Merge pull request #1 from yoshiko2/master

同步代码

AV_Data_Capture.py

@@ -1,11 +1,19 @@
 import argparse
-from core import *
 import os
+import sys
+
 from number_parser import get_number
+from core import *
 
 
 def check_update(local_version):
-    data = json.loads(get_html("https://api.github.com/repos/yoshiko2/AV_Data_Capture/releases/latest"))
+    try:
+        data = json.loads(get_html("https://api.github.com/repos/yoshiko2/AV_Data_Capture/releases/latest"))
+    except Exception as e:
+        print("[-] Failed to update! Please check new version manually:")
+        print("[-] https://github.com/yoshiko2/AV_Data_Capture/releases")
+        print("[*]======================================================")
+        return
 
     remote = data["tag_name"]
     local = local_version
@@ -22,18 +30,22 @@ def argparse_function(ver: str) -> [str, str, bool]:
     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("-n", "--number", default='', nargs='?',help="Custom file number")
+    parser.add_argument("-n", "--number", default='', nargs='?', help="Custom file number")
-    parser.add_argument("--version", action="version", version=ver)
+    parser.add_argument("-a", "--auto-exit", dest='autoexit', action="store_true",
+                        help="Auto exit after program complete")
+    parser.add_argument("-v", "--version", action="version", version=ver)
     args = parser.parse_args()
 
-    return args.file, args.config, args.number
+    return args.file, args.config, args.number, args.autoexit
+
 
 def movie_lists(root, escape_folder):
     for folder in escape_folder:
         if folder in root:
             return []
     total = []
-    file_type = ['.mp4', '.avi', '.rmvb', '.wmv', '.mov', '.mkv', '.flv', '.ts', '.webm', '.MP4', '.AVI', '.RMVB', '.WMV','.MOV', '.MKV', '.FLV', '.TS', '.WEBM', '.iso','.ISO']
+    file_type = ['.mp4', '.avi', '.rmvb', '.wmv', '.mov', '.mkv', '.flv', '.ts', '.webm', '.MP4', '.AVI', '.RMVB',
+                 '.WMV', '.MOV', '.MKV', '.FLV', '.TS', '.WEBM', '.iso', '.ISO']
     dirs = os.listdir(root)
     for entry in dirs:
         f = os.path.join(root, entry)
@@ -50,22 +62,22 @@ def create_failed_folder(failed_folder):
             os.makedirs(failed_folder + '/')
         except:
             print("[-]failed!can not be make folder 'failed'\n[-](Please run as Administrator)")
-            os._exit(0)
+            sys.exit(0)
 
 
-def CEF(path):
+def rm_empty_folder(path):
     try:
         files = os.listdir(path)  # 获取路径下的子文件(夹)列表
         for file in files:
-            os.removedirs(path + '/' + file)  # 删除这个空文件夹
+            os.rmdir(path + '/' + file)  # 删除这个空文件夹
             print('[+]Deleting empty folder', path + '/' + file)
     except:
         a = ''
 
 
-def create_data_and_move(file_path: str, c: config.Config,debug):
+def create_data_and_move(file_path: str, c: config.Config, debug):
     # Normalized number, eg: 111xxx-222.mp4 -> xxx-222.mp4
-    n_number = get_number(debug,file_path)
+    n_number = get_number(debug, file_path)
 
     if debug == True:
         print("[!]Making Data for [{}], the number is [{}]".format(file_path, n_number))
@@ -96,6 +108,7 @@ def create_data_and_move(file_path: str, c: config.Config,debug):
                     except Exception as err:
                         print('[!]', err)
 
+
 def create_data_and_move_with_custom_number(file_path: str, c: config.Config, custom_number=None):
     try:
         print("[!]Making Data for [{}], the number is [{}]".format(file_path, custom_number))
@@ -117,10 +130,10 @@ def create_data_and_move_with_custom_number(file_path: str, c: config.Config, cu
 
 
 if __name__ == '__main__':
-    version = '4.0.3'
+    version = '4.2.2'
 
     # Parse command line args
-    single_file_path, config_file, custom_number = argparse_function(version)
+    single_file_path, config_file, custom_number, auto_exit = argparse_function(version)
 
     # Read config.ini
     conf = config.Config(path=config_file)
@@ -139,21 +152,21 @@ if __name__ == '__main__':
     # ========== Single File ==========
     if not single_file_path == '':
         print('[+]==================== Single File =====================')
-        create_data_and_move_with_custom_number(single_file_path, conf,custom_number)
+        create_data_and_move_with_custom_number(single_file_path, conf, custom_number)
-        CEF(conf.success_folder())
+        rm_empty_folder(conf.success_folder())
-        CEF(conf.failed_folder())
+        rm_empty_folder(conf.failed_folder())
         print("[+]All finished!!!")
         input("[+][+]Press enter key exit, you can check the error messge before you exit.")
-        exit()
+        sys.exit(0)
     # ========== Single File ==========
 
-    movie_list = movie_lists(".", re.split("[,，]", conf.escape_folder()))
+    movie_list = movie_lists(os.getcwd(), re.split("[,，]", conf.escape_folder()))
 
     count = 0
     count_all = str(len(movie_list))
     print('[+]Find', count_all, 'movies')
     if conf.debug() == True:
-        print('[+]'+' DEBUG MODE ON '.center(54, '-'))
+        print('[+]' + ' DEBUG MODE ON '.center(54, '-'))
     if conf.soft_link():
         print('[!] --- Soft link mode is ENABLE! ----')
     for movie_path in movie_list:  # 遍历电影列表 交给core处理
@@ -162,9 +175,12 @@ if __name__ == '__main__':
         print('[!] - ' + percentage + ' [' + str(count) + '/' + count_all + '] -')
         create_data_and_move(movie_path, conf, conf.debug())
 
-    CEF(conf.success_folder())
+    rm_empty_folder(conf.success_folder())
-    CEF(conf.failed_folder())
+    rm_empty_folder(conf.failed_folder())
     print("[+]All finished!!!")
     if conf.auto_exit():
-        os._exit(0)
+        sys.exit(0)
-    input("[+][+]Press enter key exit, you can check the error message before you exit.")
+    if auto_exit:
+        sys.exit(0)
+    input("Press enter key exit, you can check the error message before you exit...")
+    sys.exit(0)

WebCrawler/airav.py

@@ -0,0 +1,174 @@
+import sys
+sys.path.append('../')
+import re
+from pyquery import PyQuery as pq#need install
+from lxml import etree#need install
+from bs4 import BeautifulSoup#need install
+import json
+from ADC_function import *
+
+
+
+# airav这个网站没有演员图片，所以直接使用javbus的图
+def getActorPhoto(htmlcode): #//*[@id="star_qdt"]/li/a/img
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    a = soup.find_all(attrs={'class': 'star-name'})
+    d={}
+    for i in a:
+        l=i.a['href']
+        t=i.get_text()
+        html = etree.fromstring(get_html(l), etree.HTMLParser())
+        p=str(html.xpath('//*[@id="waterfall"]/div[1]/div/div[1]/img/@src')).strip(" ['']")
+        p2={t:p}
+        d.update(p2)
+    return d
+
+def getTitle(htmlcode):  #获取标题
+    doc = pq(htmlcode)
+    # h5:first-child定位第一个h5标签，妈的找了好久才找到这个语法
+    title = str(doc('div.d-flex.videoDataBlock h5.d-none.d-md-block:nth-child(2)').text()).replace(' ', '-')
+    try:
+        title2 = re.sub('n\d+-','',title)
+
+        return title2
+    except:
+        return title
+
+def getStudio(htmlcode): #获取厂商 已修改
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    # 如果记录中冇导演，厂商排在第4位
+    if '製作商:' == str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/span/text()')).strip(" ['']"):
+        result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
+    # 如果记录中有导演，厂商排在第5位
+    elif '製作商:' == str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/span/text()')).strip(" ['']"):
+        result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[5]/a/text()')).strip(" ['']")
+    else:
+        result = ''
+    return result
+def getYear(htmlcode):   #获取年份
+    html = etree.fromstring(htmlcode,etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
+    return result
+def getCover(htmlcode):  #获取封面链接
+    doc = pq(htmlcode)
+    image = doc('a.bigImage')
+    return image.attr('href')
+def getRelease(htmlcode): #获取出版日期
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[2]/text()')).strip(" ['']")
+    return result
+def getRuntime(htmlcode): #获取分钟 已修改
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[3]/text()')).strip(" ['']分鐘")
+    return result
+
+def getActor(htmlcode):   #获取女优
+    b=[]
+    soup=BeautifulSoup(htmlcode,'lxml')
+    a=soup.find_all(attrs={'class':'videoAvstarListItem'})
+    for i in a:
+        b.append(i.get_text())
+    return b
+
+def getNum(htmlcode):     #获取番号
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[1]/span[2]/text()')).strip(" ['']")
+    return result
+def getDirector(htmlcode): #获取导演 已修改
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    if '導演:' == str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/span/text()')).strip(" ['']"):
+        result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[4]/a/text()')).strip(" ['']")
+    else:
+        result = ''         # 记录中有可能没有导演数据
+    return result
+
+def getOutline(htmlcode):  #获取演员
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    try:
+        result = html.xpath("string(//div[@class='d-flex videoDataBlock']/div[@class='synopsis']/p)").replace('\n','')
+        return result
+    except:
+        return ''
+def getSerise(htmlcode):   #获取系列 已修改
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    # 如果记录中冇导演，系列排在第6位
+    if '系列:' == str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[6]/span/text()')).strip(" ['']"):
+        result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[6]/a/text()')).strip(" ['']")
+    # 如果记录中有导演，系列排在第7位
+    elif '系列:' == str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/span/text()')).strip(" ['']"):
+        result = str(html.xpath('/html/body/div[5]/div[1]/div[2]/p[7]/a/text()')).strip(" ['']")
+    else:
+        result = ''
+    return result
+def getTag(htmlcode):  # 获取标签
+    tag = []
+    soup = BeautifulSoup(htmlcode, 'lxml')
+    x = soup.find_all(attrs={'class': 'tagBtnMargin'})
+    a = x[0].find_all('a')
+
+    for i in a:
+        tag.append(i.get_text())
+    return tag
+
+def main(number):
+    try:
+        try:
+            try:
+                htmlcode = get_html('https://cn.airav.wiki/video/' + number)
+                javbus_htmlcode = get_html('https://www.javbus.com/ja/' + number)
+
+
+            except:
+                print(number)
+
+            dic = {
+                # 标题可使用airav
+                'title': str(re.sub('\w+-\d+-', '', getTitle(htmlcode))),
+                # 制作商选择使用javbus
+                'studio': getStudio(javbus_htmlcode),
+                # 年份也是用javbus
+                'year': str(re.search('\d{4}', getYear(javbus_htmlcode)).group()),
+                #  简介 使用 airav
+                'outline': getOutline(htmlcode),
+                # 使用javbus
+                'runtime': getRuntime(javbus_htmlcode),
+                # 导演 使用javbus
+                'director': getDirector(javbus_htmlcode),
+                # 作者 使用airav
+                'actor': getActor(htmlcode),
+                # 发售日使用javbus
+                'release': getRelease(javbus_htmlcode),
+                # 番号使用javbus
+                'number': getNum(javbus_htmlcode),
+                # 封面链接 使用javbus
+                'cover': getCover(javbus_htmlcode),
+
+                'imagecut': 1,
+                # 使用 airav
+                'tag': getTag(htmlcode),
+                # 使用javbus
+                'label': getSerise(javbus_htmlcode),
+                # 妈的，airav不提供作者图片
+                'actor_photo': getActorPhoto(javbus_htmlcode),
+
+                'website': 'https://www.airav.wiki/video/' + number,
+                'source': 'airav.py',
+                # 使用javbus
+                'series': getSerise(javbus_htmlcode),
+            }
+            js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), )  # .encode('UTF-8')
+            return js
+        except:
+            return main_uncensored(number)
+    except:
+        data = {
+            "title": "",
+        }
+        js = json.dumps(
+            data, ensure_ascii=False, sort_keys=True, indent=4, separators=(",", ":")
+        )
+        return js
+
+
+if __name__ == '__main__':
+    print(main('sdsi-019'))

WebCrawler/javdb.py

@@ -26,10 +26,17 @@ def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
         d.update(p)
     return d
 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")]/../span/text()')).strip(" ['']")
+#     result1 = str(html.xpath('//strong[contains(text(),"片商")]/../span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
+#     result2 = str(html.xpath('//strong[contains(text(),"片商")]/../span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
+#     return str(result1 + result2).strip('+').replace("', '", '').replace('"', '')
+    patherr = re.compile(r'<strong>片商\:</strong>[\s\S]*?<a href=\".*?>(.*?)</a></span>')
+    pianshang = patherr.findall(a)
+    if pianshang:
+        result = pianshang[0]
+    else:
+        result = ""
+    return result
 def getRuntime(a):
     html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
     result1 = str(html.xpath('//strong[contains(text(),"時長")]/../span/text()')).strip(" ['']")
@@ -46,16 +53,30 @@ def getNum(a):
     result2 = str(html.xpath('//strong[contains(text(),"番號")]/../span/a/text()')).strip(" ['']")
     return str(result2 + result1).strip('+')
 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
+    patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)\-.*?</span>')
+    dates = patherr.findall(getRelease)
+    if dates:
+        result = dates[0]
+    else:
+        result = ''
+    return result
 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")]/../span/text()')).strip(" ['']")
+#     result1 = str(html.xpath('//strong[contains(text(),"時間")]/../span/text()')).strip(" ['']")
-    result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']")
+#     result2 = str(html.xpath('//strong[contains(text(),"時間")]/../span/a/text()')).strip(" ['']")
-    return str(result1 + result2).strip('+')
+#     return str(result1 + result2).strip('+')
+    patherr = re.compile(r'<strong>日期\:</strong>\s*?.*?<span class="value">(.*?)</span>')
+    dates = patherr.findall(a)
+    if dates:
+        result = dates[0]
+    else:
+        result = ''
+    return result
 def getTag(a):
     html = etree.fromstring(a, etree.HTMLParser())  # //table/tr[1]/td[1]/text()
     try:
@@ -89,10 +110,17 @@ def getCover_small(a, index=0):
             result = 'https:' + result
         return result
     except: # 2020.7.17 Repair Cover Url crawl
-        result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@data-src")[index]
+        try:
-        if not 'https' in result:
+            result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@data-src")[index]
-            result = 'https:' + result
+            if not 'https' in result:
-        return result
+                result = 'https:' + result
+            return result
+        except:
+            result = html.xpath("//div[@class='item-image']/img/@data-src")[index]
+            if not 'https' in result:
+                result = 'https:' + result
+            return result
+
 def getCover(htmlcode):
     html = etree.fromstring(htmlcode, etree.HTMLParser())
     try:
@@ -127,14 +155,23 @@ def main(number):
         # and the first elememt maybe not the one we are looking for
         # iterate all candidates and find the match one
         urls = html.xpath('//*[@id="videos"]/div/div/a/@href')
-        ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
+        # 记录一下欧美的ids  ['Blacked','Blacked']
-        correct_url = urls[ids.index(number)]
+        if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
+            correct_url = urls[0]
+        else:
+            ids =html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
+            correct_url = urls[ids.index(number)]
+       
         detail_page = get_html('https://javdb.com' + correct_url)
 
         # no cut image by default
         imagecut = 3
         # If gray image exists ,then replace with normal cover
-        cover_small = getCover_small(query_result, index=ids.index(number))
+        if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
+            cover_small = getCover_small(query_result)
+        else:
+            cover_small = getCover_small(query_result, index=ids.index(number))
+        
         if 'placeholder' in cover_small:
             # replace wit normal cover and cut it
             imagecut = 1

core.py

@@ -1,5 +1,6 @@
 import json
 import os.path
+import pathlib
 import re
 import shutil
 import platform
@@ -29,18 +30,17 @@ def escape_path(path, escape_literals: str):  # Remove escape literals
 
 
 def moveFailedFolder(filepath, failed_folder):
-    print('[-]Move to Failed output folder')
+    if config.Config().failed_move():
-    shutil.move(filepath, str(os.getcwd()) + '/' + failed_folder + '/')
+        root_path = str(pathlib.Path(filepath).parent)
-    return 
+        file_name = pathlib.Path(filepath).name
-
+        destination_path = root_path + '/' + failed_folder + '/'
-
+        if config.Config.soft_link():
-def CreatFailedFolder(failed_folder):
+            print('[-]Create symlink to Failed output folder')
-    if not os.path.exists(failed_folder + '/'):  # 新建failed文件夹
+            os.symlink(filepath, destination_path + '/' + file_name)
-        try:
+        else:
-            os.makedirs(failed_folder + '/')
+            print('[-]Move to Failed output folder')
-        except:
+            shutil.move(filepath, destination_path)
-            print("[-]failed!can not be make Failed output folder\n[-](Please run as Administrator)")
+    return
-            return 
 
 
 def get_data_from_json(file_number, filepath, conf: config.Config):  # 从JSON返回元数据
@@ -111,23 +111,25 @@ def get_data_from_json(file_number, filepath, conf: config.Config):  # 从JSON
 
     # ================================================网站规则添加结束================================================
 
-    title = json_data['title']
+    title = json_data.get('title')
-    actor_list = str(json_data['actor']).strip("[ ]").replace("'", '').split(',')  # 字符串转列表
+    actor_list = str(json_data.get('actor')).strip("[ ]").replace("'", '').split(',')  # 字符串转列表
-    release = json_data['release']
+    release = json_data.get('release')
-    number = json_data['number']
+    number = json_data.get('number')
-    studio = json_data['studio']
+    studio = json_data.get('studio')
-    source = json_data['source']
+    source = json_data.get('source')
-    runtime = json_data['runtime']
+    runtime = json_data.get('runtime')
-    outline = json_data['outline']
+    outline = json_data.get('outline')
-    label = json_data['label']
+    label = json_data.get('label')
-    series = json_data['series']
+    series = json_data.get('series')
-    year = json_data['year']
+    year = json_data.get('year')
-    try:
+
-        cover_small = json_data['cover_small']
+    if json_data.get('cover_small') == None:
-    except:
         cover_small = ''
-    imagecut = json_data['imagecut']
+    else:
-    tag = str(json_data['tag']).strip("[ ]").replace("'", '').replace(" ", '').split(',')  # 字符串转列表 @
+        cover_small = json_data.get('cover_small')
+        
+    imagecut = json_data.get('imagecut')
+    tag = str(json_data.get('tag')).strip("[ ]").replace("'", '').replace(" ", '').split(',')  # 字符串转列表 @
     actor = str(actor_list).strip("[ ]").replace("'", '').replace(" ", '')
 
     if title == '' or number == '':
@@ -152,6 +154,7 @@ def get_data_from_json(file_number, filepath, conf: config.Config):  # 从JSON
     tmpArr = cover_small.split(',')
     if len(tmpArr) > 0:
         cover_small = tmpArr[0].strip('\"').strip('\'')
+
     # ====================处理异常字符 END================== #\/:*?"<>|
 
     # ===  替换Studio片假名
@@ -193,15 +196,13 @@ def get_data_from_json(file_number, filepath, conf: config.Config):  # 从JSON
     
     location_rule = eval(conf.location_rule())
 
-    # Process only Windows.
+    if 'actor' in conf.location_rule() and len(actor) > 100:
-    if platform.system() == "Windows":
+        print(conf.location_rule())
-        if 'actor' in conf.location_rule() and len(actor) > 100:
+        location_rule = eval(conf.location_rule().replace("actor","'多人作品'"))
-            print(conf.location_rule())
+    maxlen = conf.max_title_len()
-            location_rule = eval(conf.location_rule().replace("actor","'多人作品'"))
+    if 'title' in conf.location_rule() and len(title) > maxlen:
-        maxlen = conf.max_title_len()
+        shorttitle = title[0:maxlen]
-        if 'title' in conf.location_rule() and len(title) > maxlen:
+        location_rule = location_rule.replace(title, shorttitle)
-            shorttitle = title[0:maxlen]
-            location_rule = location_rule.replace(title, shorttitle)
 
     # 返回处理后的json_data
     json_data['title'] = title
@@ -219,26 +220,26 @@ def get_data_from_json(file_number, filepath, conf: config.Config):  # 从JSON
     naming_rule=""
     for i in conf.naming_rule().split("+"):
         if i not in json_data:
-            naming_rule+=i.strip("'").strip('"')
+            naming_rule += i.strip("'").strip('"')
         else:
-            naming_rule+=json_data[i]
+            naming_rule += json_data.get(i)
     json_data['naming_rule'] = naming_rule
     return json_data
 
 
 def get_info(json_data):  # 返回json里的数据
-    title = json_data['title']
+    title = json_data.get('title')
-    studio = json_data['studio']
+    studio = json_data.get('studio')
-    year = json_data['year']
+    year = json_data.get('year')
-    outline = json_data['outline']
+    outline = json_data.get('outline')
-    runtime = json_data['runtime']
+    runtime = json_data.get('runtime')
-    director = json_data['director']
+    director = json_data.get('director')
-    actor_photo = json_data['actor_photo']
+    actor_photo = json_data.get('actor_photo')
-    release = json_data['release']
+    release = json_data.get('release')
-    number = json_data['number']
+    number = json_data.get('number')
-    cover = json_data['cover']
+    cover = json_data.get('cover')
-    website = json_data['website']
+    website = json_data.get('website')
-    series = json_data['series']
+    series = json_data.get('series')
     label = json_data.get('label', "")
     return title, studio, year, outline, runtime, director, actor_photo, release, number, cover, website, series, label
 
@@ -260,7 +261,7 @@ def create_folder(success_folder, location_rule, json_data, conf: config.Config)
         try:
             os.makedirs(path)
         except:
-            path = success_folder + '/' + location_rule.replace('/[' + number + ']-' + title, "/number")
+            path = success_folder + '/' + location_rule.replace('/[' + number + ')-' + title, "/number")
             path = escape_path(path, conf.escape_literals())
 
             os.makedirs(path)
@@ -284,7 +285,7 @@ def download_file_with_filename(url, filename, path, conf: config.Config, filepa
 
     for i in range(retry_count):
         try:
-            if switch == 1:
+            if switch == 1 or switch == '1':
                 if not os.path.exists(path):
                     os.makedirs(path)
                 proxies = get_proxy(proxy, proxytype)
@@ -429,22 +430,22 @@ def cutImage(imagecut, path, number, c_word):
 
 
 def paste_file_to_folder(filepath, path, number, c_word, conf: config.Config):  # 文件路径，番号，后缀，要移动至的位置
-    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filepath).group())
+    houzhui = str(re.search('[.](iso|ISO|AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filepath).group())
-
+    file_parent_origin_path = str(pathlib.Path(filepath).parent)
     try:
         # 如果soft_link=1 使用软链接
         if conf.soft_link():
             os.symlink(filepath, path + '/' + number + c_word + houzhui)
         else:
             os.rename(filepath, path + '/' + number + c_word + houzhui)
-        if os.path.exists(os.getcwd() + '/' + number + c_word + '.srt'):  # 字幕移动
+        if os.path.exists(file_parent_origin_path + '/' + number + c_word + '.srt'):  # 字幕移动
-            os.rename(os.getcwd() + '/' + number + c_word + '.srt', path + '/' + number + c_word + '.srt')
+            os.rename(file_parent_origin_path + '/' + number + c_word + '.srt', path + '/' + number + c_word + '.srt')
             print('[+]Sub moved!')
-        elif os.path.exists(os.getcwd() + '/' + number + c_word + '.ssa'):
+        elif os.path.exists(file_parent_origin_path + '/' + number + c_word + '.ssa'):
-            os.rename(os.getcwd() + '/' + number + c_word + '.ssa', path + '/' + number + c_word + '.ssa')
+            os.rename(file_parent_origin_path + '/' + number + c_word + '.ssa', path + '/' + number + c_word + '.ssa')
             print('[+]Sub moved!')
-        elif os.path.exists(os.getcwd() + '/' + number + c_word + '.sub'):
+        elif os.path.exists(file_parent_origin_path + '/' + number + c_word + '.sub'):
-            os.rename(os.getcwd() + '/' + number + c_word + '.sub', path + '/' + number + c_word + '.sub')
+            os.rename(file_parent_origin_path + '/' + number + c_word + '.sub', path + '/' + number + c_word + '.sub')
             print('[+]Sub moved!')
     except FileExistsError:
         print('[-]File Exists! Please check your movie!')
@@ -458,21 +459,21 @@ def paste_file_to_folder(filepath, path, number, c_word, conf: config.Config):
 def paste_file_to_folder_mode2(filepath, path, multi_part, number, part, c_word, conf):  # 文件路径，番号，后缀，要移动至的位置
     if multi_part == 1:
         number += part  # 这时number会被附加上CD1后缀
-    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm)$', filepath).group())
+    houzhui = str(re.search('[.](AVI|RMVB|WMV|MOV|MP4|MKV|FLV|TS|WEBM|avi|rmvb|wmv|mov|mp4|mkv|flv|ts|webm|iso|ISO)$', filepath).group())
-
+    file_parent_origin_path = str(pathlib.Path(filepath).parent)
     try:
         if conf.soft_link():
             os.symlink(filepath, path + '/' + number + part + c_word + houzhui)
         else:
             os.rename(filepath, path + '/' + number + part + c_word + houzhui)
-        if os.path.exists(number + '.srt'):  # 字幕移动
+        if os.path.exists(file_parent_origin_path + '/' + number + '.srt'):  # 字幕移动
-            os.rename(number + part + c_word + '.srt', path + '/' + number + part + c_word + '.srt')
+            os.rename(file_parent_origin_path + '/' + number + part + c_word + '.srt', path + '/' + number + part + c_word + '.srt')
             print('[+]Sub moved!')
-        elif os.path.exists(number + part + c_word + '.ass'):
+        elif os.path.exists(file_parent_origin_path + '/' + number + part + c_word + '.ass'):
-            os.rename(number + part + c_word + '.ass', path + '/' + number + part + c_word + '.ass')
+            os.rename(file_parent_origin_path + '/' + number + part + c_word + '.ass', path + '/' + number + part + c_word + '.ass')
             print('[+]Sub moved!')
-        elif os.path.exists(number + part + c_word + '.sub'):
+        elif os.path.exists(file_parent_origin_path + '/' + number + part + c_word + '.sub'):
-            os.rename(number + part + c_word + '.sub', path + '/' + number + part + c_word + '.sub')
+            os.rename(file_parent_origin_path + '/' + number + part + c_word + '.sub', path + '/' + number + part + c_word + '.sub')
             print('[+]Sub moved!')
         print('[!]Success')
     except FileExistsError:
@@ -519,7 +520,9 @@ def core_main(file_path, number_th, conf: config.Config):
     cn_sub = ''
     liuchu = ''
 
-    filepath = file_path  # 影片的路径
+
+    filepath = file_path  # 影片的路径 绝对路径
+    rootpath = str(pathlib.Path(filepath).parent)
     number = number_th
     json_data = get_data_from_json(number, filepath, conf)  # 定义番号
 
@@ -534,8 +537,8 @@ def core_main(file_path, number_th, conf: config.Config):
         # but paste_file_to_folder() still use the input raw search id
         # so the solution is: use the normalized search id
         number = json_data["number"]
-    imagecut = json_data['imagecut']
+    imagecut =  json_data.get('imagecut')
-    tag = json_data['tag']
+    tag =  json_data.get('tag')
     # =======================================================================判断-C,-CD后缀
     if '-CD' in filepath or '-cd' in filepath:
         multi_part = 1
@@ -546,15 +549,12 @@ def core_main(file_path, number_th, conf: config.Config):
     if '流出' in filepath:
         liuchu = '流出'
 
-    # 创建输出失败目录
-    CreatFailedFolder(conf.failed_folder())
-
     # 调试模式检测
     if conf.debug():
         debug_print(json_data)
 
     # 创建文件夹
-    path = create_folder(conf.success_folder(), json_data['location_rule'], json_data, conf)
+    path = create_folder(rootpath + '/' + conf.success_folder(),  json_data.get('location_rule'), json_data, conf)
 
     # main_mode
     #  1: 刮削模式 / Scraping mode
@@ -565,16 +565,16 @@ def core_main(file_path, number_th, conf: config.Config):
 
         # 检查小封面, 如果image cut为3，则下载小封面
         if imagecut == 3:
-            small_cover_check(path, number, json_data['cover_small'], c_word, conf, filepath, conf.failed_folder())
+            small_cover_check(path, number,  json_data.get('cover_small'), c_word, conf, filepath, conf.failed_folder())
 
         # creatFolder会返回番号路径
-        image_download(json_data['cover'], number, c_word, path, conf, filepath, conf.failed_folder())
+        image_download( json_data.get('cover'), number, c_word, path, conf, filepath, conf.failed_folder())
 
         # 裁剪图
         cutImage(imagecut, path, number, c_word)
 
         # 打印文件
-        print_files(path, c_word, json_data['naming_rule'], part, cn_sub, json_data, filepath, conf.failed_folder(), tag, json_data['actor_list'], liuchu)
+        print_files(path, c_word,  json_data.get('naming_rule'), part, cn_sub, json_data, filepath, conf.failed_folder(), tag,  json_data.get('actor_list'), liuchu)
 
         # 移动文件
         paste_file_to_folder(filepath, path, number, c_word, conf)

docker-entrypoint.sh

@@ -1,15 +0,0 @@
-#!/bin/sh
-
-git fetch --all
-git reset --hard origin/master
-git pull
-
-apt update
-apt upgrade -y
-pip3 install --upgrade -r requirements.txt
-make
-mv bin/* /avdc_bin
-
-cd /avdc_bin
-version=$(./AV_Data_Capture --version)
-zip AV_Data_Capture-CLI-$(echo $version)-Linux-$(dpkg --print-architecture).zip AV_Data_Capture config.ini

number_parser.py

@@ -41,6 +41,11 @@ def get_number(debug,filepath: str) -> str:
                 file_number = re.search(r'\w+-\w+', filename, re.A).group()
                 return file_number
             else:  # 提取不含减号-的番号，FANZA CID
+                # 欧美番号匹配规则
+                oumei = re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', filepath)
+                if oumei:
+                    return oumei.group()
+                
                 try:
                     return str(
                         re.findall(r'(.+?)\.',
@@ -61,6 +66,11 @@ def get_number(debug,filepath: str) -> str:
             file_number = re.search(r'\w+-\w+', filename, re.A).group()
             return file_number
         else:  # 提取不含减号-的番号，FANZA CID
+            # 欧美番号匹配规则
+            oumei = re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', filepath)
+            if oumei:
+                return oumei.group()
+            
             try:
                 return str(
                     re.findall(r'(.+?)\.',
@@ -72,4 +82,4 @@ def get_number(debug,filepath: str) -> str:
 
 # if __name__ == "__main__":
 #     import doctest
-#     doctest.testmod(raise_on_error=True)
+#     doctest.testmod(raise_on_error=True)

py_to_exe.ps1

@@ -3,6 +3,9 @@
 
 $CLOUDSCRAPER_PATH=$(python -c 'import cloudscraper as _; print(_.__path__[0])' | select -Last 1)
 
+mkdir build 
+mkdir __pycache__
+
 pyinstaller --onefile AV_Data_Capture.py `
     --hidden-import ADC_function.py `
     --hidden-import core.py `

wrapper/FreeBSD.sh

@@ -0,0 +1,4 @@
+pkg install python37 py37-requests py37-pip py37-lxml py37-pillow py37-cloudscraper py37-pysocks git zip py37-pyinstaller py37-beautifulsoup448
+pip install pyquery
+pyinstaller --onefile AV_Data_Capture.py  --hidden-import ADC_function.py --hidden-import core.py
+cp config.ini ./dist

wrapper/Linux.sh

@@ -0,0 +1,15 @@
+if ['$(dpkg --print-architecture)' != 'amd64'] || ['$(dpkg --print-architecture)' != 'i386']; then
+	apt install python3 python3-pip git sudo libxml2-dev libxslt-dev build-essential wget nano libcmocka-dev libcmocka0 -y
+	apt install zlib* libjpeg-dev  -y
+	wget https://files.pythonhosted.org/packages/82/96/21ba3619647bac2b34b4996b2dbbea8e74a703767ce24192899d9153c058/pyinstaller-4.0.tar.gz
+	tar -zxvf pyinstaller-4.0.tar.gz
+	cd pyinstaller-4.0/bootloader
+	sed -i "s/                                        '-Werror',//" wscript
+	python3 ./waf distclean all
+	cd ../
+	python3 setup.py install
+	cd ../
+fi
+pip3 install -r requirements.txt
+pyinstaller --onefile AV_Data_Capture.py  --hidden-import ADC_function.py --hidden-import core.py
+cp config.ini ./dist