Update sites

scrapinglib/api.py

@@ -221,8 +221,9 @@ class Scraping:
                 sources = ["pcolle"]
             elif "fc2" in lo_file_number:
                 if "fc2" in sources:
-                    sources = insert(sources, "msin")
+                    sources = ["msin", "fc2"]
-                    sources = insert(sources, "fc2")
+                    # sources = insert(sources, "msin")
+                    # sources = insert(sources, "fc2")
             elif "mgstage" in sources and \
                     (re.search(r"\d+\D+", file_number) or "siro" in lo_file_number):
                 sources = insert(sources, "mgstage")
@@ -245,7 +246,7 @@ class Scraping:
                 todel.append(s)
         for d in todel:
             if config.getInstance().debug():
-                print('[!] Remove Source : ' + s)
+                print('[!] Remove Source : ' + d)
             sources.remove(d)
         return sources
 

scrapinglib/dlsite.py

@@ -97,3 +97,8 @@ class Dlsite(Parser):
         except:
             result = ''
         return result
+
+    def getTags(self, htmltree):
+        tags = super().getTags(htmltree)
+        tags.append("DLsite")
+        return tags

scrapinglib/getchu.py

@@ -95,9 +95,15 @@ class wwwGetchu(Parser):
     def extradict(self, dic: dict):
         """ 额外新增的  headers
         """
-        dic['headers'] =  {'referer': self.detailurl}
+        dic['headers'] = {'referer': self.detailurl}
         return dic
 
+    def getTags(self, htmltree):
+        tags = super().getTags(htmltree)
+        tags.append("Getchu")
+        return tags
+
+
 class dlGetchu(wwwGetchu):
     """ 二者基本一致
     headers extrafanart 略有区别
@@ -140,7 +146,7 @@ class dlGetchu(wwwGetchu):
 
     def extradict(self, dic: dict):
         return dic
-    
+
     def getExtrafanart(self, htmltree):
         arts = self.getTreeAll(htmltree, self.expr_extrafanart)
         extrafanart = []
@@ -148,3 +154,8 @@ class dlGetchu(wwwGetchu):
             i = "https://dl.getchu.com" + i
             extrafanart.append(i)
         return extrafanart
+
+    def getTags(self, htmltree):
+        tags = super().getTags(htmltree)
+        tags.append("Getchu")
+        return tags

scrapinglib/parser.py

@@ -219,7 +219,6 @@ class Parser:
                 if tag:
                     tags.append(tag)
         return tags
-        return [ x.strip() for x in alls if x.strip()]
 
     def getStudio(self, htmltree):
         return self.getTreeElementbyExprs(htmltree, self.expr_studio, self.expr_studio2)