Update 3.2

ADC_function.py

@@ -13,59 +13,17 @@
 # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
 # sys.setdefaultencoding('utf-8')
 
-config_file='config.ini'
+config_file = 'config.ini'
 config = ConfigParser()
 
 if os.path.exists(config_file):
     try:
         config.read(config_file, encoding='UTF-8')
-    except:
-        print('[-]Config.ini read failed! Please use the offical file!')
-else:
-    print('[+]config.ini: not found, creating...',end='')
-    with open("config.ini", "wt", encoding='UTF-8') as code:
-        file_text = """[common]
-main_mode=1
-failed_output_folder=failed
-success_output_folder=JAV_output
-soft_link=0
-
-[proxy]
-proxy=192.168.2.2:1080
-timeout=10
-retry=3
-
-[Name_Rule]
-location_rule=actor+'/'+number
-naming_rule=number+'-'+title
-
-[update]
-update_check=1
-
-[media]
-media_warehouse=emby
-#emby or plex or kodi ,emby=jellyfin
-
-[escape]
-literals=\()/
-folders=failed,JAV_output
-
-[debug_mode]
-switch=0
-
-"""
-        print(file_text, file=code)
-    time.sleep(2)
-    print('.')
-    print('[+]config.ini: created!')
-    print('[+]Please restart the program!')
-    time.sleep(4)
-    os._exit(0)
-    try:
-        config.read(config_file, encoding='UTF-8')
-    except:
+    except Exception as e:
+        print('[-]'+e)
         print('[-]Config.ini read failed! Please use the offical file!')
 
+
 def get_network_settings():
     try:
         proxy = config["proxy"]["proxy"]

AV_Data_Capture.py

@@ -33,15 +33,15 @@ def argparse_function(switch):
     parser = argparse.ArgumentParser()
     parser.add_argument("file", default='',nargs='?', help="Single Movie file path.")
     parser.add_argument("-c", "--config", default='config.ini', nargs='?', help="The config file Path.")
-    parser.add_argument("-e", "--exit", default='1', nargs='?', help="Exit Switch 1:Press enter key to exit.  2:Auto exit.")
+    parser.add_argument("-a", "--auto-exit", dest='autoexit', action="store_true", help="Auto exit after program complete")
     args = parser.parse_args()
     if switch == 1:
         if args.file == '':
             return ''
     elif switch == 2:
         return args.config
     elif switch == 3:
-        return args.exit
+        return args.autoexit
 
 def movie_lists(root, escape_folder):
     for folder in escape_folder:
@@ -100,10 +100,10 @@ def getNumber(filepath,absolute_path = False):
 
 
 if __name__ == '__main__':
-    version = '3.1.2'
+    version = '3.2'
     config_file = argparse_function(2)
     config = ConfigParser()
-    config.read(config_file, encoding='UTF-8')
+    config.read(argparse_function(2), encoding='UTF-8')
     success_folder = config['common']['success_output_folder']
     failed_folder = config['common']['failed_output_folder']  # 失败输出目录
     escape_folder = config['escape']['folders']  # 多级目录刮削需要排除的目录
@@ -148,7 +148,7 @@ def getNumber(filepath,absolute_path = False):
             core_main(i, getNumber(i), config_file=config_file)
             print("[*]======================================================")
         except Exception as e:  # 番号提取异常
-            print('[-]' + i + ' ERRPR :')
+            print('[-]' + i + ' ERROR :')
             print('[-]',e)
             if config['common']['soft_link'] == '1':
                 print('[-]Link', i, 'to failed folder')
@@ -164,6 +164,6 @@ def getNumber(filepath,absolute_path = False):
     CEF(success_folder)
     CEF(failed_folder)
     print("[+]All finished!!!")
-    if argparse_function(3) == '2':
+    if argparse_function(3) == True:
         os._exit(0)
-    input("[+][+]Press enter key exit, you can check the error messge before you exit.")
+    input("[+][+]Press enter key exit, you can check the error messge before you exit.")

README.md

@@ -173,14 +173,12 @@ update_check=1
 0为关闭，1为开启，不建议关闭
 
 ---
-### 媒体库选择 
+### 刮削网站优先级
 ```
-[media]
-media_warehouse=emby
-#emby plex kodi
+[priority]
+website=javbus,javdb,fanza,xcity,mgstage,fc2,avsox,jav321
 ```
-可选择emby, plex, kodi
-如果是PLEX，请安装插件：```XBMCnfoMoviesImporter```
+用```,```英文逗号分开网站，刮削顺序从左往右
 
 ---
 ### 排除指定字符和目录
@@ -267,12 +265,12 @@ AV_Data_Capture xxx-xxx-xxx.mp4
 ```
 AV_Data_Capture -c config_other.ini
 ```
-### 程序退出选择参数
-默认值为```1```
+### 程序自动退出
+
 ```
-AV_Data_Capture -e 1
+AV_Data_Capture -a
 ```
-1为默认值，刮削结束后要按下回车键程序才会结束，如果是2，程序刮削完毕后会自动结束程序
+输入参数即可在刮削结束后自动结束程序
 
 ## 多集影片处理
 **建议使用视频合并合并为一个视频文件**

config.ini

@@ -16,9 +16,12 @@ naming_rule=number+'-'+title
 [update]
 update_check=1
 
+[priority]
+website=javbus,javdb,fanza,xcity,mgstage,fc2,avsox,jav321
+
 [escape]
 literals=\()/
 folders=failed,JAV_output
 
 [debug_mode]
-switch=0
+switch=0

core.py

@@ -20,7 +20,7 @@
 import javdb
 import fanza
 import jav321
-
+import xcity
 
 # =====================本地文件处理===========================
 
@@ -47,7 +47,7 @@ def CreatFailedFolder(failed_folder):
             return 
 
 
-def getDataFromJSON(file_number, filepath, failed_folder):  # 从JSON返回元数据
+def getDataFromJSON(file_number, filepath, failed_folder, sources):  # 从JSON返回元数据
     """
     iterate through all services and fetch the data
     """
@@ -60,10 +60,11 @@ def getDataFromJSON(file_number, filepath, failed_folder):  # 从JSON返回元
         "javbus": javbus.main,
         "mgstage": mgstage.main,
         "jav321": jav321.main,
+        "xcity" : xcity.main,
     }
 
     # default fetch order list, from the begining to the end
-    sources = ["javbus", "javdb", "fanza", "mgstage", "fc2",  "avsox", "jav321"]
+    sources = sources.split(',')
 
     # if the input file name matches centain rules,
     # move some web service to the begining of the list
@@ -308,7 +309,7 @@ def PrintFiles(path, c_word, naming_rule, part, cn_sub, json_data, filepath, fai
             print("  <cover>" + cover + "</cover>", file=code)
             print("  <website>" + website + "</website>", file=code)
             print("</movie>", file=code)
-            print("[+]Writeed!          " + path + "/" + number + c_word + ".nfo")
+            print("[+]Wrote!            " + path + "/" + number + c_word + ".nfo")
     except IOError as e:
         print("[-]Write Failed!")
         print(e)
@@ -430,9 +431,10 @@ def core_main(file_path, number_th, config_file):
     program_mode = Config['common']['main_mode']  # 运行模式
     failed_folder = Config['common']['failed_output_folder']  # 失败输出目录
     success_folder = Config['common']['success_output_folder']  # 成功输出目录
+    sources = Config['priority']['website'] # 网站优先级
     filepath = file_path  # 影片的路径
     number = number_th
-    json_data = getDataFromJSON(number, filepath, failed_folder)  # 定义番号
+    json_data = getDataFromJSON(number, filepath, failed_folder, sources)  # 定义番号
     if json_data["number"] != number:
         # fix issue #119
         # the root cause is we normalize the search id

mgstage.py

@@ -77,7 +77,7 @@ def getDirector(a):
     return str(result1 + result2).strip('+').replace("', '",'').replace('"','')
 def getOutline(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
-    result = str(html.xpath('//p/text()')).strip(" ['']")
+    result = str(html.xpath('//p/text()')).strip(" ['']").replace(u'\\n', '').replace("', '', '", '')
     return result
 def main(number2):
     number=number2.upper()
@@ -108,4 +108,5 @@ def main(number2):
     return js
     #print(htmlcode)
 
-#print(main('SIRO-3607'))
+if __name__ == '__main__':
+    print(main('SIRO-4149'))

update_check.json

@@ -1,5 +1,5 @@
 {
-	"version": "3.1.2",
-	"version_show": "3.1.2",
+	"version": "3.2",
+	"version_show": "3.2",
 	"download": "https://github.com/yoshiko2/AV_Data_Capture/releases"
 }

xcity.py

@@ -0,0 +1,157 @@
+import re
+from lxml import etree
+import json
+from bs4 import BeautifulSoup
+from ADC_function import *
+
+
+# import sys
+# import io
+# sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
+
+def getTitle(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result = html.xpath('//*[@id="program_detail_title"]/text()')[0]
+    return result
+
+
+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()
+    result1 = html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[3]/a/text()')[0]
+    return result1
+
+
+def getActorPhoto(actor):  # //*[@id="star_qdt"]/li/a/img
+    a = actor.split(',')
+    d = {}
+    for i in a:
+        p = {i: ''}
+        d.update(p)
+    return d
+
+
+def getStudio(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[4]/a/span/text()')).strip(" ['']")
+    result2 = str(html.xpath('//strong[contains(text(),"片商")]/../following-sibling::span/a/text()')).strip(" ['']")
+    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
+
+
+def getRuntime(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[2]/li[3]/text()')).strip(" ['']")
+    try:
+        return re.findall('\d+',result1)[0]
+    except:
+        return ''
+
+
+def getLabel(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[5]/a/span/text()')).strip(" ['']")
+    return result1
+
+
+def getNum(a):
+    html = etree.fromstring(a, etree.HTMLParser())
+    result1 = str(html.xpath('//*[@id="hinban"]/text()')).strip(" ['']")
+    return result1
+
+
+def getYear(getRelease):
+    try:
+        result = str(re.search('\d{4}', getRelease).group())
+        return result
+    except:
+        return getRelease
+
+
+def getRelease(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[2]/li[4]/text()')).strip(" ['']")
+    try:
+        return re.findall('\d{4}/\d{2}/\d{2}', result1)[0]
+    except:
+        return ''
+
+
+def getTag(a):
+    result2=[]
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[1]/li[6]/a/text()')
+    for i in result1:
+        i=i.replace(u'\n','')
+        i=i.replace(u'\t','')
+        result2.append(i)
+    return result2
+
+
+def getCover_small(a, index=0):
+    # same issue mentioned below,
+    # javdb sometime returns multiple results
+    # DO NOT just get the firt one, get the one with correct index number
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
+    if not 'https' in result:
+        result = 'https:' + result
+    return result
+
+
+def getCover(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="avodDetails"]/div/div[3]/div[1]/p/a/@href')).strip(" ['']")
+    return 'https:'+result
+
+
+def getDirector(a):
+    html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+    result1 = str(html.xpath('//*[@id="program_detail_director"]/text()')).strip(" ['']").replace(u'\\n','').replace(u'\\t','')
+    return result1
+
+
+def getOutline(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="avodDetails"]/div/div[3]/div[2]/div/ul[2]/li[5]/p/text()')).strip(" ['']")
+    try:
+        return re.sub('\\\\\w*\d+','',result)
+    except:
+        return result
+
+
+def main(number):
+    try:
+        number = number.upper()
+        query_result = get_html(
+            'https://xcity.jp/result_published/?genre=%2Fresult_published%2F&q=' + number.replace('-',
+                                                                                                  '') + '&sg=main&num=30')
+        html = etree.fromstring(query_result, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
+        urls = html.xpath("//table[contains(@class, 'resultList')]/tr[2]/td[1]/a/@href")[0]
+        detail_page = get_html('https://xcity.jp' + urls)
+        dic = {
+            'actor': getActor(detail_page),
+            'title': getTitle(detail_page),
+            'studio': getStudio(detail_page),
+            'outline': getOutline(detail_page),
+            'runtime': getRuntime(detail_page),
+            'director': getDirector(detail_page),
+            'release': getRelease(detail_page),
+            'number': getNum(detail_page),
+            'cover': getCover(detail_page),
+            'cover_small': '',
+            'imagecut': 1,
+            'tag': getTag(detail_page),
+            'label': getLabel(detail_page),
+            'year': getYear(getRelease(detail_page)),  # str(re.search('\d{4}',getRelease(a)).group()),
+            'actor_photo': getActorPhoto(getActor(detail_page)),
+            'website': 'https://javdb.com' + urls,
+            'source': 'xcity.py',
+        }
+    except Exception as e:
+        # print(e)
+        dic = {"title": ""}
+
+    js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
+    return js
+
+if __name__ == '__main__':
+    print(main('VNDS-2624'))