更可靠的无码识别方法

WebCrawler/carib.py

@@ -40,6 +40,7 @@ def main(number: str) -> json:
             'website': f'{G_SITE}/moviepages/{number}/index.html',
             'source': 'carib.py',
             'series': get_series(lx),
+            '无码': True
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )
         return js

WebCrawler/javbus.py

@@ -83,6 +83,9 @@ def getExtrafanart(htmlcode):  # 获取剧照
         if extrafanart_imgs:
             return [urljoin('https://www.javbus.com',img) for img in extrafanart_imgs]
     return ''
+def getUncensored(html):
+    x = html.xpath('//*[@id="navbar"]/ul[1]/li[@class="active"]/a[contains(@href,"uncensored")]')
+    return bool(x)
 
 def main_uncensored(number):
     htmlcode = get_html('https://www.javbus.com/ja/' + number)
@@ -109,6 +112,7 @@ def main_uncensored(number):
         'website': 'https://www.javbus.com/ja/' + number,
         'source': 'javbus.py',
         'series': getSeriseJa(lx),
+        '无码': getUncensored(lx)
     }
     js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), )  # .encode('UTF-8')
     return js
@@ -151,6 +155,7 @@ def main(number):
                 'website': 'https://www.javbus.com/' + number,
                 'source': 'javbus.py',
                 'series': getSerise(lx),
+                '无码': getUncensored(lx)
             }
             js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4,separators=(',', ':'), )  # .encode('UTF-8')
             return js

WebCrawler/javdb.py

@@ -179,6 +179,9 @@ def getUserRating(html):
         return float(v[0][0]), int(v[0][1])
     except:
         return
+def getUncensored(html):
+    x = html.xpath('//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?")]')
+    return bool(x)
 
 def main(number):
     # javdb更新后同一时间只能登录一个数字站，最新登录站会踢出旧的登录，因此按找到的第一个javdb*.json文件选择站点，
@@ -300,7 +303,7 @@ def main(number):
             'website': urljoin('https://javdb.com', correct_url),
             'source': 'javdb.py',
             'series': getSeries(lx),
-
+            '无码': getUncensored(lx)
         }
         userrating = getUserRating(lx)
         if isinstance(userrating, tuple) and len(userrating) == 2:
@@ -328,7 +331,7 @@ if __name__ == "__main__":
     # print(main('blacked.20.05.30'))
     # print(main('AGAV-042'))
     # print(main('BANK-022'))
-    # print(main('070116-197'))
+    print(main('070116-197'))
     # print(main('093021_539'))  # 没有剧照 片商pacopacomama
     #print(main('FC2-2278260'))
     # print(main('FC2-735670'))

WebCrawler/madou.py

@@ -146,7 +146,8 @@ def main(number):
             'website': url,
             'source': 'madou.py',
             # 使用
-            'series': getSerise(html)
+            'series': getSerise(html),
+            '无码': True
         }
         js = json.dumps(dic, ensure_ascii=False, sort_keys=True,
                         indent=4, separators=(',', ':'), )  # .encode('UTF-8')

core.py

@@ -617,6 +617,7 @@ def debug_print(data: json):
 
 def core_main_no_net_op(movie_path, number):
     conf = config.getInstance()
+    part = ''
     leak_word = ''
     leak = 0
     c_word = ''
@@ -627,6 +628,8 @@ def core_main_no_net_op(movie_path, number):
     imagecut = 1
     path = str(Path(movie_path).parent)
 
+    if re.search('-CD\d+', movie_path, re.IGNORECASE):
+        part = re.findall('-CD\d+', movie_path, re.IGNORECASE)[0]
     if '-c.' in movie_path or '-C.' in movie_path or '中文' in movie_path or '字幕' in movie_path:
         cn_sub = '1'
         c_word = '-C'  # 中文字幕影片后缀
@@ -639,12 +642,19 @@ def core_main_no_net_op(movie_path, number):
         hack = 1
         hack_word = "-hack"
 
-    fanart_path =  f"{number}{leak_word}{c_word}{hack_word}-fanart{ext}"
+    prestr = f"{number}{leak_word}{c_word}{hack_word}"
-    poster_path = f"{number}{leak_word}{c_word}{hack_word}-poster{ext}"
+    fanart_path =  f"{prestr}-fanart{ext}"
-    thumb_path =  f"{number}{leak_word}{c_word}{hack_word}-thumb{ext}"
+    poster_path = f"{prestr}-poster{ext}"
+    thumb_path =  f"{prestr}-thumb{ext}"
     full_fanart_path = os.path.join(path, fanart_path)
     full_poster_path = os.path.join(path, poster_path)
     full_thumb_path = os.path.join(path, thumb_path)
+    full_nfo = Path(path) / f"{prestr}{part}.nfo"
+
+    if full_nfo.is_file():
+        nfo = full_nfo.read_text(encoding='utf-8')
+        if nfo.find(r'<tag>无码</tag>'):
+            uncensored = 1
 
     if not all(os.path.isfile(f) for f in (full_fanart_path, full_thumb_path)):
         return
@@ -695,7 +705,8 @@ def core_main(movie_path, number_th, oCC):
 
     # 判断是否无码
     uncensored = 1 if is_uncensored(number) else 0
-
+    if json_data.get('无码'):
+        uncensored = 1
 
     if '流出' in movie_path or 'uncensored' in movie_path:
         liuchu = '流出'