Add anime support

WebCrawler/__init__.py

@@ -86,6 +86,8 @@ def get_data_from_json(file_number, oCC):
             sources = insert(sources,"carib")
         elif "item" in file_number:
             sources = insert(sources,"getchu")
+        elif "rj" in lo_file_number or "vj" in lo_file_number or re.match(r"[\u4e00-\u9fa5]", file_number):
+            sources = insert(sources,"dlsite")
         elif re.match(r"^\d{5,}", file_number) or "heyzo" in lo_file_number:
             if "avsox" in sources:
                 sources = insert(sources,"avsox")
@@ -97,10 +99,6 @@ def get_data_from_json(file_number, oCC):
                 sources = insert(sources,"fc2")
         elif "gcolle" in sources and (re.search("\d{6}", file_number)):
             sources = insert(sources,"gcolle")
-        elif "dlsite" in sources and (
-                "rj" in lo_file_number or "vj" in lo_file_number
-        ):
-            sources = insert(sources,"dlsite")
         elif re.match(r"^[a-z0-9]{3,}$", lo_file_number):
             if "xcity" in sources:
                 sources = insert(sources,"xcity")
@@ -170,6 +168,10 @@ def get_data_from_json(file_number, oCC):
     # 然而也可以跟进关注其它命名规则例如airav.wiki Domain Creation Date: 2019-08-28T07:18:42.0Z
     # 如果将来javdb.com命名规则下不同Studio出现同名碰撞导致无法区分，可考虑更换规则，更新相应的number分析和抓取代码。
     if str(json_data.get('number')).upper() != file_number.upper():
+        try:
+            if json_data.get('allow_number_change'):
+                pass
+        except:
             print('[-]Movie number has changed! [{}]->[{}]'.format(file_number, str(json_data.get('number'))))
             return None
 

WebCrawler/dlsite.py

@@ -26,7 +26,7 @@ def getActorPhoto(actor): #//*[@id="star_qdt"]/li/a/img
 def getStudio(html):
     try:
         try:
-            result = html.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0]
+            result = html.xpath('//th[contains(text(),"商标名")]/../td/span[1]/a/text()')[0]
         except:
             result = html.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0]
     except:
@@ -101,14 +101,29 @@ def getSeries(html):
     except:
         result = ''
     return result
+#
+def getExtrafanart(html):
+    try:
+        result = []
+        for i in html.xpath('//*[@id="work_left"]/div/div/div[1]/div/@data-src'):
+            result.append("https:" + i)
+    except:
+        result = ''
+    return result
 def main(number):
     try:
+        if "RJ" in number or "VJ" in number:
             number = number.upper()
-        htmlcode = get_html('https://www.dlsite.com/maniax/work/=/product_id/' + number + '.html/?locale=zh_CN',
+            htmlcode = get_html('https://www.dlsite.com/maniax/work/=/product_id/' + number + '.html/?locale=zh_CN',cookies={'locale': 'zh-cn'})
-                            cookies={'locale': 'zh-cn'})
             html = etree.fromstring(htmlcode, etree.HTMLParser())
+        else:
+            htmlcode = get_html(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie',cookies={'locale': 'zh-cn'})
+            html = etree.HTML(htmlcode)
+            a = html.xpath('//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')[0]
+            html = etree.HTML(get_html(a,cookies={'locale': 'zh-cn'}))
+            number = str(re.findall("\wJ\w+",a)).strip(" [']")
         dic = {
-            'actor': getActor(html),
+            'actor': getStudio(html),
             'title': getTitle(html),
             'studio': getStudio(html),
             'outline': getOutline(html),
@@ -118,7 +133,7 @@ def main(number):
             'number': number,
             'cover': 'https:' + getCover(html),
             'cover_small': '',
-            'imagecut': 0,
+            'imagecut': 1,
             'tag': getTag(html),
             'label': getLabel(html),
             'year': getYear(getRelease(html)),  # str(re.search('\d{4}',getRelease(a)).group()),
@@ -126,6 +141,8 @@ def main(number):
             'website': 'https://www.dlsite.com/maniax/work/=/product_id/' + number + '.html',
             'source': 'dlsite.py',
             'series': getSeries(html),
+            'extrafanart':getExtrafanart(html),
+            'allow_number_change':True,
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
         return js
@@ -144,5 +161,5 @@ def main(number):
 # 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。")
 if __name__ == "__main__":
     config.getInstance().set_override("debug_mode:switch=1")
-    print(main('VJ013178'))
+    print(main('牝教師4～穢された教壇～ 「生意気ドジっ娘女教師・美結～高飛車ハメ堕ち2濁金」'))
     print(main('RJ329607'))

core.py

@@ -698,14 +698,14 @@ def debug_print(data: json):
         print("[+] ------- DEBUG INFO -------")
         for i, v in data.items():
             if i == 'outline':
-                print('[+]  -', "%-14s" % i, ':', len(v), 'characters')
+                print('[+]  -', "%-19s" % i, ':', len(v), 'characters')
                 continue
             if i == 'actor_photo' or i == 'year':
                 continue
             if i == 'extrafanart':
-                print('[+]  -', "%-14s" % i, ':', len(v), 'links')
+                print('[+]  -', "%-19s" % i, ':', len(v), 'links')
                 continue
-            print(f'[+]  - {i:<{cnspace(i,14)}} : {v}')
+            print(f'[+]  - {i:<{cnspace(i,19)}} : {v}')
 
         print("[+] ------- DEBUG INFO -------")
     except:

number_parser.py

@@ -18,6 +18,8 @@ def get_number(debug: bool, file_path: str) -> str:
     'snis-829'
     >>> get_number(False, "/Users/Guest/AV_Data_Capture/snis-829-C.mp4")
     'snis-829'
+    >>> get_number(False, "/Users/Guest/AV_Data_Capture/[脸肿字幕组][PoRO]牝教師4～穢された教壇～ 「生意気ドジっ娘女教師・美結～高飛車ハメ堕ち2濁金」[720p][x264_aac].mp4")
+    '牝教師4～穢された教壇～ 「生意気ドジっ娘女教師・美結～高飛車ハメ堕ち2濁金」'
     >>> get_number(False, "C:¥Users¥Guest¥snis-829.mp4")
     'snis-829'
     >>> get_number(False, "C:¥Users¥Guest¥snis-829-C.mp4")
@@ -41,6 +43,11 @@ def get_number(debug: bool, file_path: str) -> str:
         file_number = get_number_by_dict(filepath)
         if file_number:
             return file_number
+        elif '字幕组' in filepath or 'SUB' in filepath.upper():
+            filepath = G_spat.sub("", filepath)
+            filepath = re.sub("\[.*?\]","",filepath)
+            file_number = str(re.findall(r'(.+?)\.', filepath)).strip(" [']")
+            return file_number
         elif '-' in filepath or '_' in filepath:  # 普通提取番号 主要处理包含减号-和_的番号
             filepath = G_spat.sub("", filepath)
             filename = str(re.sub("\[\d{4}-\d{1,2}-\d{1,2}\] - ", "", filepath))  # 去除文件名中时间