
-            file_number = re.search('\w+-\w+\d+', filename).group()
+        :return:
-        return file_number
+        """
-    except:  # 提取不含减号-的番号
+        name = filepath.upper()  # 转大写
-        try:
+        if absolute_path:
-            filename = str(re.sub("ts6\d", "", filepath)).strip('Tokyo-hot').strip('tokyo-hot')
+            name = name.replace('\\', '/')
-            filename = str(re.sub(".*?\.com-\d+", "", filename)).replace('_', '')
+        # 移除干扰字段
-            file_number = str(re.search('\w+\d{4}', filename).group(0))
+        name = PathNameProcessor.remove_distractions(name)
-            return file_number
+        # 抽取 文件路径中可能存在的尾部集数，和抽取尾部集数的后的文件路径
-        except:  # 提取无减号番号
+        suffix_episode, name = PathNameProcessor.extract_suffix_episode(name)
-            filename = str(re.sub("ts6\d", "", filepath))  # 去除ts64/265
+        # 抽取 文件路径中可能存在的 番号后跟随的集数 和 处理后番号
-            filename = str(re.sub(".*?\.com-\d+", "", filename))
+        episode_behind_code, code_number = PathNameProcessor.extract_code(name)
-            file_number = str(re.match('\w+', filename).group())
+        # 无番号 则设置空字符
-            file_number = str(file_number.replace(re.match("^[A-Za-z]+", file_number).group(),re.match("^[A-Za-z]+", file_number).group() + '-'))
+        code_number = code_number if code_number else ''
-            return file_number
+        # 优先取尾部集数，无则取番号后的集数（几率低），都无则为空字符
-
+        episode = suffix_episode if suffix_episode else episode_behind_code if episode_behind_code else ''
-def RunCore():
+
-    if Platform == 'win32':
+        return code_number, episode
-        if os.path.exists('core.py'):
+
-            os.system('python core.py' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从py文件启动（用于源码py）
+    maps = {}
-        elif os.path.exists('core.exe'):
+    for path in paths:
-            os.system('core.exe' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从exe启动（用于EXE版程序）
+        number, episode = get_number(path)
-        elif os.path.exists('core.py') and os.path.exists('core.exe'):
+        maps[path] = (number, episode)
-            os.system('python core.py' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从py文件启动（用于源码py）
+
-    else:
+    return maps
-        if os.path.exists('core.py'):
+
-            os.system('python3 core.py' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从py文件启动（用于源码py）
+
-        elif os.path.exists('core.exe'):
+def create_folder(paths):
-            os.system('core.exe' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从exe启动（用于EXE版程序）
+    for path_to_make in paths:
-        elif os.path.exists('core.py') and os.path.exists('core.exe'):
+        if path_to_make:
-            os.system('python3 core.py' + '   "' + i + '" --number "' + getNumber(i) + '"')  # 从py文件启动（用于源码py）
+            try:
-
+                os.makedirs(path_to_make)
-if __name__ =='__main__':
+            except FileExistsError as e:
-    print('[*]================== AV Data Capture ===================')
+                # name = f'{folder=}'.split('=')[0].split('.')[-1]
-    print('[*]                     Version '+version)
+                print(path_to_make + " 已经存在")
-    print('[*]======================================================')
+                pass
-    CreatFailedFolder()
+            except Exception as exception:
-    UpdateCheck()
+                print('! 创建文件夹 ' + path_to_make + ' 失败，文件夹路径错误或权限不够')
-    moveMovies()
+                raise exception
-    os.chdir(os.getcwd())
+        else:
-
+            raise Exception('！创建的文件夹路径为空，请确认')
-    count = 0
+
-    count_all = str(len(movie_lists()))
+
-    print('[+]Find',str(len(movie_lists())),'movies')
+if __name__ == '__main__':
-    if config['common']['soft_link'] == '1':
+    version = '2.8.2'
-        print('[!] --- Soft link mode is ENABLE! ----')
+
-    for i in movie_lists(): #遍历电影列表 交给core处理
+    print('[*]================== AV Data Capture ===================')
-        count = count + 1
+    print('[*]                    Version ' + version)
-        percentage = str(count/int(count_all)*100)[:4]+'%'
+    print('[*]======================================================')
-        print('[!] - '+percentage+' ['+str(count)+'/'+count_all+'] -')
+
-        try:
+    # UpdateCheck(version)
-            print("[!]Making Data for   [" + i + "], the number is [" + getNumber(i) + "]")
+
-            RunCore()
+    CreatFailedFolder(config.failed_folder)
-            print("[*]======================================================")
+    os.chdir(os.getcwd())
-        except:  # 番号提取异常
+
-            print('[-]' + i + ' Cannot catch the number :')
+    # 创建文件夹
-            if config['common']['soft_link'] == '1':
+    create_folder([config.failed_folder, config.search_folder, config.temp_folder])
-                print('[-]Link',i,'to failed folder')
+
-                os.symlink(i,str(os.getcwd()) + '/' + 'failed/')
+    # temp 文件夹中infos放 番号json信息，pics中放图片信息
-            else:
+    path_infos = config.temp_folder + '/infos'
-                print('[-]Move ' + i + ' to failed folder')
+    path_pics = config.temp_folder + '/pics'
-                shutil.move(i, str(os.getcwd()) + '/' + 'failed/')
+
-            continue
+    create_folder([path_infos, path_pics])
-
+
-    CEF(exclude_directory_1)
+    # 遍历搜索目录下所有视频的路径
-    CEF(exclude_directory_2)
+    movie_list = movie_lists(config.escape_folder)
-    print("[+]All finished!!!")
+
-    input("[+][+]Press enter key exit, you can check the error messge before you exit.")
+    # 以下是从文本中提取测试的数据
+    # f = open('TestPathNFO.txt', 'r')
+    # f = open('TestPathSpecial.txt', 'r')
+    # movie_list = [line[:-1] for line in f.readlines()]
+    # f.close()
+
+    # 获取 番号,集数,路径  的字典->list
+    code_ep_paths = [[codeEposode[0], codeEposode[1], path] for path, codeEposode in get_numbers(movie_list).items()]
+    [print(i) for i in code_ep_paths]
+    #  按番号分组片子列表（重点），用于寻找相同番号的片子
+    '''
+    这里利用pandas分组 "https://pandas.pydata.org/pandas-docs/stable/user_guide/groupby.html"
+    
+    '''
+    # # 设置打印时显示所有列
+    # pd.set_option('display.max_columns', None)
+    # # 显示所有行
+    # pd.set_option('display.max_rows', None)
+    # # 设置value的显示长度为100，默认为50
+    # pd.set_option('max_colwidth', 30)
+    # # 创建框架
+    # df = pd.DataFrame(code_ep_paths, columns=('code', 'ep', 'path'))
+    # # 以番号分组
+    # groupedCode_code_ep_paths = df.groupby(['code'])
+    # # print(df.groupby(['code', 'ep']).describe().unstack())
+    # grouped_code_ep = df.groupby(['code', 'ep'])['path']
+    #
+    sorted_code_list = sorted(code_ep_paths, key=lambda code_ep_path: code_ep_path[0])
+    group_code_list = itertools.groupby(sorted_code_list, key=lambda code_ep_path: code_ep_path[0])
+
+
+    def group_code_list_to_dict(group_code_list):
+        data_dict = {}
+        for code, code_ep_path_group in group_code_list:
+            code_ep_path_list = list(code_ep_path_group)
+            eps_of_code = {}
+            group_ep_list = itertools.groupby(code_ep_path_list, key=lambda code_ep_path: code_ep_path[1])
+            for ep, group_ep_group in group_ep_list:
+                group_ep_list = list(group_ep_group)
+                eps_of_code[ep] = [code_ep_path[2] for code_ep_path in group_ep_list]
+            data_dict[code] = eps_of_code
+
+        return data_dict
+
+
+    def print_same_code_ep_path(data_dict_in):
+        for code_in in data_dict_in:
+            ep_path_list = data_dict_in[code_in]
+            if len(ep_path_list) > 1:
+                print('--' * 60)
+                print("|" + (code_in if code_in else 'unknown') + ":")
+
+                # group_ep_list = itertools.groupby(code_ep_path_list.items(), key=lambda code_ep_path: code_ep_path[0])
+                for ep in ep_path_list:
+                    path_list = ep_path_list[ep]
+                    print('--' * 12)
+                    ep = ep if ep else ' '
+                    if len(path_list) == 1:
+                        print('|           集数:' + ep + ' 文件: ' + path_list[0])
+                    else:
+                        print('|           集数:' + ep + ' 文件: ')
+                        for path in path_list:
+                            print('|                       ' + path)
+
+            else:
+                pass
+
+
+    # 分好组的数据 {code:{ep:[path]}}
+    data_dict_groupby_code_ep = group_code_list_to_dict(group_code_list)
+
+    print('--' * 100)
+    print("找到影片数量:" + str(len(movie_list)))
+    print("合计番号数量:" + str(len(data_dict_groupby_code_ep)) + "  (多个相同番号的影片只统计一个，不能识别的番号 都统一为'unknown')")
+    print('Warning:!!!! 以下为相同番号的电影明细')
+    print('◤' + '--' * 80)
+    print_same_code_ep_path(data_dict_groupby_code_ep)
+    print('◣' + '--' * 80)
+
+    isContinue = input('任意键继续? N 退出 \n')
+    if isContinue.strip(' ') == "N":
+        exit(1)
+
+
+    # ========== 野鸡番号拖动 ==========
+    # number_argparse = argparse_get_file()
+    # if not number_argparse == '':
+    #     print("[!]Making Data for   [" + number_argparse + "], the number is [" + getNumber(number_argparse,
+    #                                                                                         absolute_path=True) + "]")
+    #     nfo = core_main(number_argparse, getNumber(number_argparse, absolute_path=True))
+    #     print("[*]======================================================")
+    #     CEF(config.success_folder)
+    #     CEF(config.failed_folder)
+    #     print("[+]All finished!!!")
+    #     input("[+][+]Press enter key exit, you can check the error messge before you exit.")
+    #     os._exit(0)
+    # ========== 野鸡番号拖动 ==========
+
+    def download_code_infos(code_list, is_read_cache=True):
+        """
+         遍历按番号分组的集合，刮取番号信息并缓存
+
+        :param is_read_cache: 是否读取缓存数据
+        :param code_list:
+        :return: {code:nfo}
+        """
+        count_all_grouped = len(code_list)
+        count = 0
+        code_info_dict = {}
+
+        for code in code_list:
+            count = count + 1
+            percentage = str(count / int(count_all_grouped) * 100)[:4] + '%'
+            print('[!] - ' + percentage + ' [' + str(count) + '/' + str(count_all_grouped) + '] -')
+            try:
+                print("[!]搜刮数据 [" + code + "]")
+                if code:
+                    # 创建番号的文件夹
+                    file_path = path_infos + '/' + code + '.json'
+                    nfo = {}
+                    # 读取缓存信息，如果没有则联网搜刮
+
+                    path = Path(file_path)
+                    if is_read_cache and (path.exists() and path.is_file() and path.stat().st_size > 0):
+                        print('找到缓存信息')
+                        with open(file_path) as fp:
+                            nfo = json.load(fp)
+                    else:
+
+                        # 核心功能 - 联网抓取信息字典
+                        print('联网搜刮')
+                        nfo = core_main(code)
+                        print('正在写入', end='')
+
+                        # 把缓存信息写入缓存文件夹中，有时会设备占用而失败，重试即可
+                        @retry(stop=stop_after_delay(3), wait=wait_fixed(2))
+                        def read_file():
+                            with open(file_path, 'w') as fp:
+                                json.dump(nfo, fp)
+
+                        read_file()
+                        print('完成！')
+                    # 将番号信息放入字典
+                    code_info_dict[code] = nfo
+                    print("[*]======================================================")
+
+            except Exception as e:  # 番号的信息获取失败
+                code_info_dict[code] = ''
+                print("找不到信息:" + code + ',Reason:' + str(e))
+
+                # if config.soft_link:
+                #     print('[-]Link', file_path_name, 'to failed folder')
+                #     os.symlink(file_path_name, config.failed_folder + '/')
+                # else:
+                #     try:
+                #         print('[-]Move ' + file_path_name + ' to failed folder:' + config.failed_folder)
+                #         shutil.move(file_path_name, config.failed_folder + '/')
+                #     except FileExistsError:
+                #         print('[!]File exists in failed!')
+                #     except:
+                #         print('[+]skip')
+                continue
+        return code_info_dict
+
+
+    print('----------------------------------')
+    code_infos = download_code_infos(data_dict_groupby_code_ep)
+    print("----未找到番号数据的番号----")
+    print([print(code) for code in code_infos if code_infos[code] == ''])
+    print("-------------------------")
+
+
+    def download_images_of_nfos(code_info_dict):
+        """
+        遍历番号信息，下载番号电影的海报，图片
+        :param code_info_dict:
+        :return: 无图片的信息的番号
+        """
+
+        code_list_empty_image = []
+        for code in code_info_dict:
+            nfo = code_info_dict[code]
+            if len(nfo.keys()) == 0:
+                code_list_empty_image.append(code)
+                continue
+
+            code_pics_folder_to_save = path_pics + '/' + code
+            # 1 创建 番号文件夹
+            os.makedirs(code_pics_folder_to_save, exist_ok=True)
+            #  下载缩略图
+            if nfo['imagecut'] == 3:  # 3 是缩略图
+                path = Path(code_pics_folder_to_save + '/' + 'thumb.png')
+                if path.exists() and path.is_file() and path.stat().st_size > 0:
+                    print(code + '：缩略图已有缓存')
+                else:
+                    print(code + '：缩略图下载中...')
+                    download_file(nfo['cover_small'], code_pics_folder_to_save, 'thumb.png')
+                    print(code + '：缩略图下载完成')
+            #  下载海报
+            path = Path(code_pics_folder_to_save + '/' + 'poster.png')
+            if path.exists() and path.is_file() and path.stat().st_size > 0:
+                print(code + '：海报已有缓存')
+            else:
+                print(code + '：海报下载中...')
+                download_file(nfo['cover'], code_pics_folder_to_save, 'poster.png')
+                print(code + '：海报下载完成')
+        return code_list_empty_image
+
+
+
+    code_list_empty = download_images_of_nfos(code_infos)
+    print("----未找到集数的番号----")
+    print([print(code) for code in code_list_empty])
+    print("------搜刮未找到集数的番号------")
+    code_infos_of_no_ep = download_code_infos(code_list_empty, is_read_cache=False)
+    print("----还是未找到番号数据的番号----")
+    print([print(code) for code in code_infos_of_no_ep if code_infos_of_no_ep[code] == ''])
+    print("----------------------")
+    # 开始操作
+    # # 2 创建缩略图海报
+    # if nfo['imagecut'] == 3:  # 3 是缩略图
+    #     download_cover_file(nfo['cover_small'], code, code_pics_folder_to_save)
+    # # 3 创建图
+    # download_image(nfo['cover'], code, code_pics_folder_to_save)
+    # # 4 剪裁
+    # crop_image(nfo['imagecut'], code, code_pics_folder_to_save)
+    # # 5 背景图
+    # copy_images_to_background_image(code, code_pics_folder_to_save)
+    # 6 创建 mame.nfo(不需要，需要时从infos中josn文件转为nfo文件)
+    # make_nfo_file(nfo, code, temp_path_to_save)
+    # 相同番号处理：按集数添加-CD[X]；视频格式 and 大小 分；
+    # TODO 方式1 刮削：添加nfo，封面，内容截图等
+    # 6 创建 mame.nfo(不需要，需要时从infos中josn文件转为nfo文件)
+    make_nfo_file(nfo, code, temp_path_to_save)
+    # TODO 方式2 整理：按规则移动影片，字幕 到 演员，发行商，有无🐎 等
+
+    # if config.program_mode == '1':
+    #     if multi_part == 1:
+    #         number += part  # 这时number会被附加上CD1后缀
+    #     smallCoverCheck(path, number, imagecut, json_data['cover_small'], c_word, option, filepath, config.failed_folder)  # 检查小封面
+    #     imageDownload(option, json_data['cover'], number, c_word, path, multi_part, filepath, config.failed_folder)  # creatFoder会返回番号路径
+    #     cutImage(option, imagecut, path, number, c_word)  # 裁剪图
+    #     copyRenameJpgToBackdrop(option, path, number, c_word)
+    #     PrintFiles(option, path, c_word, json_data['naming_rule'], part, cn_sub, json_data, filepath, config.failed_folder, tag)  # 打印文件 .nfo
+    #     pasteFileToFolder(filepath, path, number, c_word)  # 移动文件
+    #     # =======================================================================整理模式
+    # elif config.program_mode == '2':
+    #     pasteFileToFolder_mode2(filepath, path, multi_part, number, part, c_word)  # 移动文件
+
+    # CEF(config.success_folder)
+    # CEF(config.failed_folder)
+    print("[+]All finished!!!")
+    input("[+][+]Press enter key exit, you can check the error message before you exit.")

ConfigApp.py

@@ -0,0 +1,28 @@
+from configparser import ConfigParser
+
+from MediaServer import MediaServer
+
+
+class ConfigApp:
+    def __init__(self):
+        config_file = 'config.ini'
+        config = ConfigParser()
+        config.read(config_file, encoding='UTF-8')
+        self.success_folder = config['common']['success_output_folder']
+        self.failed_folder = config['common']['failed_output_folder']  # 失败输出目录
+        self.escape_folder = config['escape']['folders']  # 多级目录刮削需要排除的目录
+        self.search_folder = config['common']['search_folder']  # 搜索路径
+        self.temp_folder = config['common']['temp_folder']  # 临时资源路径
+        self.soft_link = (config['common']['soft_link'] == 1)
+        # self.escape_literals = (config['escape']['literals'] == 1)
+        self.naming_rule = config['Name_Rule']['naming_rule']
+        self.location_rule = config['Name_Rule']['location_rule']
+
+        self.proxy = config['proxy']['proxy']
+        self.timeout = float(config['proxy']['timeout'])
+        self.retry = int(config['proxy']['retry'])
+        self.media_server = MediaServer[config['media']['media_warehouse']]
+        self.update_check = config['update']['update_check']
+        self.debug_mode = config['debug_mode']['switch']
+
+

LearningNote/GroupbyDemo.py

@@ -0,0 +1,19 @@
+import pandas as pd
+import numpy as np
+
+df = pd.DataFrame({'A': ['foo', 'bar', 'foo', 'bar',
+                         'foo', 'bar', 'foo', 'foo'],
+                   'B': ['one', 'one', 'two', 'three',
+                         'two', 'two', 'one', 'three'],
+                   'C': np.random.randn(8),
+                   'D': np.random.randn(8)})
+
+print(df)
+groupedA = df.groupby('A').describe()
+groupedAB = df.groupby(['A', 'B'])['C']
+print('---'*18)
+for a, b in groupedAB:
+    print('--'*18)
+    print(a)
+    print('-' * 18)
+    print(b)

LearningNote/PandasDemo.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import numpy as np
+
+'''
+python数据处理三剑客之一pandas
+https://pandas.pydata.org/pandas-docs/stable/user_guide 
+https://www.pypandas.cn/docs/getting_started/10min.html
+'''
+
+dates = pd.date_range('20130101', periods=6)
+df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
+print(dates)
+print(df)
+
+df2 = pd.DataFrame({'A': 1.,
+                    'B': pd.Timestamp('20130102'),
+                    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
+                    'D': np.array([3] * 4, dtype='int32'),
+                    'E': pd.Categorical(["test", "train", "test", "train"]),
+                    'F': 'foo'})
+print(df2)
+print(df2.dtypes)
+print(df.head())
+print(df.tail(5))
+print(df.index)
+print(df.columns)
+df.describe() # 统计数据摘要
+df.T # index columns互转
+df.sort_index(axis=1, ascending=False) # 排序，axis=1 是columns，axis=1 是index
+df.sort_values(by='B') # 按值排序 按B列中的值排序
+
+# 切行
+df.A
+df['A']
+# 切行
+df['20130102':'20130104']
+df[0:3]
+

MediaServer.py

@@ -0,0 +1,28 @@
+from enum import Enum, auto
+
+
+class MediaServer(Enum):
+    EMBY = auto()
+    PLEX = auto()
+    KODI = auto()
+
+    # media = EMBY
+    #
+    # def __init__(self, arg):
+    #     self = [e for e in MediaServer if arg.upper() == self.name]
+
+    def poster_name(self, name):
+        if self == MediaServer.EMBY:  # 保存[name].png
+            return name + '.png'
+        elif self == MediaServer.KODI:  # 保存[name]-poster.jpg
+            return name + '-poster.jpg'
+        elif self == MediaServer.PLEX:  # 保存 poster.jpg
+            return 'poster.jpg'
+
+    def image_name(self, name):
+        if self == MediaServer.EMBY:  # name.jpg
+            return name + '.jpg'
+        elif self == MediaServer.KODI:  # [name]-fanart.jpg
+            return name + '-fanart.jpg'
+        elif self == MediaServer.PLEX:  # fanart.jpg
+            return 'fanart.jpg'

Metadate.py

@@ -0,0 +1,3 @@
+from addict import Dict
+
+# class Metadata:

PathNameProcessor.py

@@ -0,0 +1,115 @@
+import re
+
+import fuckit
+
+
+class PathNameProcessor:
+    # 类变量
+    pattern_of_file_name_suffixes = r'.(mov|mp4|avi|rmvb|wmv|mov|mkv|flv|ts|m2ts)$'
+
+    # def __init__(self):
+
+    @staticmethod
+    def remove_distractions(origin_name):
+        """移除干扰项"""
+        # 移除文件类型后缀
+        origin_name = re.sub(PathNameProcessor.pattern_of_file_name_suffixes, '', origin_name, 0, re.IGNORECASE)
+
+        # 处理包含减号-和_的番号'/-070409_621'
+        origin_name = re.sub(r'[-_~*# ]', "-", origin_name, 0)
+
+        origin_name = re.sub(r'(Carib)(bean)?', '-', origin_name, 0, re.IGNORECASE)
+        origin_name = re.sub(r'(1pondo)', '-', origin_name, 0, re.IGNORECASE)
+        origin_name = re.sub(r'(tokyo)[-. ]?(hot)', '-', origin_name, 0, re.IGNORECASE)
+        origin_name = re.sub(r'Uncensored', '-', origin_name, 0, re.IGNORECASE)
+        origin_name = re.sub(r'JAV', '-', origin_name, 0, re.IGNORECASE)
+        # 移除干扰字段
+        origin_name = origin_name.replace('22-sht.me', '-')
+
+        # 去除文件名中时间 1970-2099年 月 日
+        pattern_of_date = r'(?:-)(19[789]\d|20\d{2})(-?(0\d|1[012])-?(0[1-9]|[12]\d|3[01])?)?[-.]'
+        # 移除字母开头 清晰度相关度 字符
+        pattern_of_resolution_alphas = r'(?<![a-zA-Z])(SD|((F|U)|(Full|Ultra)[-_*. ~]?)?HD|BD|(blu[-_*. ~]?ray)|[hx]264|[hx]265|HEVC)'
+        # 数字开头的 清晰度相关度 字符
+        pattern_of_resolution_numbers = r'(?<!\d)(4K|(1080[ip])|(720p)|(480p))'
+        origin_name = re.sub(pattern_of_resolution_alphas, "-", origin_name, 0, re.IGNORECASE)
+        origin_name = re.sub(pattern_of_resolution_numbers, "-", origin_name, 0, re.IGNORECASE)
+        origin_name = re.sub(pattern_of_date, "-", origin_name)
+
+        if 'FC2' or 'fc2' in origin_name:
+            origin_name = origin_name.replace('-PPV', '').replace('PPV-', '').replace('FC2PPV-', 'FC2-').replace(
+                'FC2PPV_', 'FC2-')
+
+        # 移除连续重复无意义符号-
+        origin_name = re.sub(r"([-.])(\1+)", r"\1", origin_name)
+        # 移除尾部无意义符号 方便识别剧集数
+        origin_name = re.sub(r'[-.]+$', "", origin_name)
+
+        return origin_name
+
+    @staticmethod
+    def extract_suffix_episode(origin_name):
+        """ 提取尾部集数号 123ABC(只识别一位) part1 ，ipz.A  ， CD1 ， NOP019B.HD.wmv"""
+        episode = None
+        with fuckit:
+            # 零宽断言获取尾部数字 剧集数 123
+            pattern_episodes_number = r'(?<!\d)\d$'
+            episode = re.findall(pattern_episodes_number, origin_name)[-1]
+            origin_name = re.sub(pattern_episodes_number, "", origin_name)
+        with fuckit:
+            # 零宽断言获取尾部字幕 剧集数 abc
+            pattern_episodes_alpha = r'(?<![a-zA-Z])[a-zA-Z]$'
+            episode = re.findall(pattern_episodes_alpha, origin_name)[-1]
+            origin_name = re.sub(pattern_episodes_alpha, "", origin_name)
+        return episode, origin_name
+
+    @staticmethod
+    def extract_code(origin_name):
+        """
+        提取集数和 规范过的番号
+        """
+        name = None
+        episode = None
+        with fuckit:
+            # 找到含- 或不含-的 番号：1. 数字+数字 2. 字母+数字
+            name = re.findall(r'(?:\d{2,}-\d{2,})|(?:[A-Z]+-?[A-Z]*\d{2,})', origin_name)[-1]
+            episode = PathNameProcessor.extract_episode_behind_code(origin_name, name)
+            # 将未-的名字处理加上 -
+            if not ('-' in name):
+                # 无减号-的番号,尝试分段加上-
+                # 非贪婪匹配非特殊字符，零宽断言后，数字至少2位连续,ipz221.part2 ， mide072hhb ,n1180
+                with fuckit:
+                    name = re.findall(r'[a-zA-Z]+\d{2,}', name)[-1]
+                    # 比如MCDV-47 mcdv-047 是2个不一样的片子，但是 SIVR-00008 和 SIVR-008是同同一部,但是heyzo除外,heyzo 是四位数
+                    if "heyzo" not in name.lower():
+                        name = re.sub(r'([a-zA-Z]{2,})(?:0*?)(\d{2,})', r'\1-\2', name)
+
+            # 正则取含-的番号 【字母-[字母]数字】,数字必定大于2位 番号的数组的最后的一个元素
+            with fuckit:
+                # MKBD_S03-MaRieS
+                name = re.findall(r'[a-zA-Z|\d]+-[a-zA-Z|\d]*\d{2,}', name)[-1]
+                # 107NTTR-037 -> NTTR-037 , SIVR-00008 -> SIVR-008 ，但是heyzo除外
+                if "heyzo" not in name.lower():
+                    searched = re.search(r'([a-zA-Z]{2,})-(?:0*)(\d{3,})', name)
+                    if searched:
+                        name = '-'.join(searched.groups())
+
+        return episode, name
+
+    @staticmethod
+    def extract_episode_behind_code(origin_name, code):
+        episode = None
+
+        with fuckit:
+            # 零宽断言获取尾部字幕 剧集数 abc123
+            result_dict = re.search(rf'(?<={code})-?((?P<alpha>([A-Z](?![A-Z])))|(?P<num>\d(?!\d)))', origin_name,
+                                    re.I).groupdict()
+            episode = result_dict['alpha'] or result_dict['num']
+        return episode
+
+
+def safe_list_get(list_in, idx, default):
+    try:
+        return list_in[idx]
+    except IndexError:
+        return default

Pipfile

@@ -0,0 +1,19 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+
+[packages]
+bs4 = "*"
+tenacity = "*"
+fuckit = "*"
+requests = "*"
+image = "*"
+lazyxml = {editable = true,git = "https://github.com/waynedyck/lazyxml.git",ref = "python-3-conversion_wd1"}
+lxml = "*"
+pyquery = "*"
+
+[requires]
+python_version = "3.8"

Pipfile.lock

@@ -0,0 +1,246 @@
+{
+    "_meta": {
+        "hash": {
+            "sha256": "15bf3c6af3ec315358a0217481a13285f95fc742bb5db8a1f934e0d1c3d7d5e2"
+        },
+        "pipfile-spec": 6,
+        "requires": {
+            "python_version": "3.8"
+        },
+        "sources": [
+            {
+                "name": "pypi",
+                "url": "https://pypi.org/simple",
+                "verify_ssl": true
+            }
+        ]
+    },
+    "default": {
+        "asgiref": {
+            "hashes": [
+                "sha256:5ee950735509d04eb673bd7f7120f8fa1c9e2df495394992c73234d526907e17",
+                "sha256:7162a3cb30ab0609f1a4c95938fd73e8604f63bdba516a7f7d64b83ff09478f0"
+            ],
+            "markers": "python_version >= '3.5'",
+            "version": "==3.3.1"
+        },
+        "beautifulsoup4": {
+            "hashes": [
+                "sha256:4c98143716ef1cb40bf7f39a8e3eec8f8b009509e74904ba3a7b315431577e35",
+                "sha256:84729e322ad1d5b4d25f805bfa05b902dd96450f43842c4e99067d5e1369eb25",
+                "sha256:fff47e031e34ec82bf17e00da8f592fe7de69aeea38be00523c04623c04fb666"
+            ],
+            "version": "==4.9.3"
+        },
+        "bs4": {
+            "hashes": [
+                "sha256:36ecea1fd7cc5c0c6e4a1ff075df26d50da647b75376626cc186e2212886dd3a"
+            ],
+            "index": "pypi",
+            "version": "==0.0.1"
+        },
+        "certifi": {
+            "hashes": [
+                "sha256:1a4995114262bffbc2413b159f2a1a480c969de6e6eb13ee966d470af86af59c",
+                "sha256:719a74fb9e33b9bd44cc7f3a8d94bc35e4049deebe19ba7d8e108280cfd59830"
+            ],
+            "version": "==2020.12.5"
+        },
+        "chardet": {
+            "hashes": [
+                "sha256:0d6f53a15db4120f2b08c94f11e7d93d2c911ee118b6b30a04ec3ee8310179fa",
+                "sha256:f864054d66fd9118f2e67044ac8981a54775ec5b67aed0441892edb553d21da5"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4'",
+            "version": "==4.0.0"
+        },
+        "cssselect": {
+            "hashes": [
+                "sha256:f612ee47b749c877ebae5bb77035d8f4202c6ad0f0fc1271b3c18ad6c4468ecf",
+                "sha256:f95f8dedd925fd8f54edb3d2dfb44c190d9d18512377d3c1e2388d16126879bc"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
+            "version": "==1.1.0"
+        },
+        "django": {
+            "hashes": [
+                "sha256:2d78425ba74c7a1a74b196058b261b9733a8570782f4e2828974777ccca7edf7",
+                "sha256:efa2ab96b33b20c2182db93147a0c3cd7769d418926f9e9f140a60dca7c64ca9"
+            ],
+            "markers": "python_version >= '3.6'",
+            "version": "==3.1.5"
+        },
+        "fuckit": {
+            "hashes": [
+                "sha256:059488e6aa2053da9db5eb5101e2498f608314da5118bf2385acb864568ccc25"
+            ],
+            "index": "pypi",
+            "version": "==4.8.1"
+        },
+        "idna": {
+            "hashes": [
+                "sha256:b307872f855b18632ce0c21c5e45be78c0ea7ae4c15c828c20788b26921eb3f6",
+                "sha256:b97d804b1e9b523befed77c48dacec60e6dcb0b5391d57af6a65a312a90648c0"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
+            "version": "==2.10"
+        },
+        "image": {
+            "hashes": [
+                "sha256:baa2e09178277daa50f22fd6d1d51ec78f19c12688921cb9ab5808743f097126"
+            ],
+            "index": "pypi",
+            "version": "==1.5.33"
+        },
+        "lazyxml": {
+            "editable": true,
+            "git": "https://github.com/waynedyck/lazyxml.git",
+            "ref": "f42ea4a4febf4c1e120b05d6ca9cef42556a75d5"
+        },
+        "lxml": {
+            "hashes": [
+                "sha256:0448576c148c129594d890265b1a83b9cd76fd1f0a6a04620753d9a6bcfd0a4d",
+                "sha256:127f76864468d6630e1b453d3ffbbd04b024c674f55cf0a30dc2595137892d37",
+                "sha256:1471cee35eba321827d7d53d104e7b8c593ea3ad376aa2df89533ce8e1b24a01",
+                "sha256:2363c35637d2d9d6f26f60a208819e7eafc4305ce39dc1d5005eccc4593331c2",
+                "sha256:2e5cc908fe43fe1aa299e58046ad66981131a66aea3129aac7770c37f590a644",
+                "sha256:2e6fd1b8acd005bd71e6c94f30c055594bbd0aa02ef51a22bbfa961ab63b2d75",
+                "sha256:366cb750140f221523fa062d641393092813b81e15d0e25d9f7c6025f910ee80",
+                "sha256:42ebca24ba2a21065fb546f3e6bd0c58c3fe9ac298f3a320147029a4850f51a2",
+                "sha256:4e751e77006da34643ab782e4a5cc21ea7b755551db202bc4d3a423b307db780",
+                "sha256:4fb85c447e288df535b17ebdebf0ec1cf3a3f1a8eba7e79169f4f37af43c6b98",
+                "sha256:50c348995b47b5a4e330362cf39fc503b4a43b14a91c34c83b955e1805c8e308",
+                "sha256:535332fe9d00c3cd455bd3dd7d4bacab86e2d564bdf7606079160fa6251caacf",
+                "sha256:535f067002b0fd1a4e5296a8f1bf88193080ff992a195e66964ef2a6cfec5388",
+                "sha256:5be4a2e212bb6aa045e37f7d48e3e1e4b6fd259882ed5a00786f82e8c37ce77d",
+                "sha256:60a20bfc3bd234d54d49c388950195d23a5583d4108e1a1d47c9eef8d8c042b3",
+                "sha256:648914abafe67f11be7d93c1a546068f8eff3c5fa938e1f94509e4a5d682b2d8",
+                "sha256:681d75e1a38a69f1e64ab82fe4b1ed3fd758717bed735fb9aeaa124143f051af",
+                "sha256:68a5d77e440df94011214b7db907ec8f19e439507a70c958f750c18d88f995d2",
+                "sha256:69a63f83e88138ab7642d8f61418cf3180a4d8cd13995df87725cb8b893e950e",
+                "sha256:6e4183800f16f3679076dfa8abf2db3083919d7e30764a069fb66b2b9eff9939",
+                "sha256:6fd8d5903c2e53f49e99359b063df27fdf7acb89a52b6a12494208bf61345a03",
+                "sha256:791394449e98243839fa822a637177dd42a95f4883ad3dec2a0ce6ac99fb0a9d",
+                "sha256:7a7669ff50f41225ca5d6ee0a1ec8413f3a0d8aa2b109f86d540887b7ec0d72a",
+                "sha256:7e9eac1e526386df7c70ef253b792a0a12dd86d833b1d329e038c7a235dfceb5",
+                "sha256:7ee8af0b9f7de635c61cdd5b8534b76c52cd03536f29f51151b377f76e214a1a",
+                "sha256:8246f30ca34dc712ab07e51dc34fea883c00b7ccb0e614651e49da2c49a30711",
+                "sha256:8c88b599e226994ad4db29d93bc149aa1aff3dc3a4355dd5757569ba78632bdf",
+                "sha256:923963e989ffbceaa210ac37afc9b906acebe945d2723e9679b643513837b089",
+                "sha256:94d55bd03d8671686e3f012577d9caa5421a07286dd351dfef64791cf7c6c505",
+                "sha256:97db258793d193c7b62d4e2586c6ed98d51086e93f9a3af2b2034af01450a74b",
+                "sha256:a9d6bc8642e2c67db33f1247a77c53476f3a166e09067c0474facb045756087f",
+                "sha256:cd11c7e8d21af997ee8079037fff88f16fda188a9776eb4b81c7e4c9c0a7d7fc",
+                "sha256:d8d3d4713f0c28bdc6c806a278d998546e8efc3498949e3ace6e117462ac0a5e",
+                "sha256:e0bfe9bb028974a481410432dbe1b182e8191d5d40382e5b8ff39cdd2e5c5931",
+                "sha256:f4822c0660c3754f1a41a655e37cb4dbbc9be3d35b125a37fab6f82d47674ebc",
+                "sha256:f83d281bb2a6217cd806f4cf0ddded436790e66f393e124dfe9731f6b3fb9afe",
+                "sha256:fc37870d6716b137e80d19241d0e2cff7a7643b925dfa49b4c8ebd1295eb506e"
+            ],
+            "index": "pypi",
+            "version": "==4.6.2"
+        },
+        "pillow": {
+            "hashes": [
+                "sha256:165c88bc9d8dba670110c689e3cc5c71dbe4bfb984ffa7cbebf1fac9554071d6",
+                "sha256:1d208e670abfeb41b6143537a681299ef86e92d2a3dac299d3cd6830d5c7bded",
+                "sha256:22d070ca2e60c99929ef274cfced04294d2368193e935c5d6febfd8b601bf865",
+                "sha256:2353834b2c49b95e1313fb34edf18fca4d57446675d05298bb694bca4b194174",
+                "sha256:39725acf2d2e9c17356e6835dccebe7a697db55f25a09207e38b835d5e1bc032",
+                "sha256:3de6b2ee4f78c6b3d89d184ade5d8fa68af0848f9b6b6da2b9ab7943ec46971a",
+                "sha256:47c0d93ee9c8b181f353dbead6530b26980fe4f5485aa18be8f1fd3c3cbc685e",
+                "sha256:5e2fe3bb2363b862671eba632537cd3a823847db4d98be95690b7e382f3d6378",
+                "sha256:604815c55fd92e735f9738f65dabf4edc3e79f88541c221d292faec1904a4b17",
+                "sha256:6c5275bd82711cd3dcd0af8ce0bb99113ae8911fc2952805f1d012de7d600a4c",
+                "sha256:731ca5aabe9085160cf68b2dbef95fc1991015bc0a3a6ea46a371ab88f3d0913",
+                "sha256:7612520e5e1a371d77e1d1ca3a3ee6227eef00d0a9cddb4ef7ecb0b7396eddf7",
+                "sha256:7916cbc94f1c6b1301ac04510d0881b9e9feb20ae34094d3615a8a7c3db0dcc0",
+                "sha256:81c3fa9a75d9f1afafdb916d5995633f319db09bd773cb56b8e39f1e98d90820",
+                "sha256:887668e792b7edbfb1d3c9d8b5d8c859269a0f0eba4dda562adb95500f60dbba",
+                "sha256:93a473b53cc6e0b3ce6bf51b1b95b7b1e7e6084be3a07e40f79b42e83503fbf2",
+                "sha256:96d4dc103d1a0fa6d47c6c55a47de5f5dafd5ef0114fa10c85a1fd8e0216284b",
+                "sha256:a3d3e086474ef12ef13d42e5f9b7bbf09d39cf6bd4940f982263d6954b13f6a9",
+                "sha256:b02a0b9f332086657852b1f7cb380f6a42403a6d9c42a4c34a561aa4530d5234",
+                "sha256:b09e10ec453de97f9a23a5aa5e30b334195e8d2ddd1ce76cc32e52ba63c8b31d",
+                "sha256:b6f00ad5ebe846cc91763b1d0c6d30a8042e02b2316e27b05de04fa6ec831ec5",
+                "sha256:bba80df38cfc17f490ec651c73bb37cd896bc2400cfba27d078c2135223c1206",
+                "sha256:c3d911614b008e8a576b8e5303e3db29224b455d3d66d1b2848ba6ca83f9ece9",
+                "sha256:ca20739e303254287138234485579b28cb0d524401f83d5129b5ff9d606cb0a8",
+                "sha256:cb192176b477d49b0a327b2a5a4979552b7a58cd42037034316b8018ac3ebb59",
+                "sha256:cdbbe7dff4a677fb555a54f9bc0450f2a21a93c5ba2b44e09e54fcb72d2bd13d",
+                "sha256:cf6e33d92b1526190a1de904df21663c46a456758c0424e4f947ae9aa6088bf7",
+                "sha256:d355502dce85ade85a2511b40b4c61a128902f246504f7de29bbeec1ae27933a",
+                "sha256:d673c4990acd016229a5c1c4ee8a9e6d8f481b27ade5fc3d95938697fa443ce0",
+                "sha256:dc577f4cfdda354db3ae37a572428a90ffdbe4e51eda7849bf442fb803f09c9b",
+                "sha256:dd9eef866c70d2cbbea1ae58134eaffda0d4bfea403025f4db6859724b18ab3d",
+                "sha256:f50e7a98b0453f39000619d845be8b06e611e56ee6e8186f7f60c3b1e2f0feae"
+            ],
+            "markers": "python_version >= '3.6'",
+            "version": "==8.1.0"
+        },
+        "pyquery": {
+            "hashes": [
+                "sha256:1fc33b7699455ed25c75282bc8f80ace1ac078b0dda5a933dacbd8b1c1f83963",
+                "sha256:a388eefb6bc4a55350de0316fbd97cda999ae669b6743ae5b99102ba54f5aa72"
+            ],
+            "index": "pypi",
+            "version": "==1.4.3"
+        },
+        "pytz": {
+            "hashes": [
+                "sha256:16962c5fb8db4a8f63a26646d8886e9d769b6c511543557bc84e9569fb9a9cb4",
+                "sha256:180befebb1927b16f6b57101720075a984c019ac16b1b7575673bea42c6c3da5"
+            ],
+            "version": "==2020.5"
+        },
+        "requests": {
+            "hashes": [
+                "sha256:27973dd4a904a4f13b263a19c866c13b92a39ed1c964655f025f3f8d3d75b804",
+                "sha256:c210084e36a42ae6b9219e00e48287def368a26d03a048ddad7bfee44f75871e"
+            ],
+            "index": "pypi",
+            "version": "==2.25.1"
+        },
+        "six": {
+            "hashes": [
+                "sha256:30639c035cdb23534cd4aa2dd52c3bf48f06e5f4a941509c8bafd8ce11080259",
+                "sha256:8b74bedcbbbaca38ff6d7491d76f2b06b3592611af620f8426e82dddb04a5ced"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'",
+            "version": "==1.15.0"
+        },
+        "soupsieve": {
+            "hashes": [
+                "sha256:4bb21a6ee4707bf43b61230e80740e71bfe56e55d1f1f50924b087bb2975c851",
+                "sha256:6dc52924dc0bc710a5d16794e6b3480b2c7c08b07729505feab2b2c16661ff6e"
+            ],
+            "markers": "python_version >= '3.0'",
+            "version": "==2.1"
+        },
+        "sqlparse": {
+            "hashes": [
+                "sha256:017cde379adbd6a1f15a61873f43e8274179378e95ef3fede90b5aa64d304ed0",
+                "sha256:0f91fd2e829c44362cbcfab3e9ae12e22badaa8a29ad5ff599f9ec109f0454e8"
+            ],
+            "markers": "python_version >= '3.5'",
+            "version": "==0.4.1"
+        },
+        "tenacity": {
+            "hashes": [
+                "sha256:baed357d9f35ec64264d8a4bbf004c35058fad8795c5b0d8a7dc77ecdcbb8f39",
+                "sha256:e14d191fb0a309b563904bbc336582efe2037de437e543b38da749769b544d7f"
+            ],
+            "index": "pypi",
+            "version": "==6.3.1"
+        },
+        "urllib3": {
+            "hashes": [
+                "sha256:19188f96923873c92ccb987120ec4acaa12f0461fa9ce5d3d0772bc965a39e08",
+                "sha256:d8ff90d979214d7b4f8ce956e80f4028fc6860e4431f731ea4a8c08f23f99473"
+            ],
+            "markers": "python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4' and python_version < '4'",
+            "version": "==1.26.2"
+        }
+    },
+    "develop": {}
+}

README.md

@@ -1,15 +1,24 @@
-# AV Data Capture
+# AV Data Capture (CLI)
-
 
+CLI 版本  
 <a title="Hits" target="_blank" href="https://github.com/yoshiko2/AV_Data_Capture"><img src="https://hits.b3log.org/yoshiko2/AV_Data_Capture.svg"></a>
 ![](https://img.shields.io/badge/build-passing-brightgreen.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/downloads/yoshiko2/av_data_capture/total.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)
 ![](https://img.shields.io/badge/Python-3.7-yellow.svg?style=flat-square&logo=python)<br>
+[GUI 版本](https://github.com/moyy996/AVDC)  
+<a title="Hits" target="_blank" href="https://github.com/moyy996/avdc"><img src="https://hits.b3log.org/moyy996/AVDC.svg"></a>
+![](https://img.shields.io/badge/build-passing-brightgreen.svg?style=flat-square)
+![](https://img.shields.io/github/downloads/moyy996/avdc/total.svg?style=flat-square)
+![](https://img.shields.io/github/license/moyy996/avdc.svg?style=flat-square)
+![](https://img.shields.io/github/release/moyy996/avdc.svg?style=flat-square)
+![](https://img.shields.io/badge/Python-3.6-yellow.svg?style=flat-square&logo=python)
+![](https://img.shields.io/badge/Pyqt-5-blue.svg?style=flat-square)<br>
 
 
-**日本电影元数据 抓取工具 | 刮削器**，配合本地影片管理软件EMBY,KODI等管理本地影片，该软件起到分类与元数据抓取作用，利用元数据信息来分类，供本地影片分类整理使用。
+**日本电影元数据 抓取工具 | 刮削器**，配合本地影片管理软件 Emby, Jellyfin, Kodi 等管理本地影片，该软件起到分类与元数据（metadata）抓取作用，利用元数据信息来分类，供本地影片分类整理使用。  
+##### 本地电影刮削与整理一体化解决方案
 
 # 目录
 * [声明](#声明)
@@ -17,112 +26,115 @@
 * [故事](#故事)
 * [效果图](#效果图)
 * [如何使用](#如何使用)
-* [下载](#下载)
+    * [下载](#下载)
-* [简明教程](#简要教程)
+    * [简要教程](#简要教程)
-* [模块安装](#1模块安装)
+* [完整文档](#完整文档)
-* [配置](#2配置configini)
+    * [模块安装](#模块安装)
-* [多目录影片处理](#4多目录影片处理)
+    * [配置](#配置configini)
-* [多集影片处理](#多集影片处理)
+    * [多目录影片处理](#多目录影片处理)
-* [(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)
+    * [多集影片处理](#多集影片处理)
-* [运行软件](#5运行-av_data_capturepyexe)
+    * [中文字幕处理](#中文字幕处理)
-* [影片原路径处理](#4建议把软件拷贝和电影的统一目录下)
+    * [异常处理（重要）](#异常处理重要)
-* [异常处理（重要）](#51异常处理重要)
+* [写在后面](#写在后面)
-* [导入至媒体库](#7把jav_output文件夹导入到embykodi中等待元数据刷新完成)
-* [关于群晖NAS](#8关于群晖NAS)
-* [写在后面](#9写在后面)
 
 # 声明
-* 本软件仅供**技术交流，学术交流**使用<br>
+* 本软件仅供**技术交流，学术交流**使用
-* 本软件作者编写出该软件旨在学习Python3，提高编程水平<br>
+* 本软件作者编写出该软件旨在学习 Python ，提高编程水平
-* 用户在使用该软件前，请用户自觉遵守当地法律法规，如果该软件使用过程中存在违反当地法律法规的行为，请勿使用该软件<br>
+* 用户在使用本软件前，请用户自觉遵守当地法律法规，如果本软件使用过程中存在违反当地法律法规的行为，请勿使用该软件
-* 用户使用该软件时，若产生一切违法行为由用户承担<br>
+* 用户在使用本软件时，若产生一切违法行为由用户承担
-* 严禁用户使用于商业和个人其他意图<br>
+* 严禁用户将本软件使用于商业和个人其他意图
-* 本软件作者保留最终决定权和最终解释权<br>
+* 本软件作者保留最终决定权和最终解释权
 
-**若用户不同意上述条款任意一条，请勿使用该软件**<br>
+**若用户不同意上述条款任意一条，请勿使用本软件**
 
 # FAQ
-### 这软件能下片吗？
+### 软件能下片吗？
-* 该软件不提供任何影片下载地址，仅供本地影片分类整理使用。
+* 本软件不提供任何影片下载地址，仅供本地影片分类整理使用
-### 什么是元数据？
+### 什么是元数据（metadata）？
-* 元数据包括了影片的：封面，导演，演员，简介，类型......
+* 元数据包括了影片的封面，导演，演员，简介，类型......
 ### 软件收费吗？
-* 软件永久免费。**除了作者钦点以外**
+* 本软件永久免费，**除了作者<ruby>钦<rt>yìng</rt></ruby>点以外**
 ### 软件运行异常怎么办？
-* 认真看 [异常处理（重要）](#5异常处理重要)
+* 认真看 [异常处理（重要）](#异常处理重要)
-
+### 为什么软件要单线程运行？
-# 故事
+* 多线程爬取可能会触发网站反爬机制，同时也违背了些道德，故单线程运行
-[点击跳转至作者博客文章](https://yoshiko2.github.io/2019/10/18/AVDC/)
 
 # 效果图
-**图片来自网络**，由于相关法律法规，具体效果请自行联想
+**图片来自网络**，图片仅供参考，具体效果请自行联想
-![](https://i.loli.net/2019/07/04/5d1cf9bb1b08b86592.jpg)
+![preview_picture_1](https://i.loli.net/2019/07/04/5d1cf9bb1b08b86592.jpg)
-![](https://i.loli.net/2019/07/04/5d1cf9bb2696937880.jpg)<br>
+![preview_picture_2](https://i.loli.net/2019/07/04/5d1cf9bb2696937880.jpg)
 
 # 如何使用
-### 下载
+## 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>Release 下载地址(**仅限Windows**):<br>[![](https://img.shields.io/badge/%E4%B8%8B%E8%BD%BD-windows-blue.svg?style=for-the-badge&logo=windows)](https://github.com/yoshiko2/AV_Data_Capture/releases)<br>
+* release的程序可脱离**python环境**运行，可跳过 [模块安装](#模块安装)
-* Linux,MacOS请下载源码包运行
+### Windows
+Release 下载地址(**仅限Windows**):
 
-* Windows Python环境:[点击前往](https://www.python.org/downloads/windows/) 选中executable installer下载
+[![](https://img.shields.io/badge/%E4%B8%8B%E8%BD%BD-windows-blue.svg?style=for-the-badge&logo=windows)](https://github.com/yoshiko2/AV_Data_Capture/releases)
-* MacOS Python环境：[点击前往](https://www.python.org/downloads/mac-osx/)
-* Linux Python环境：Linux用户懂的吧，不解释下载地址
-### 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（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**<br>
 
-## 1.模块安装
+* 若 Windows 用户需要运行源代码版本，请安装 Windows Python 环境:[点击前往](https://www.python.org/downloads/windows/) 选中 executable installer 下载
+
+### MacOS, Linux
+* MacOS, Linux 用户请下载源码包运行
+* MacOS Python环境：开箱即用，[可选安装最新版本](https://docs.brew.sh/Homebrew-and-Python)
+* Linux Python环境：开箱即用，可选安装最新版本，恕 Linux 版本众多请自行搜索
+
+## 简要教程:
+1. 把软件拉到和电影的同一目录
+2. 设置 config.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）
+3. 运行软件等待完成
+4. 把 JAV_output 导入至 Kodi, Emby, Jellyfin 中。
+
+详细请看以下完整文档
+
+# 完整文档
+
+## 模块安装
 如果运行**源码**版，运行前请安装**Python环境**和安装以下**模块**  
-在终端/cmd/Powershell中输入以下代码来安装模块
-```python
-pip install requests
-```
-### 
-```python
-pip install pyquery
-```
-###
-```python
-pip install lxml
-```
-###
-```python
-pip install Beautifulsoup4
-```
-###
-```python
-pip install pillow
-```
-###
 
-## 2.配置config.ini
+在终端 cmd/Powershell/Terminal 中输入以下代码来安装模块
-#### 运行模式
->[common]<br>
->main_mode=1<br>
 
-1为普通模式<br>
+```python
+pip install requests pyquery lxml Beautifulsoup4 pillow
+```
+
+## 配置config.ini
+### 运行模式
+```
+[common]
+main_mode=1
+```
+1为普通模式，  
 2为整理模式：仅根据女优把电影命名为番号并分类到女优名称的文件夹下
 
->failed_output_folder=failed<br>
+```
->success_output_folder=JAV_outputd<br>
+success_output_folder=JAV_outputd
-
+failed_output_folder=failed
+```
 设置成功输出目录和失败输出目录
 
 ---
 #### 软链接
->[common]  
+方便PT下载完既想刮削又想继续上传的仓鼠党同志
->soft_link=0  
+```
-
+[common]
+soft_link=0
+```
 1为开启软链接模式  
 0为关闭
 
 ---
 ### 网络设置
->[proxy]  
+```
->proxy=127.0.0.1:1081  
+[proxy]  
->timeout=10  
+proxy=127.0.0.1:1081  
->retry=3  
+timeout=10  
+retry=3
+```  
 #### 针对某些地区的代理设置
->proxy=127.0.0.1:1081  
+```
+proxy=127.0.0.1:1081  
+```
 
 打开```config.ini```,在```[proxy]```下的```proxy```行设置本地代理地址和端口，支持Shadowxxxx/X,V2XXX本地代理端口  
 素人系列抓取建议使用日本代理  
@@ -132,98 +144,120 @@ pip install pillow
 
 ---
 #### 连接超时重试设置
->timeout=10  
+```
-
+timeout=10  
+```
 10为超时重试时间 单位：秒
 
 ---
 #### 连接重试次数设置
->retry=3  
+```
-
+retry=3  
+```
 3即为重试次数
 
 ---
 #### 检查更新开关
->[update]  
+```
->update_check=1  
+[update]  
-
+update_check=1  
+```
 0为关闭，1为开启，不建议关闭
 
 ---
 ### 媒体库选择 
->[media]<br>
+```
->media_warehouse=emby<br>
+[media]
->#emby plex kodi<br>
+media_warehouse=emby
-
+#emby plex kodi
-可选择emby, plex, kodi<br>
+```
+可选择emby, plex, kodi
 如果是PLEX，请安装插件：```XBMCnfoMoviesImporter```
 
 ---
-### 抓取目录
+### 排除指定字符和目录
->[escape]  
+```
->literals=\  
+[escape]  
+literals=\  
+folders=failed,JAV_output
+```
 
-```literals=``` 标题指定字符删除，例如```iterals=\()```，删除标题中```\()```字符
+```literals=``` 标题指定字符删除，例如```iterals=\()```，则删除标题中```\()```字符  
-
+```folders=``` 指定目录，例如```folders=failed,JAV_output```，多目录刮削时跳过failed,JAV_output  
----
-### 抓取目录选择
->[movie_location]<br>
->path=<br>
-
-如果directory后面为空，则抓取和程序同一目录下的影片
 
 ---
 ### 调试模式
->[debug_mode]<br>switch=1  
+```
+[debug_mode]
+switch=1  
+```
 
 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
 
 ---
-### 3.(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
->[Name_Rule]<br>
+```
->location_rule=actor+'/'+number<br>
+[Name_Rule]
->naming_rule=number+'-'+title<br>
+location_rule=actor+'/'+number
-
+naming_rule=number+'-'+title
+```
 已有默认配置
 
 ---
 #### 命名参数
->title = 片名<br>
+```
->actor = 演员<br>
+title = 片名
->studio = 公司<br>
+actor = 演员
->director = 导演<br>
+studio = 公司
->release = 发售日<br>
+director = 导演
->year = 发行年份<br>
+release = 发售日
->number = 番号<br>
+year = 发行年份
->cover = 封面链接<br>
+number = 番号
->tag = 类型<br>
+cover = 封面链接
->outline = 简介<br>
+tag = 类型
->runtime = 时长<br>
+outline = 简介
+runtime = 时长
+```
 
 上面的参数以下都称之为**变量**
 
 #### 例子：
-自定义规则方法：有两种元素，变量和字符，无论是任何一种元素之间连接必须要用加号 **+** ，比如：```'naming_rule=['+number+']-'+title```，其中冒号 ' ' 内的文字是字符，没有冒号包含的文字是变量，元素之间连接必须要用加号 **+** <br>
+自定义规则方法：有两种元素，变量和字符，无论是任何一种元素之间连接必须要用加号 **+** ，比如：```'naming_rule=['+number+']-'+title```，其中冒号 ' ' 内的文字是字符，没有冒号包含的文字是变量，元素之间连接必须要用加号 **+** 
-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。
+目录结构规则：默认 ```location_rule=actor+'/'+number```
+
+**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。
+
+影片命名规则：默认 ```naming_rule=number+'-'+title```
+
+**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>
+```
+[update]
+update_check=1
+```
 
 1为开，0为关
 
-## 4.多目录影片处理
+## 多目录影片处理
 可以在多个有影片目录的父目录下搜索影片后缀，然后剪切到和程序同一目录下  
 
 ## 多集影片处理
+**建议使用视频合并合并为一个视频文件**
 可以把多集电影按照集数后缀命名为类似```ssni-xxx-cd1.mp4m,ssni-xxx-cd2.mp4，abp-xxx-CD1.mp4```的规则，只要含有```-CDn./-cdn.```类似命名规则，即可使用分集功能
 
-## 5.运行 ```AV_Data_capture.py/.exe```
+## 中文字幕处理
-当文件名包含:<br>
+
+运行 ```AV_Data_capture.py/.exe```
+
+当文件名包含:
 中文，字幕，-c., -C., 处理元数据时会加上**中文字幕**标签
-## 5.1 异常处理（重要）
+
+## 异常处理（重要）
+
 ### 请确保软件是完整地！确保ini文件内容是和下载提供ini文件内容的一致的！
 ---
 ### 关于软件打开就闪退
@@ -243,41 +277,50 @@ pip install pillow
 
 ---
 ### 关于连接拒绝的错误
-请设置好[代理](#针对某些地区的代理设置)<br>
+请设置好[代理](#针对某些地区的代理设置)
 
 ---
 ### 关于Nonetype,xpath报错
-同上<br>
+同上
 
 ---
 ### 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:300Maan,259luxu,siro等,FC2系列**<br>
+**目前可以提取元素的影片:JAVBUS上有元数据的电影，素人系列:300Maan,259luxu,siro等,FC2系列**
->下一张图片来自Pockies的blog 原作者已授权<br>
+
+>下一张图片来自 Pockies 的 blog 原作者已授权
 
 ![](https://raw.githubusercontent.com/Pockies/pic/master/741f9461gy1g1cxc31t41j20i804zdgo.jpg)
 
-目前作者已经完善了番号提取机制，功能较为强大，可提取上述文件名的的番号，如果出现提取失败或者异常的情况，请用以下规则命名<br>
+目前作者已经完善了番号提取机制，功能较为强大，可提取上述文件名的的番号，如果出现提取失败或者异常的情况，请用以下规则命名
-**妈蛋不要喂软件那么多野鸡片子，不让软件好好活了，操**
+
+
 ```
 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 ```XXX-XXX-1```,  ```1301XX-MINA_YUKA``` 这种**野鸡**番号，在javbus等资料库存在的作品。<br>**重要**：除了 **影片文件名**  ```XXXX-XXX-C```，后面这种-C的是指电影有中文字幕！<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>
+对于多影片重命名，可以用 [ReNamer](http://www.den4b.com/products/renamer) 来批量重命名
+
 
 ---
 ### 关于PIL/image.py
-暂时无解，可能是网络问题或者pillow模块打包问题，你可以用源码运行（要安装好第一步的模块）
+暂时无解，可能是网络问题或者pillow模块打包问题，你可以用源码运行（要安装好第一步的模块）  
+
+### 拖动法
+针对格式比较奇葩的番号  
+影片放在和程序同一目录下，拖动至```AV_Data_Capture.exe```，即可完成刮削和整理
 
 
-## 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，根据演员分类，失败的电影移动到failed文件夹中。
+### 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，根据演员分类，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，等待元数据刷新，完成
+
-## 8.关于群晖NAS
+### 把JAV_output文件夹导入到 Emby, Kodi中，等待元数据刷新，完成
-开启SMB在Windows上挂载为网络磁盘即可使用本软件，也适用于其他NAS
+
-## 9.写在后面
+### 关于群晖NAS
-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>
+开启 SMB，并在 Windows 上挂载为网络磁盘即可使用本软件，也适用于其他 NAS
-**tg官方电报群:[ 点击进群](https://t.me/joinchat/J54y1g3-a7nxJ_-WS4-KFQ)**<br>
+
+## 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?
+
+**tg官方电报群:[ 点击进群](https://t.me/joinchat/J54y1g3-a7nxJ_-WS4-KFQ)**
 
 

SiteSource/avsox.py

@@ -1,112 +1,116 @@
-import re
+import re
-from lxml import etree
+from lxml import etree
-import json
+import json
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup
-from ADC_function import *
+from ADC_function import *
-
+# import sys
-def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
+# import io
-    soup = BeautifulSoup(htmlcode, 'lxml')
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
-    a = soup.find_all(attrs={'class': 'avatar-box'})
+
-    d = {}
+def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
-    for i in a:
+    soup = BeautifulSoup(htmlcode, 'lxml')
-        l = i.img['src']
+    a = soup.find_all(attrs={'class': 'avatar-box'})
-        t = i.span.get_text()
+    d = {}
-        p2 = {t: l}
+    for i in a:
-        d.update(p2)
+        l = i.img['src']
-    return d
+        t = i.span.get_text()
-def getTitle(a):
+        p2 = {t: l}
-    try:
+        d.update(p2)
-        html = etree.fromstring(a, etree.HTMLParser())
+    return d
-        result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0]
+def getTitle(a):
-        return result.replace('/', '')
+    try:
-    except:
+        html = etree.fromstring(a, etree.HTMLParser())
-        return ''
+        result = str(html.xpath('/html/body/div[2]/h3/text()')).strip(" ['']") #[0]
-def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+        return result.replace('/', '')
-    soup = BeautifulSoup(a, 'lxml')
+    except:
-    a = soup.find_all(attrs={'class': 'avatar-box'})
+        return ''
-    d = []
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
-    for i in a:
+    soup = BeautifulSoup(a, 'lxml')
-        d.append(i.span.get_text())
+    a = soup.find_all(attrs={'class': 'avatar-box'})
-    return d
+    d = []
-def getStudio(a):
+    for i in a:
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        d.append(i.span.get_text())
-    result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ')
+    return d
-    return result1
+def getStudio(a):
-def getRuntime(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//p[contains(text(),"制作商: ")]/following-sibling::p[1]/a/text()')).strip(" ['']").replace("', '",' ')
-    result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']")
+    return result1
-    return result1
+def getRuntime(a):
-def getLabel(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//span[contains(text(),"长度:")]/../text()')).strip(" ['分钟']")
-    result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']")
+    return result1
-    return result1
+def getLabel(a):
-def getNum(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//p[contains(text(),"系列:")]/following-sibling::p[1]/a/text()')).strip(" ['']")
-    result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']")
+    return result1
-    return result1
+def getNum(a):
-def getYear(release):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    try:
+    result1 = str(html.xpath('//span[contains(text(),"识别码:")]/../span[2]/text()')).strip(" ['']")
-        result = str(re.search('\d{4}',release).group())
+    return result1
-        return result
+def getYear(release):
-    except:
+    try:
-        return release
+        result = str(re.search('\d{4}',release).group())
-def getRelease(a):
+        return result
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    except:
-    result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']")
+        return release
-    return result1
+def getRelease(a):
-def getCover(htmlcode):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result1 = str(html.xpath('//span[contains(text(),"发行时间:")]/../text()')).strip(" ['']")
-    result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']")
+    return result1
-    return result
+def getCover(htmlcode):
-def getCover_small(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')).strip(" ['']")
-    result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
+    return result
-    return result
+def getCover_small(htmlcode):
-def getTag(a):  # 获取演员
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    soup = BeautifulSoup(a, 'lxml')
+    result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
-    a = soup.find_all(attrs={'class': 'genre'})
+    return result
-    d = []
+def getTag(a):  # 获取演员
-    for i in a:
+    soup = BeautifulSoup(a, 'lxml')
-        d.append(i.get_text())
+    a = soup.find_all(attrs={'class': 'genre'})
-    return d
+    d = []
-
+    for i in a:
-def main(number):
+        d.append(i.get_text())
-    a = get_html('https://avsox.host/cn/search/' + number)
+    return d
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+
-    result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
+def main(number):
-    if result1 == '' or result1 == 'null' or result1 == 'None':
+    url = 'https://avsox.host/cn/search/' + number
-        a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_'))
+    a = get_html(url)
-        print(a)
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
-        result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
+    if result1 == '' or result1 == 'null' or result1 == 'None':
-        if result1 == '' or result1 == 'null' or result1 == 'None':
+        a = get_html('https://avsox.host/cn/search/' + number.replace('-', '_'))
-            a = get_html('https://avsox.host/cn/search/' + number.replace('_', ''))
+        print(a)
-            print(a)
+        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-            html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
-            result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
+        if result1 == '' or result1 == 'null' or result1 == 'None':
-    web = get_html(result1)
+            a = get_html('https://avsox.host/cn/search/' + number.replace('_', ''))
-    soup = BeautifulSoup(web, 'lxml')
+            print(a)
-    info = str(soup.find(attrs={'class': 'row movie'}))
+            html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    dic = {
+            result1 = str(html.xpath('//*[@id="waterfall"]/div/a/@href')).strip(" ['']")
-        'actor': getActor(web),
+    web = get_html(result1)
-        'title': getTitle(web).strip(getNum(web)),
+    soup = BeautifulSoup(web, 'lxml')
-        'studio': getStudio(info),
+    info = str(soup.find(attrs={'class': 'row movie'}))
-        'outline': '',#
+    dic = {
-        'runtime': getRuntime(info),
+        'actor': getActor(web),
-        'director': '', #
+        'title': getTitle(web).strip(getNum(web)),
-        'release': getRelease(info),
+        'studio': getStudio(info),
-        'number': getNum(info),
+        'outline': '',#
-        'cover': getCover(web),
+        'runtime': getRuntime(info),
-        'cover_small': getCover_small(a),
+        'director': '', #
-        'imagecut': 3,
+        'release': getRelease(info),
-        'tag': getTag(web),
+        'number': getNum(info),
-        'label': getLabel(info),
+        'cover': getCover(web),
-        'year': getYear(getRelease(info)),  # str(re.search('\d{4}',getRelease(a)).group()),
+        'cover_small': getCover_small(a),
-        'actor_photo': getActorPhoto(web),
+        'imagecut': 3,
-        'website': result1,
+        'tag': getTag(web),
-        'source': 'avsox.py',
+        'label': getLabel(info),
-    }
+        'year': getYear(getRelease(info)),  # str(re.search('\d{4}',getRelease(a)).group()),
-    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        'actor_photo': getActorPhoto(web),
-    return js
+        'website': result1,
-
+        'source': 'avsox.py',
+    }
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+    return js
+
 #print(main('012717_472'))

SiteSource/fanza.py

@@ -0,0 +1,229 @@
+#!/usr/bin/python3
+# -*- coding: utf-8 -*-
+import json
+import re
+
+from lxml import etree
+
+from ADC_function import *
+
+# import sys
+# import io
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
+
+
+def getTitle(text):
+    html = etree.fromstring(text, etree.HTMLParser())
+    result = html.xpath('//*[@id="title"]/text()')[0]
+    return result
+
+
+def getActor(text):
+    # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+    html = etree.fromstring(text, etree.HTMLParser())
+    result = (
+        str(
+            html.xpath(
+                "//td[contains(text(),'出演者')]/following-sibling::td/span/a/text()"
+            )
+        )
+        .strip(" ['']")
+        .replace("', '", ",")
+    )
+    return result
+
+
+def getStudio(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    try:
+        result = html.xpath(
+            "//td[contains(text(),'メーカー')]/following-sibling::td/a/text()"
+        )[0]
+    except:
+        result = html.xpath(
+            "//td[contains(text(),'メーカー')]/following-sibling::td/text()"
+        )[0]
+    return result
+
+
+def getRuntime(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result = html.xpath("//td[contains(text(),'収録時間')]/following-sibling::td/text()")[0]
+    return re.search(r"\d+", str(result)).group()
+
+
+def getLabel(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    try:
+        result = html.xpath(
+            "//td[contains(text(),'シリーズ：')]/following-sibling::td/a/text()"
+        )[0]
+    except:
+        result = html.xpath(
+            "//td[contains(text(),'シリーズ：')]/following-sibling::td/text()"
+        )[0]
+    return result
+
+
+def getNum(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    try:
+        result = html.xpath(
+            "//td[contains(text(),'品番：')]/following-sibling::td/a/text()"
+        )[0]
+    except:
+        result = html.xpath(
+            "//td[contains(text(),'品番：')]/following-sibling::td/text()"
+        )[0]
+    return result
+
+
+def getYear(getRelease):
+    try:
+        result = str(re.search(r"\d{4}", getRelease).group())
+        return result
+    except:
+        return getRelease
+
+
+def getRelease(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    try:
+        result = html.xpath(
+            "//td[contains(text(),'発売日：')]/following-sibling::td/a/text()"
+        )[0].lstrip("\n")
+    except:
+        result = html.xpath(
+            "//td[contains(text(),'発売日：')]/following-sibling::td/text()"
+        )[0].lstrip("\n")
+    return result
+
+
+def getTag(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    try:
+        result = html.xpath(
+            "//td[contains(text(),'ジャンル：')]/following-sibling::td/a/text()"
+        )
+    except:
+        result = html.xpath(
+            "//td[contains(text(),'ジャンル：')]/following-sibling::td/text()"
+        )
+    return result
+
+
+def getCover(text, number):
+    html = etree.fromstring(text, etree.HTMLParser())
+    cover_number = number
+    try:
+        result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
+    except:
+        # sometimes fanza modify _ to \u0005f for image id
+        if "_" in cover_number:
+            cover_number = cover_number.replace("_", r"\u005f")
+        try:
+            result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0]
+        except:
+            # (TODO) handle more edge case
+            # print(html)
+            # raise exception here, same behavior as before
+            # people's major requirement is fetching the picture
+            raise ValueError("can not find image")
+    return result
+
+
+def getDirector(text):
+    html = etree.fromstring(text, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    try:
+        result = html.xpath(
+            "//td[contains(text(),'監督：')]/following-sibling::td/a/text()"
+        )[0]
+    except:
+        result = html.xpath(
+            "//td[contains(text(),'監督：')]/following-sibling::td/text()"
+        )[0]
+    return result
+
+
+def getOutline(text):
+    html = etree.fromstring(text, etree.HTMLParser())
+    try:
+        result = str(html.xpath("//div[@class='mg-b20 lh4']/text()")[0]).replace(
+            "\n", ""
+        )
+        if result == "":
+            result = str(html.xpath("//div[@class='mg-b20 lh4']//p/text()")[0]).replace(
+                "\n", ""
+            )
+    except:
+        # (TODO) handle more edge case
+        # print(html)
+        return ""
+    return result
+
+
+def main(number):
+    # fanza allow letter + number + underscore, normalize the input here
+    # @note: I only find the usage of underscore as h_test123456789
+    fanza_search_number = number
+    # AV_Data_Capture.py.getNumber() over format the input, restore the h_ prefix
+    if fanza_search_number.startswith("h-"):
+        fanza_search_number = fanza_search_number.replace("h-", "h_")
+
+    fanza_search_number = re.sub(r"[^0-9a-zA-Z_]", "", fanza_search_number).lower()
+
+    fanza_urls = [
+        "https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=",
+        "https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=",
+        "https://www.dmm.co.jp/digital/anime/-/detail/=/cid=",
+        "https://www.dmm.co.jp/mono/anime/-/detail/=/cid=",
+    ]
+    chosen_url = ""
+    for url in fanza_urls:
+        chosen_url = url + fanza_search_number
+        htmlcode = get_html(chosen_url)
+        if "404 Not Found" not in htmlcode:
+            break
+    if "404 Not Found" in htmlcode:
+        return json.dumps({"title": "",})
+    try:
+        # for some old page, the input number does not match the page
+        # for example, the url will be cid=test012
+        # but the hinban on the page is test00012
+        # so get the hinban first, and then pass it to following functions
+        fanza_hinban = getNum(htmlcode)
+        data = {
+            "title": getTitle(htmlcode).strip(getActor(htmlcode)),
+            "studio": getStudio(htmlcode),
+            "outline": getOutline(htmlcode),
+            "runtime": getRuntime(htmlcode),
+            "director": getDirector(htmlcode) if "anime" not in chosen_url else "",
+            "actor": getActor(htmlcode) if "anime" not in chosen_url else "",
+            "release": getRelease(htmlcode),
+            "number": fanza_hinban,
+            "cover": getCover(htmlcode, fanza_hinban),
+            "imagecut": 1,
+            "tag": getTag(htmlcode),
+            "label": getLabel(htmlcode),
+            "year": getYear(
+                getRelease(htmlcode)
+            ),  # str(re.search('\d{4}',getRelease(a)).group()),
+            "actor_photo": "",
+            "website": chosen_url,
+            "source": "fanza.py",
+        }
+    except:
+        data = {
+            "title": "",
+        }
+    js = json.dumps(
+        data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
+    )  # .encode('UTF-8')
+    return js
+
+
+if __name__ == "__main__":
+    # print(main("DV-1562"))
+    # 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。")
+    # print(main("ipx292"))
+    pass

SiteSource/fc2fans_club.py

@@ -0,0 +1,162 @@
+import re
+from lxml import etree#need install
+import json
+import ADC_function
+# import sys
+# import io
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
+
+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(" ['']")
+    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(" ['']")
+    return result
+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 #
+    #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 'https://fc2club.com' +  result2
+    return 'http:' + result
+def getOutline(htmlcode2):     #获取番号 #
+    html = etree.fromstring(htmlcode2, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/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()'))
+    return result.strip(" ['']").replace("'",'').replace(' ','')
+def getYear(release):
+    try:
+        result = re.search('\d{4}',release).group()
+        return result
+    except:
+        return ''
+
+def getTitle_fc2com(htmlcode): #获取厂商
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/h3/text()')[0]
+    return result
+def getActor_fc2com(htmlcode):
+    try:
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0]
+        return result
+    except:
+        return ''
+def getStudio_fc2com(htmlcode): #获取厂商
+    try:
+        html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')).strip(" ['']")
+        return result
+    except:
+        return ''
+def getNum_fc2com(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 getRelease_fc2com(htmlcode2): #
+    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_fc2com(htmlcode2): #获取厂商 #
+    html = etree.fromstring(htmlcode2, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[1]/span/img/@src')).strip(" ['']")
+    return 'http:' + result
+def getOutline_fc2com(htmlcode2):     #获取番号 #
+    html = etree.fromstring(htmlcode2, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div/text()')).strip(" ['']").replace("\\n",'',10000).replace("'",'',10000).replace(', ,','').strip('  ').replace('。,',',')
+    return result
+def getTag_fc2com(number):     #获取番号
+    htmlcode = str(bytes(ADC_function.get_html('http://adult.contents.fc2.com/api/v4/article/'+number+'/tag?'),'utf-8').decode('unicode-escape'))
+    result = re.findall('"tag":"(.*?)"', htmlcode)
+    return result
+def getYear_fc2com(release):
+    try:
+        result = re.search('\d{4}',release).group()
+        return result
+    except:
+        return ''
+
+def main(number):
+    try:
+        htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/'+number+'/')
+        htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html')
+        actor = getActor(htmlcode)
+        if getActor(htmlcode) == '':
+            actor = 'FC2系列'
+        dic = {
+            'title':    getTitle(htmlcode),
+            'studio':   getStudio(htmlcode),
+            'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
+            'outline':  '',#getOutline(htmlcode2),
+            'runtime':  getYear(getRelease(htmlcode)),
+            'director': getStudio(htmlcode),
+            'actor':    actor,
+            'release':  getRelease(number),
+            'number':  'FC2-'+number,
+            'label': '',
+            'cover':    getCover(htmlcode,number,htmlcode2),
+            'imagecut': 0,
+            'tag':      getTag(htmlcode),
+            'actor_photo':'',
+            'website':  'https://fc2club.com//html/FC2-' + number + '.html',
+            'source':'https://fc2club.com//html/FC2-' + number + '.html',
+        }
+        if dic['title'] == '':
+            htmlcode2 = ADC_function.get_html('https://adult.contents.fc2.com/article/' + number + '/',cookies={'wei6H':'1'})
+            actor = getActor(htmlcode)
+            if getActor(htmlcode) == '':
+                actor = 'FC2系列'
+            dic = {
+                'title': getTitle_fc2com(htmlcode2),
+                'studio': getStudio_fc2com(htmlcode2),
+                'year': '',  # str(re.search('\d{4}',getRelease(number)).group()),
+                'outline': getOutline_fc2com(htmlcode2),
+                'runtime': getYear_fc2com(getRelease(htmlcode2)),
+                'director': getStudio_fc2com(htmlcode2),
+                'actor': actor,
+                'release': getRelease_fc2com(number),
+                'number': 'FC2-' + number,
+                'cover': getCover_fc2com(htmlcode2),
+                'imagecut': 0,
+                'tag': getTag_fc2com(number),
+                'label': '',
+                'actor_photo': '',
+                'website': 'http://adult.contents.fc2.com/article/' + number + '/',
+                'source': 'http://adult.contents.fc2.com/article/' + number + '/',
+            }
+    except Exception as e:
+        # (TODO) better handle this
+        # print(e)
+        dic = {"title": ""}
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
+    return js
+
+
+#print(main('1252953'))

SiteSource/javbus.py

@@ -1,138 +1,139 @@
-import re
+import re
-from pyquery import PyQuery as pq#need install
+from pyquery import PyQuery as pq#need install
-from lxml import etree#need install
+from lxml import etree#need install
-from bs4 import BeautifulSoup#need install
+from bs4 import BeautifulSoup#need install
-import json
+import json
-from ADC_function import *
+from ADC_function import *
-
+
-def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
+def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
-    soup = BeautifulSoup(htmlcode, 'lxml')
+    soup = BeautifulSoup(htmlcode, 'lxml')
-    a = soup.find_all(attrs={'class': 'star-name'})
+    a = soup.find_all(attrs={'class': 'star-name'})
-    d={}
+    d={}
-    for i in a:
+    for i in a:
-        l=i.a['href']
+        l=i.a['href']
-        t=i.get_text()
+        t=i.get_text()
-        html = etree.fromstring(get_html(l), etree.HTMLParser())
+        html = etree.fromstring(get_html(l), etree.HTMLParser())
-        p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
+        p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
-        p2={t:p}
+        p2={t:p}
-        d.update(p2)
+        d.update(p2)
-    return d
+    return d
-def getTitle(htmlcode):  #获取标题
+def getTitle(htmlcode):  #获取标题
-    doc = pq(htmlcode)
+    doc = pq(htmlcode)
-    title=str(doc('div.container h3').text()).replace(' ','-')
+    title=str(doc('div.container h3').text()).replace(' ','-')
-    try:
+    try:
-        title2 = re.sub('n\d+-','',title)
+        title2 = re.sub('n\d+-','',title)
-        return title2
+        return title2
-    except:
+    except:
-        return title
+        return title
-def getStudio(htmlcode): #获取厂商
+def getStudio(htmlcode): #获取厂商
-    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
-    return result
+    return result
-def getYear(htmlcode):   #获取年份
+def getYear(htmlcode):   #获取年份
-    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
-    return result
+    return result
-def getCover(htmlcode):  #获取封面链接
+def getCover(htmlcode):  #获取封面链接
-    doc = pq(htmlcode)
+    doc = pq(htmlcode)
-    image = doc('a.bigImage')
+    image = doc('a.bigImage')
-    return image.attr('href')
+    return image.attr('href')
-def getRelease(htmlcode): #获取出版日期
+def getRelease(htmlcode): #获取出版日期
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
-    return result
+    return result
-def getRuntime(htmlcode): #获取分钟
+def getRuntime(htmlcode): #获取分钟
-    soup = BeautifulSoup(htmlcode, 'lxml')
+    soup = BeautifulSoup(htmlcode, 'lxml')
-    a = soup.find(text=re.compile('分鐘'))
+    a = soup.find(text=re.compile('分鐘'))
-    return a
+    return a
-def getActor(htmlcode):   #获取女优
+def getActor(htmlcode):   #获取女优
-    b=[]
+    b=[]
-    soup=BeautifulSoup(htmlcode,'lxml')
+    soup=BeautifulSoup(htmlcode,'lxml')
-    a=soup.find_all(attrs={'class':'star-name'})
+    a=soup.find_all(attrs={'class':'star-name'})
-    for i in a:
+    for i in a:
-        b.append(i.get_text())
+        b.append(i.get_text())
-    return b
+    return b
-def getNum(htmlcode):     #获取番号
+def getNum(htmlcode):     #获取番号
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
-    return result
+    return result
-def getDirector(htmlcode): #获取导演
+def getDirector(htmlcode): #获取导演
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
-    return result
+    return result
-def getOutline(htmlcode):  #获取演员
+def getOutline(htmlcode):  #获取演员
-    doc = pq(htmlcode)
+    doc = pq(htmlcode)
-    result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
+    result = str(doc('tr td div.mg-b20.lh4 p.mg-b20').text())
-    return result
+    return result
-def getSerise(htmlcode):
+def getSerise(htmlcode):
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
-    return result
+    return result
-def getTag(htmlcode):  # 获取演员
+def getTag(htmlcode):  # 获取演员
-    tag = []
+    tag = []
-    soup = BeautifulSoup(htmlcode, 'lxml')
+    soup = BeautifulSoup(htmlcode, 'lxml')
-    a = soup.find_all(attrs={'class': 'genre'})
+    a = soup.find_all(attrs={'class': 'genre'})
-    for i in a:
+    for i in a:
-        if 'onmouseout' in str(i):
+        if 'onmouseout' in str(i):
-            continue
+            continue
-        tag.append(i.get_text())
+        tag.append(i.get_text())
-    return tag
+    return tag
-
+
-
+
-def main(number):
+def main(number):
-    try:
+    try:
-        htmlcode = get_html('https://www.javbus.com/' + number)
+        htmlcode = get_html('https://www.javbus.com/' + number)
-        try:
+        try:
-            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("-", ''))
-        except:
+        except:
-            dww_htmlcode = ''
+            dww_htmlcode = ''
-        dic = {
+        dic = {
-            'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
+            'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
-            'studio': getStudio(htmlcode),
+            'studio': getStudio(htmlcode),
-            'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
+            'year': str(re.search('\d{4}', getYear(htmlcode)).group()),
-            'outline': getOutline(dww_htmlcode),
+            'outline': getOutline(dww_htmlcode),
-            'runtime': getRuntime(htmlcode),
+            'runtime': getRuntime(htmlcode),
-            'director': getDirector(htmlcode),
+            'director': getDirector(htmlcode),
-            'actor': getActor(htmlcode),
+            'actor': getActor(htmlcode),
-            'release': getRelease(htmlcode),
+            'release': getRelease(htmlcode),
-            'number': getNum(htmlcode),
+            'number': getNum(htmlcode),
-            'cover': getCover(htmlcode),
+            'cover': getCover(htmlcode),
-            'imagecut': 1,
+            'imagecut': 1,
-            'tag': getTag(htmlcode),
+            'tag': getTag(htmlcode),
-            'label': getSerise(htmlcode),
+            'label': getSerise(htmlcode),
-            'actor_photo': getActorPhoto(htmlcode),
+            'actor_photo': getActorPhoto(htmlcode),
-            'website': 'https://www.javbus.com/' + number,
+            'website': 'https://www.javbus.com/' + number,
-            'source' : 'javbus.py',
+            'source' : 'javbus.py',
-        }
+        }
-        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
-        return js
+        return js
-    except:
+    except:
-        return main_uncensored(number)
+        return main_uncensored(number)
-
+
-def main_uncensored(number):
+
-    htmlcode = get_html('https://www.javbus.com/' + number)
+def main_uncensored(number):  # 无码
-    dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+    htmlcode = get_html('https://www.javbus.com/' + number)
-    if getTitle(htmlcode) == '':
+    dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
-        htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
+    if getTitle(htmlcode) == '':
-        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
+        htmlcode = get_html('https://www.javbus.com/' + number.replace('-','_'))
-    dic = {
+        dww_htmlcode = get_html("https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=" + number.replace("-", ''))
-        'title': str(re.sub('\w+-\d+-','',getTitle(htmlcode))).replace(getNum(htmlcode)+'-',''),
+    dic = {
-        'studio': getStudio(htmlcode),
+        'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))).replace(getNum(htmlcode)+'-', ''),
-        'year': getYear(htmlcode),
+        'studio': getStudio(htmlcode),
-        'outline': getOutline(dww_htmlcode),
+        'year': getYear(htmlcode),
-        'runtime': getRuntime(htmlcode),
+        'outline': getOutline(dww_htmlcode),
-        'director': getDirector(htmlcode),
+        'runtime': getRuntime(htmlcode),
-        'actor': getActor(htmlcode),
+        'director': getDirector(htmlcode),
-        'release': getRelease(htmlcode),
+        'actor': getActor(htmlcode),
-        'number': getNum(htmlcode),
+        'release': getRelease(htmlcode),
-        'cover': getCover(htmlcode),
+        'number': getNum(htmlcode),
-        'tag': getTag(htmlcode),
+        'cover': getCover(htmlcode),
-        'label': getSerise(htmlcode),
+        'tag': getTag(htmlcode),
-        'imagecut': 0,
+        'label': getSerise(htmlcode),
-        'actor_photo': '',
+        'imagecut': 0,
-        'website': 'https://www.javbus.com/' + number,
+        'actor_photo': '',
-        'source': 'javbus.py',
+        'website': 'https://www.javbus.com/' + number,
-    }
+        'source': 'javbus.py',
-    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+    }
-    return js
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
-
+    return js
+

SiteSource/javdb.py

@@ -1,152 +1,123 @@
-import re
+import re
-from lxml import etree
+from lxml import etree
-import json
+import json
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup
-from ADC_function import *
+from ADC_function import *
-
+# import sys
-def getTitle(a):
+# import io
-    try:
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
-        html = etree.fromstring(a, etree.HTMLParser())
+
-        result = str(html.xpath('/html/body/section/div/h2/strong/text()')).strip(" ['']")
+def getTitle(a):
-        return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', '').replace(' : ', ''))
+    html = etree.fromstring(a, etree.HTMLParser())
-    except:
+    result = html.xpath("/html/body/section/div/h2/strong/text()")[0]
-        return re.sub('.*\] ', '', result.replace('/', ',').replace('\\xa0', ''))
+    return result
-def getActor(a):  # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+def getActor(a):  # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"演員")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
+    return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',').replace(',', ', ')
-def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
+def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
-    a = actor.split(',')
+    a = actor.split(',')
-    d={}
+    d={}
-    for i in a:
+    for i in a:
-        p={i:''}
+        p={i:''}
-        d.update(p)
+        d.update(p)
-    return d
+    return d
-def getStudio(a):
+def getStudio(a):
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
+    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
-def getRuntime(a):
+def getRuntime(a):
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"時長")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').rstrip('mi')
+    return str(result1 + result2).strip('+').rstrip('mi')
-def getLabel(a):
+def getLabel(a):
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"系列")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
+    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
-def getNum(a):
+def getNum(a):
-    html = etree.fromstring(a, etree.HTMLParser())
+    html = etree.fromstring(a, etree.HTMLParser())
-    result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"番號")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result2 + result1).strip('+')
+    return str(result2 + result1).strip('+')
-def getYear(getRelease):
+def getYear(getRelease):
-    try:
+    try:
-        result = str(re.search('\d{4}', getRelease).group())
+        result = str(re.search('\d{4}', getRelease).group())
-        return result
+        return result
-    except:
+    except:
-        return getRelease
+        return getRelease
-def getRelease(a):
+def getRelease(a):
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"時間")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+')
+    return str(result1 + result2).strip('+')
-def getTag(a):
+def getTag(a):
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"类别")]/../following-sibling::span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
+    return str(result1 + result2).strip('+').replace(",\\xa0", "").replace("'", "").replace(' ', '').replace(',,', '').lstrip(',')
-def getCover_small(a):
+def getCover_small(a, index=0):
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    # same issue mentioned below,
-    result = 'http:' + html.xpath(
+    # javdb sometime returns multiple results
-        '//div[@id=\'videos\']/div[@class=\'grid columns\']/div[@class=\'grid-item column\'][1]/a['
+    # DO NOT just get the firt one, get the one with correct index number
-        '@class=\'box\']/div[@class=\'item-image fix-scale-cover\']/img/@src')[0]
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    return result
+    result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
-def getCover(htmlcode):
+    if not 'https' in result:
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+        result = 'https:' + result
-    result = str(html.xpath('/html/body/section/div/div[2]/div[1]/a/img/@src')).strip(" ['']")
+    return result
-    if result == '':
+def getCover(htmlcode):
-        result = str(html.xpath('/html/body/section/div/div[4]/div[1]/a/img/@src')).strip(" ['']")
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    return result
+    result = str(html.xpath("//div[@class='column column-video-cover']/a/img/@src")).strip(" ['']")
-def getDirector(a):
+    return result
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+def getDirector(a):
-    result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-    result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
+    result1 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
+    result2 = str(html.xpath('//strong[contains(text(),"導演")]/../following-sibling::span/a/text()')).strip(" ['']")
-def getOutline(htmlcode):
+    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+def getOutline(htmlcode):
-    result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    return result
+    result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
-def main(number):
+    return result
-    number = number.upper()
+def main(number):
-    try:
+    try:
-        a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
+        number = number.upper()
-        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        query_result = get_html('https://javdb.com/search?q=' + number + '&f=all')
-        result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0]
+        html = etree.fromstring(query_result, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
+        # javdb sometime returns multiple results,
-        dic = {
+        # and the first elememt maybe not the one we are looking for
-            'actor': getActor(b),
+        # iterate all candidates and find the match one
-            'title': getTitle(b).replace("\\n", '').replace('        ', '').replace(getActor(a), '').replace(getNum(a),
+        urls = html.xpath('//*[@id="videos"]/div/div/a/@href')
-                                                                                                             '').replace(
+        ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
-                '无码', '').replace('有码', '').lstrip(' ').replace(number,''),
+        correct_url = urls[ids.index(number)]
-            'studio': getStudio(b),
+        detail_page = get_html('https://javdb.com' + correct_url)
-            'outline': getOutline(b),
+        dic = {
-            'runtime': getRuntime(b),
+            'actor': getActor(detail_page),
-            'director': getDirector(b),
+            'title': getTitle(detail_page),
-            'release': getRelease(b),
+            'studio': getStudio(detail_page),
-            'number': getNum(b),
+            'outline': getOutline(detail_page),
-            'cover': getCover(b),
+            'runtime': getRuntime(detail_page),
-            'cover_small': getCover_small(a),
+            'director': getDirector(detail_page),
-            'imagecut': 3,
+            'release': getRelease(detail_page),
-            'tag': getTag(b),
+            'number': getNum(detail_page),
-            'label': getLabel(b),
+            'cover': getCover(detail_page),
-            'year': getYear(getRelease(b)),  # str(re.search('\d{4}',getRelease(a)).group()),
+            'cover_small': getCover_small(query_result, index=ids.index(number)),
-            'actor_photo': getActorPhoto(getActor(b)),
+            'imagecut': 3,
-            'website': 'https://javdb.com' + result1,
+            'tag': getTag(detail_page),
-            'source': 'javdb.py',
+            'label': getLabel(detail_page),
-        }
+            'year': getYear(getRelease(detail_page)),  # str(re.search('\d{4}',getRelease(a)).group()),
-        if getNum(b) != number:  # 与搜索到的番号不匹配
+            'actor_photo': getActorPhoto(getActor(detail_page)),
-            dic['title'] = ''
+            'website': 'https://javdb.com' + correct_url,
-            dic['number'] = ''
+            'source': 'javdb.py',
-        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        }
-        return js
+    except Exception as e:
-    except:
+        # print(e)
-        a = get_html('https://javdb.com/search?q=' + number + '&f=all').replace(u'\xa0', u' ')
+        dic = {"title": ""}
-        html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
-        result1 = html.xpath('//*[@id="videos"]/div/div/a/@href')[0]
+    return js
-        print(html.xpath('//*[@id="videos"]/div/div/a/@href'))
+
-        b = get_html('https://javdb.com' + result1).replace(u'\xa0', u' ')
+# main('DV-1562')
-        dic = {
+# 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。")
-            'actor': getActor(b),
+#print(main('ipx-292'))
-            'title': getTitle(b).replace("\\n", '').replace('        ', '').replace(getActor(a), '').replace(
-                getNum(b),
-                '').replace(
-                '无码', '').replace('有码', '').lstrip(' ').replace(number,''),
-            'studio': getStudio(b),
-            'outline': getOutline(b),
-            'runtime': getRuntime(b),
-            'director': getDirector(b),
-            'release': getRelease(b),
-            'number': getNum(b),
-            'cover': getCover(b),
-            'cover_small': getCover_small(a),
-            'imagecut': 3,
-            'tag': getTag(b),
-            'label': getLabel(b),
-            'year': getYear(getRelease(b)),  # str(re.search('\d{4}',getRelease(a)).group()),
-            'actor_photo': getActorPhoto(getActor(b)),
-            'website': 'https://javdb.com' + result1,
-            'source': 'javdb.py',
-        }
-        if getNum(b) != number:  # 与搜索到的番号不匹配
-            dic['title'] = ''
-            dic['number'] = ''
-        js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
-        return js
-
-# main('DV-1562')
-# 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。")
-# print(get_html('https://javdb1.com/v/WwZ0Q'))

SiteSource/mgstage.py

@@ -1,105 +1,108 @@
-import re
+import re
-from lxml import etree
+from lxml import etree
-import json
+import json
-from bs4 import BeautifulSoup
+from bs4 import BeautifulSoup
-from ADC_function import *
+from ADC_function import *
-
+# import sys
-def getTitle(a):
+# import io
-    try:
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
-        html = etree.fromstring(a, etree.HTMLParser())
+
-        result = str(html.xpath('//*[@id="center_column"]/div[1]/h1/text()')).strip(" ['']")
+def getTitle(a):
-        return result.replace('/', ',')
+    try:
-    except:
+        html = etree.fromstring(a, etree.HTMLParser())
-        return ''
+        result = str(html.xpath('//*[@id="center_column"]/div[1]/h1/text()')).strip(" ['']")
-def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
+        return result.replace('/', ',')
-    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+    except:
-    result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+        return ''
-    result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+def getActor(a): #//*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text()
-    return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
-def getStudio(a):
+    result1=str(html.xpath('//th[contains(text(),"出演：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
+    result2=str(html.xpath('//th[contains(text(),"出演：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    return str(result1+result2).strip('+').replace("', '",'').replace('"','').replace('/',',')
-    result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+def getStudio(a):
-    return str(result1+result2).strip('+').replace("', '",'').replace('"','')
+    html = etree.fromstring(a, etree.HTMLParser()) #//table/tr[1]/td[1]/text()
-def getRuntime(a):
+    result1=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result2=str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+    return str(result1+result2).strip('+').replace("', '",'').replace('"','')
-    result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
+def getRuntime(a):
-    return str(result1 + result2).strip('+').rstrip('mi')
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-def getLabel(a):
+    result1 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result2 = str(html.xpath('//th[contains(text(),"収録時間：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip('\\n')
-    result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+    return str(result1 + result2).strip('+').rstrip('mi')
-        '\\n')
+def getLabel(a):
-    result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        '\\n')
+    result1 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+        '\\n')
-def getNum(a):
+    result2 = str(html.xpath('//th[contains(text(),"シリーズ：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        '\\n')
-    result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
-        '\\n')
+def getNum(a):
-    result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        '\\n')
+    result1 = str(html.xpath('//th[contains(text(),"品番：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return str(result1 + result2).strip('+')
+        '\\n')
-def getYear(getRelease):
+    result2 = str(html.xpath('//th[contains(text(),"品番：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
-    try:
+        '\\n')
-        result = str(re.search('\d{4}',getRelease).group())
+    return str(result1 + result2).strip('+')
-        return result
+def getYear(getRelease):
-    except:
+    try:
-        return getRelease
+        result = str(re.search('\d{4}',getRelease).group())
-def getRelease(a):
+        return result
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    except:
-    result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+        return getRelease
-        '\\n')
+def getRelease(a):
-    result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        '\\n')
+    result1 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return str(result1 + result2).strip('+')
+        '\\n')
-def getTag(a):
+    result2 = str(html.xpath('//th[contains(text(),"配信開始日：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        '\\n')
-    result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+    return str(result1 + result2).strip('+')
-        '\\n')
+def getTag(a):
-    result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        '\\n')
+    result1 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','')
+        '\\n')
-def getCover(htmlcode):
+    result2 = str(html.xpath('//th[contains(text(),"ジャンル：")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+        '\\n')
-    result = str(html.xpath('//*[@id="center_column"]/div[1]/div[1]/div/div/h2/img/@src')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','')
-    #                    /html/body/div[2]/article[2]/div[1]/div[1]/div/div/h2/img/@src
+def getCover(htmlcode):
-    return result
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-def getDirector(a):
+    result = str(html.xpath('//*[@id="center_column"]/div[1]/div[1]/div/div/h2/img/@src')).strip(" ['']")
-    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    #                    /html/body/div[2]/article[2]/div[1]/div[1]/div/div/h2/img/@src
-    result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
+    return result
-        '\\n')
+def getDirector(a):
-    result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
-        '\\n')
+    result1 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/a/text()')).strip(" ['']").strip('\\n    ').strip(
-    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
+        '\\n')
-def getOutline(htmlcode):
+    result2 = str(html.xpath('//th[contains(text(),"シリーズ")]/../td/text()')).strip(" ['']").strip('\\n    ').strip(
-    html = etree.fromstring(htmlcode, etree.HTMLParser())
+        '\\n')
-    result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
-    return result
+def getOutline(htmlcode):
-def main(number2):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
-    number=number2.upper()
+    result = str(html.xpath('//*[@id="introduction"]/dd/p[1]/text()')).strip(" ['']")
-    htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'}))
+    return result
-    soup = BeautifulSoup(htmlcode, 'lxml')
+def main(number2):
-    a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n                                        ','').replace('                                ','').replace('\n                            ','').replace('\n                        ','')
+    number=number2.upper()
-    dic = {
+    htmlcode=str(get_html('https://www.mgstage.com/product/product_detail/'+str(number)+'/',cookies={'adc':'1'}))
-        'title': getTitle(htmlcode).replace("\\n",'').replace('        ',''),
+    soup = BeautifulSoup(htmlcode, 'lxml')
-        'studio': getStudio(a),
+    a = str(soup.find(attrs={'class': 'detail_data'})).replace('\n                                        ','').replace('                                ','').replace('\n                            ','').replace('\n                        ','')
-        'outline': getOutline(htmlcode),
+    dic = {
-        'runtime': getRuntime(a),
+        'title': getTitle(htmlcode).replace("\\n",'').replace('        ',''),
-        'director': getDirector(a),
+        'studio': getStudio(a),
-        'actor': getActor(a),
+        'outline': getOutline(htmlcode),
-        'release': getRelease(a),
+        'runtime': getRuntime(a),
-        'number': getNum(a),
+        'director': getDirector(a),
-        'cover': getCover(htmlcode),
+        'actor': getActor(a),
-        'imagecut': 0,
+        'release': getRelease(a),
-        'tag': getTag(a),
+        'number': getNum(a),
-        'label':getLabel(a),
+        'cover': getCover(htmlcode),
-        'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
+        'imagecut': 0,
-        'actor_photo': '',
+        'tag': getTag(a),
-        'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
+        'label':getLabel(a),
-        'source': 'siro.py',
+        'year': getYear(getRelease(a)),  # str(re.search('\d{4}',getRelease(a)).group()),
-    }
+        'actor_photo': '',
-    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+        'website':'https://www.mgstage.com/product/product_detail/'+str(number)+'/',
-    return js
+        'source': 'mgstage.py',
-
+    }
-#print(main('SIRO-3607'))
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+    return js
+
+#print(main('SIRO-3607'))

TestPathNFO.txt

@@ -0,0 +1,41 @@
+/Volumes/Adult/Files/ノ瀬アメリ/Tokyo Hot N0646.avi
+/Volumes/Adult/Files/ノ瀬アメリ/MKBD_S03-MaRieS.mp4
+/Volumes/192.168.2.100/Adult/Files/Aki Sasaki Megapack/HODV-21299.mkv
+/Volumes/Adult/Files/[Tokyo-Hot] [n1180] 美人秘書3穴串刺奉仕残業 (中井綾香 Ayaka Nakai)/(Tokyo-Hot)(n1180)美人秘書3穴串刺奉仕残業 中井綾香.mp4
+/mcdv47.avi
+/mcdv-47.avi
+/mcdv-047.mp4
+/mcdv047.mp4
+/mcdv0047.mp4
+/1pondo-070409_621.mp4
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#1(181222)@RUNBKK/No-Watermarked/HOBD00015.FHD2.wmv
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 1/720p/RBD-406_1.mp4
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 1/720p/MDYD-664B.mp4
+/Volumes/Adult/Files/107NTTR-037A.mp4
+/Volumes/Adult/Files/Yua.Mikami-PML/SNIS-986 国民的アイドル アドレナリン大爆発！禁欲1ヶ月後の性欲剥き出し焦らされトランスFUCK 三上悠亜【桃花族】.mp4
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 2/FHD/UPSM-109_2.mkv
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#2(181231)@RUNBKK/No-Watermarked/PPT003.SD3.wmv
+/Volumes/Adult/Files/波多野结衣/THE波多野結衣 ぶっかけ50連発！ CD1.wmv
+/Volumes/Adult/Files/波多野结衣/欲しがり 後編 波多野結衣.wmv
+/Volumes/Adult/Files/波多野结衣/欲しがり 前編 波多野結衣.wmv
+/Volumes/Adult/Files/波多野结衣/加勒比 062212-055 夫の目の前で妻が ~元上司に縛られて～波多野結衣～.rmvb
+/Volumes/Adult/Files/波多野结衣/022213-271-carib-whole_s.mp4
+/Volumes/Adult/Files/SKYHD-001~010/SKYHD-009_H265.mkv
+/Volumes/Adult/Files/大桥步兵合集/LAFBD-41.LaForet.Girl.41.angel.and.devil.Miku.Ohashi.2015.Bluray.1080p.x264.ac3-MTeam.mkv
+/Volumes/Adult/Files/大桥步兵合集/032015_161-caribpr-high.mp4
+/Volumes/Adult/Files/桃谷绘里香(桃谷エリカ) 所有作品集合/118ppt00016hhb2.mkv
+/Volumes/Adult/Files/tia/soe935C.HD.wmv
+/Volumes/Adult/Files/SKYHD-011~020/SKYHD-020_H265.mkv
+/Volumes/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/VR/sivr00008_E.mp4
+/Volumes/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/DMM.Video/onsd00899hhb3.mp4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/SHKD-744 営業課長の湿ったパンスト 里美ゆりあ.mp4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/ABP-627 裏・鈴村あいり-鈴村あいりのオトナの激情SEX4本番 鈴村あいり.MP4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/20 ABP-408 上原瑞穂/上原瑞穂 ABP-408 无码流出片段/[ThZu.Cc]20150909164411.m2ts
+/Volumes/Adult/Files/Caribbean-101717-520-HD/100917-515/100917-515-carib-1080p.mp4
+/Volumes/Adult/Files/ノ瀬アメリ/20081105栗栖エリカ - Sky Angel Blue 10 天舞超絕美少女天使降臨(skyhd010)(中文字幕).avi
+/Volumes/Adult/Files/ノ瀬アメリ/一ノ瀬アメリ~加勒比 VERY SEXY.wmv
+/Volumes/Adult/Files/ノ瀬アメリ/20101202一ノ瀬アメリ - 東京ブルドック05(inu006).avi
+/Volumes/Adult/Files/ノ瀬アメリ/Sky Angel Vol 80 - CD2.mp4
+/Volumes/Adult/Files/Mika Sumire すみれ美香/Caribbean-091818-755.mp4
+/Volumes/Adult/Files/Takizawa Rola/[HD]abp-031C.wmv
+/Volumes/Adult/Files/Takizawa Rola/ABP-013HDA.wmv

TestPathSpecial.txt

@@ -0,0 +1,51 @@
+/Volumes/192.168.2.100/Adult/Files/Aki Sasaki Megapack/HODV-21222.mkv
+/Volumes/Adult/Files/ノ瀬アメリ/Tokyo Hot N0646.avi
+/Volumes/Adult/Files/ノ瀬アメリ/MKBD_S03-MaRieS.mp4
+/Volumes/192.168.2.100/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/DMM.Video/onsd00899hhb3.mp4
+/Volumes/192.168.2.100/Adult/Files/Rating Top 30 JAV pack/IPTD-999-1 彼女の姉貴とイケナイ関係 Rio.wmv
+/Volumes/192.168.2.100/Adult/Files/Rating Top 30 JAV pack/IPTD-999A 彼女の姉貴とイケナイ関係 Rio.wmv
+/Volumes/192.168.2.100/Adult/Files/Rating Top 30 JAV pack/IPTD-999-A 彼女の姉貴とイケナイ関係 Rio.wmv
+/Volumes/192.168.2.100/Adult/Files/Rating Top 30 JAV pack/IPTD-999-C 彼女の姉貴とイケナイ関係 Rio.wmv
+/Volumes/192.168.2.100/Adult/Files/Rating Top 30 JAV pack/IPTD-999-B 彼女の姉貴とイケナイ関係 Rio.wmv
+/Volumes/192.168.2.100/Adult/Files/tia/soe935C.HD.wmv
+/Volumes/192.168.2.100/Adult/Files/tia/soe935B.HD.wmv
+/Volumes/192.168.2.100/Adult/Files/tia/soe935A.HD.wmv
+/Volumes/192.168.2.100/Adult/Files/tia/soe935D.HD.wmv
+/Volumes/Adult/Files/大桥步兵合集/LAFBD-41.LaForet.Girl.41.angel.and.devil.Miku.Ohashi.2015.Bluray.1080p.x264.ac3-MTeam.mkv
+/Volumes/Adult/Files/[Tokyo-Hot] [n1180] 美人秘書3穴串刺奉仕残業 (中井綾香 Ayaka Nakai)/(Tokyo-Hot)(n1180)美人秘書3穴串刺奉仕残業 中井綾香.mp4
+/mcdv47.avi
+/mcdv-47.avi
+/mcdv-047.mp4
+/mcdv047.mp4
+/mcdv0047.mp4
+/1pondo-070409_621.mp4
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#1(181222)@RUNBKK/No-Watermarked/HOBD00015.FHD2.wmv
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 1/720p/RBD-406_1.mp4
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 1/720p/MDYD-664B.mp4
+/Volumes/Adult/Files/107NTTR-037A.mp4
+/Volumes/Adult/Files/Yua.Mikami-PML/SNIS-986 国民的アイドル アドレナリン大爆発！禁欲1ヶ月後の性欲剥き出し焦らされトランスFUCK 三上悠亜【桃花族】.mp4
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 2/FHD/UPSM-109_2.mkv
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#2(181231)@RUNBKK/No-Watermarked/PPT003.SD3.wmv
+/Volumes/Adult/Files/波多野结衣/THE波多野結衣 ぶっかけ50連発！ CD1.wmv
+/Volumes/Adult/Files/波多野结衣/欲しがり 後編 波多野結衣.wmv
+/Volumes/Adult/Files/波多野结衣/欲しがり 前編 波多野結衣.wmv
+/Volumes/Adult/Files/波多野结衣/加勒比 062212-055 夫の目の前で妻が ~元上司に縛られて～波多野結衣～.rmvb
+/Volumes/Adult/Files/波多野结衣/022213-271-carib-whole_s.mp4
+/Volumes/Adult/Files/SKYHD-001~010/SKYHD-009_H265.mkv
+/Volumes/Adult/Files/大桥步兵合集/LAFBD-41.LaForet.Girl.41.angel.and.devil.Miku.Ohashi.2015.Bluray.1080p.x264.ac3-MTeam.mkv
+/Volumes/Adult/Files/大桥步兵合集/032015_161-caribpr-high.mp4
+/Volumes/Adult/Files/桃谷绘里香(桃谷エリカ) 所有作品集合/118ppt00016hhb2.mkv
+/Volumes/Adult/Files/SKYHD-011~020/SKYHD-020_H265.mkv
+/Volumes/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/VR/sivr00008_E.mp4
+/Volumes/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/DMM.Video/onsd00899hhb3.mp4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/SHKD-744 営業課長の湿ったパンスト 里美ゆりあ.mp4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/ABP-627 裏・鈴村あいり-鈴村あいりのオトナの激情SEX4本番 鈴村あいり.MP4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/20 ABP-408 上原瑞穂/上原瑞穂 ABP-408 无码流出片段/[ThZu.Cc]20150909164411.m2ts
+/Volumes/Adult/Files/Caribbean-101717-520-HD/100917-515/100917-515-carib-1080p.mp4
+/Volumes/Adult/Files/ノ瀬アメリ/20081105栗栖エリカ - Sky Angel Blue 10 天舞超絕美少女天使降臨(skyhd010)(中文字幕).avi
+/Volumes/Adult/Files/ノ瀬アメリ/一ノ瀬アメリ~加勒比 VERY SEXY.wmv
+/Volumes/Adult/Files/ノ瀬アメリ/20101202一ノ瀬アメリ - 東京ブルドック05(inu006).avi
+/Volumes/Adult/Files/ノ瀬アメリ/Sky Angel Vol 80 - CD2.mp4
+/Volumes/Adult/Files/Mika Sumire すみれ美香/Caribbean-091818-755.mp4
+/Volumes/Adult/Files/Takizawa Rola/[HD]abp-031C.wmv
+/Volumes/Adult/Files/Takizawa Rola/ABP-013HDA.wmv

TestPaths.txt

@@ -0,0 +1,50 @@
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#1(181222)@RUNBKK/No-Watermarked/HOBD00015.FHD2.wmv
+/1pondo-070409_621.mp4
+/Volumes/Adult/Files/107NTTR-037.mp4
+/Volumes/Adult/Files/107NTTR-037A.mp4
+/Volumes/Adult/Files/Yua.Mikami-PML/TEK-097 ふたりは無敵.wmv
+/Volumes/Adult/Files/Yua.Mikami-PML/SNIS-986 国民的アイドル アドレナリン大爆発！禁欲1ヶ月後の性欲剥き出し焦らされトランスFUCK 三上悠亜【桃花族】.mp4
+/Volumes/Adult/Files/Yua.Mikami-PML/SSNI-030 三上悠亜ファン感謝祭 国民的アイドル×一般ユーザー20人‘ガチファンとSEX解禁’ハメまくりスペシャル【桃花族】.mp4
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 2/FHD/MIDD-893A.mkv
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 2/FHD/UPSM-109_2.mkv
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#2(181231)@RUNBKK/No-Watermarked/PPT003.SD3.wmv
+/Volumes/Adult/Files/波多野结衣/THE波多野結衣 ぶっかけ50連発！ CD1.wmv
+/Volumes/Adult/Files/波多野结衣/欲しがり 後編 波多野結衣.wmv
+/Volumes/Adult/Files/波多野结衣/欲しがり 前編 波多野結衣.wmv
+/Volumes/Adult/Files/波多野结衣/加勒比 062212-055 夫の目の前で妻が ~元上司に縛られて～波多野結衣～.rmvb
+/Volumes/Adult/Files/波多野结衣/022213-271-carib-whole_s.mp4
+/Volumes/Adult/Files/桜木凛 Rin Sakuragi FHD Collection Pack Vol/BBI-183.wmv
+/Volumes/Adult/Files/NOP-019 芭蕾教室 水嶋あずみ/NOP019B.HD.wmv
+/Volumes/Adult/Files/一ノ瀬アメリ part2/栗栖エリカ/20081105栗栖エリカ - Sky Angel Blue 10 天舞超絕美少女天使降臨(skyhd010)(中文字幕).avi
+/Volumes/Adult/Files/一ノ瀬アメリ part2/Max Girls/Max Girls 24(xv804)伊東遥,Rio,小沢アリス,葉月しおり,一ノ瀬アメリ,ひなた結衣,藤崎りお.avi
+/Volumes/Adult/Files/一ノ瀬アメリ part2/ノ瀬アメリAmeri Ichinose/20091127一ノ瀬アメリ - 一見面就做愛(xv801).avi
+/Volumes/Adult/Files/Aki Sasaki Megapack/MSTG-003.mkv
+/Volumes/Adult/Files/SKYHD-001~010/SKYHD-009_H265.mkv
+/Volumes/Adult/Files/大桥步兵合集/LAFBD-41.LaForet.Girl.41.angel.and.devil.Miku.Ohashi.2015.Bluray.1080p.x264.ac3-MTeam.mkv
+/Volumes/Adult/Files/大桥步兵合集/032015_161-caribpr-high.mp4
+/Volumes/Adult/Files/桃谷绘里香(桃谷エリカ) 所有作品集合/(PRESTIGE)(ABP-171)彼女のお姉さんは、誘惑ヤリたがり娘。桃谷エリカ.wmv
+/Volumes/Adult/Files/桃谷绘里香(桃谷エリカ) 所有作品集合/(PRESTIGE)(ABP-145)濃密な接吻と欲情ベロキス性交 04 桃谷エリカ.wmv
+/Volumes/Adult/Files/桃谷绘里香(桃谷エリカ) 所有作品集合/118ppt00016hhb2.mkv
+/Volumes/Adult/Files/tia/soe935C.HD.wmv
+/Volumes/Adult/Files/SKYHD-011~020/SKYHD-020_H265.mkv
+/Volumes/Adult/Files/sakumomo1203-PML/IDBD-795 ももに夢中 2018年日本人にもっとも愛された女優桜空ももPREMIUM BOX8時間BEST.mp4
+/Volumes/Adult/Files/sakumomo1203-PML/IDBD-768 Gカップグラビアアイドル桜空もも初ベスト 原石 2【桃花族】.mp4
+/Volumes/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/VR/sivr00008_E.mp4
+/Volumes/Adult/Files/RION(りおん).Utsunomiya.Shion.宇都宮しをん(うつのみやしをん)/DMM.Video/onsd00899hhb3.mp4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/SHKD-744 営業課長の湿ったパンスト 里美ゆりあ.mp4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/ABP-627 裏・鈴村あいり-鈴村あいりのオトナの激情SEX4本番 鈴村あいり.MP4
+/Volumes/Adult/Files/Rating Top 30 JAV pack/20 ABP-408 上原瑞穂/上原瑞穂 ABP-408 无码流出片段/[ThZu.Cc]20150909164411.m2ts
+/Volumes/Adult/Files/Caribbean-101717-520-HD/100917-515/100917-515-carib-1080p.mp4
+/Volumes/Adult/Files/Kirara Asuka (@明日花キララ) FHD Pack Vol#3(190119)@RUNBKK/No-Watermarked/SOE976.FHD3.wmv
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 1/720p/RBD-406_1.mp4
+/Volumes/Adult/Files/(1.18TB) Julia movie pack collection Part 1/720p/MDYD-664B.mp4
+/Volumes/Adult/Files/ノ瀬アメリ/20081105栗栖エリカ - Sky Angel Blue 10 天舞超絕美少女天使降臨(skyhd010)(中文字幕).avi
+/Volumes/Adult/Files/ノ瀬アメリ/一ノ瀬アメリ~加勒比 VERY SEXY.wmv
+/Volumes/Adult/Files/ノ瀬アメリ/20101202一ノ瀬アメリ - 東京ブルドック05(inu006).avi
+/Volumes/Adult/Files/ノ瀬アメリ/Sky Angel Vol 80 - CD2.mp4
+/Volumes/Adult/Files/ノ瀬アメリ/20100226一ノ瀬アメリ - OL Style 制服(xv827).avi
+/Volumes/Adult/Files/Mika Sumire すみれ美香/Caribbean-091818-755.mp4
+/Volumes/Adult/Files/[Tokyo-Hot] [n1180] 美人秘書3穴串刺奉仕残業 (中井綾香 Ayaka Nakai)/(Tokyo-Hot)(n1180)美人秘書3穴串刺奉仕残業 中井綾香.mp4
+/Volumes/Adult/Files/Takizawa Rola/[HD]abp-031C.wmv
+/Volumes/Adult/Files/Takizawa Rola/ABP-013HDA.wmv
+/Volumes/Adult/Files/Uncensored Mosaic Removal Megapack/ADN-017(Asami Ogawa).mp4

config.ini

@@ -1,27 +1,35 @@
 [common]
-main_mode=1
+main_mode=2
-failed_output_folder=failed
+# 路径均为绝对路径，不要写入" '等符号
-success_output_folder=JAV_output
+search_folder=          /Volumes/192.168.2.100/Adult/AVTest
+# 如果failed_output_folder 为空，抓取不到相关信息的视频将不回移动
+failed_output_folder=   /Volumes/192.168.2.100/Adult/UnknownStars
+success_output_folder=  /Volumes/192.168.2.100/Adult/Files
+#临时资源存储路径，比如xxx.nfo 海报图
+temp_folder=            /Volumes/192.168.2.100/Adult/temp
+# 如果是远程挂载的盘符，建议不开启创建软连接：软连接链接的是绝对路径，远程NAS上的路径和本地挂载的路径一般不同。
 soft_link=0
 
 [proxy]
-proxy=
+#例子为socks代理配置，可以 =后留空
-timeout=10
+proxy=      socks5h://127.0.0.1:1081
-retry=3
+timeout=    10
+retry=      5
 
 [Name_Rule]
-location_rule=actor+'/'+number
+location_rule=  actor+'/'+number
-naming_rule=number+'-'+title
+naming_rule=    number+'-'+title
 
 [update]
 update_check=1
 
 [media]
-media_warehouse=emby
 #emby or plex or kodi ,emby=jellyfin
+media_warehouse=EMBY
 
 [escape]
 literals=\()
+folders=/Volumes/Adult/UnknownStars,/Volumes/Adult/Stars
 
-[movie_location]
+[debug_mode]
-path=
+switch=1

fc2fans_club.py

@@ -1,84 +0,0 @@
-import re
-from lxml import etree#need install
-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(" ['']")
-    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(" ['']")
-    return result
-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 #
-    #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 'https://fc2club.com' +  result2
-    return 'http:' + result
-def getOutline(htmlcode2):     #获取番号 #
-    html = etree.fromstring(htmlcode2, etree.HTMLParser())
-    result = str(html.xpath('/html/body/div[1]/div[2]/div[2]/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()'))
-    return result.strip(" ['']").replace("'",'').replace(' ','')
-def getYear(release):
-    try:
-        result = re.search('\d{4}',release).group()
-        return result
-    except:
-        return ''
-
-def main(number):
-    htmlcode2 = ADC_function.get_html('http://adult.contents.fc2.com/article_search.php?id='+number+'&utm_source=aff_php&utm_medium=source_code&utm_campaign=from_aff_php')
-    htmlcode = ADC_function.get_html('https://fc2club.com//html/FC2-' + number + '.html')
-    actor = getActor(htmlcode)
-    if getActor(htmlcode) == '':
-        actor = 'FC2系列'
-    dic = {
-        'title':    getTitle(htmlcode),
-        'studio':   getStudio(htmlcode),
-        'year': '',#str(re.search('\d{4}',getRelease(number)).group()),
-        'outline':  getOutline(htmlcode2),
-        'runtime':  getYear(getRelease(htmlcode)),
-        'director': getStudio(htmlcode),
-        'actor':    actor,
-        'release':  getRelease(number),
-        'number':  'FC2-'+number,
-        'cover':    getCover(htmlcode,number,htmlcode2),
-        'imagecut': 0,
-        'tag':      getTag(htmlcode),
-        'actor_photo':'',
-        'website':  'https://fc2club.com//html/FC2-' + number + '.html',
-        'source':'https://fc2club.com//html/FC2-' + number + '.html',
-    }
-    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'),)#.encode('UTF-8')
-    return js
-
-#print(main('1051725'))

resource/This is readms.md's images folder

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

resource/ruquirments.txt

@@ -0,0 +1 @@
+pipenv install -rlxml bs4 pillow pyquery

test.py

@@ -0,0 +1,80 @@
+import os
+import re
+from itertools import groupby
+
+import fuckit as fuckit
+import pandas as pd
+from tenacity import retry, stop_after_delay, wait_fixed
+
+
+def go():
+    a = [1, 2, 3, 4, 5, 6]
+    # [print(x) for x in a]
+    # [print(x) for x in a]
+    a1 = groupby(a, key=lambda k: (k / 2))
+    for i in a1:
+        print(i)
+    for i in a1:
+        print(i)
+
+
+class TryDo:
+    def __init__(self, func, times=3):
+        self.tries = times
+        self.func = func
+
+    def __iter__(self):
+        self.currentTry = 1
+        return self
+
+    def __next__(self):
+        if self.currentTry > self.tries:
+            raise StopIteration(False)
+        else:
+            self.currentTry += 1
+            self.func()
+            raise StopIteration(True)
+
+    # def do(self):
+
+
+@retry(stop=stop_after_delay(3), wait=wait_fixed(2))
+def stop_after_10_s():
+    print("Stopping after 10 seconds")
+    raise Exception
+
+
+# f = iter( TryDo(do_something, 5))
+
+# stop_after_10_s()
+def errorfunc():
+    raise Exception
+
+
+def okfunc():
+    print("ok")
+
+
+# with fuckit:
+#     errorfunc()
+#     okfunc()
+# re.match()
+
+r = re.search(r'(?<=999)-?((?P<alpha>([A-Z](?![A-Z])))|(?P<num>\d(?!\d)))', "IPTD-999-B-彼女の姉貴とイケナイ関係-RIO", re.I)
+#
+print(r.groupdict())
+print(r.groupdict()['alpha'])
+print(r.group(2))
+import re
+
+line = "Cats are smarter than dogs"
+matchObj = re.search(r'(?<=a)(.*) are (.*?) .*', line, re.M | re.I)
+if matchObj:
+    print("matchObj.group() : ", matchObj.group())
+    print("matchObj.group(1) : ", matchObj.group(1))
+    print("matchObj.group(2) : ", matchObj.group(2))
+else:
+    print("No match!!")
+
+# print(r[-1])
+# print(newList)

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "2.1",
+	"version": "2.8.2",
-	"version_show":"2.1",
+	"version_show":"2.8.2",
 	"download": "https://github.com/yoshiko2/AV_Data_Capture/releases"
-}
+}