Beta 0.4 更新 *更好的错误提示

AV_Data_Capture.py

@@ -21,7 +21,8 @@ def movie_lists():
     total = a2+b2+c2+d2+e2+f2+g2
     return total
 
-def lists_from_test(custom_nuber):
+def lists_from_test(custom_nuber): #电影列表
+
     a=[]
     a.append(custom_nuber)
     return a
@@ -35,11 +36,25 @@ def CEF(path):
         except:
             a=''
 
+def rreplace(self, old, new, *max):
+#从右开始替换文件名中内容，源字符串，将被替换的子字符串， 新字符串，用于替换old子字符串，可选字符串, 替换不超过 max 次
+    count = len(self)
+    if max and str(max[0]).isdigit():
+        count = max[0]
+    return new.join(self.rsplit(old, count))
+
 if __name__ =='__main__':
     os.chdir(os.getcwd())
-    for i in movie_lists():
-        os.system('python core.py' + ' "' + i + '"')
+    for i in movie_lists(): #遍历电影列表 交给core处理
+        if '_' in i:
+            os.rename(i, rreplace(i,'_','-',1))
+            i = rreplace(i,'_','-',1)
+        os.system('python core.py' + ' "' + i + '"') #选择从py文件启动  （用于源码py）
+        #os.system('core.exe' + ' "' + i + '"')      #选择从exe文件启动（用于EXE版程序）
+        print("[*]=====================================")
+
     print("[!]Cleaning empty folders")
     CEF('JAV_output')
     print("[+]All finished!!!")
     time.sleep(3)
+    

core.py

@@ -12,13 +12,11 @@ import time
 #=====================爬虫核心部分==========================
 def get_html(url):#网页请求核心
     headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
-    getweb = requests.get(str(url),proxies={"http": "http://127.0.0.1:2334","https": "https://127.0.0.1:2334"},timeout=5,headers=headers).text
+    getweb = requests.get(str(url),timeout=5,headers=headers).text
     try:
         return getweb
-    except Exception as e:
-        print(e)
-    except IOError as e1:
-        print(e1)
+    except:
+        print("[-]Connect Failed! Please check your Proxy.")
 
 def getTitle(htmlcode):  #获取标题
     doc = pq(htmlcode)
@@ -75,17 +73,15 @@ def DownloadFileWithFilename(url,filename,path): #path = examle:photo , video.in
         with open(str(path) + "/"+str(filename), "wb") as code:
             code.write(r.content)
     except IOError as e:
-        print("[-]Download Failed1!")
-        print("[-]Error:"+str(e))
-        print("[-]Movie not found in Javbus.com!")
-        print("[*]=====================================")
+        print("[-]Movie not found in All website!")
+        #print("[*]=====================================")
         return "failed"
     except Exception as e1:
         print(e1)
         print("[-]Download Failed2!")
         time.sleep(3)
         os._exit(0)
-def PrintFiles(html,path):
+def PrintFiles(html,path,number):
     try:
         if not os.path.exists(path):
             os.makedirs(path)
@@ -96,8 +92,8 @@ def PrintFiles(html,path):
             print("  </set>", file=code)
             print("  <studio>" + getStudio(html) + "+</studio>", file=code)
             print("  <year>" + getYear(html) + "</year>", file=code)
-            print("  <outline>"+getOutline(html)+"</outline>", file=code)
-            print("  <plot>"+getOutline(html)+"</plot>", file=code)
+            print("  <outline>"+getOutline(get_html_dww(number))+"</outline>", file=code)
+            print("  <plot>"+getOutline(get_html_dww(number))+"</plot>", file=code)
             print("  <runtime>"+str(getRuntime(html)).replace(" ","")+"</runtime>", file=code)
             print("  <director>" + getDirector(html) + "</director>", file=code)
             print("  <poster>" + getNum(html) + ".png</poster>", file=code)
@@ -196,6 +192,6 @@ if __name__ == '__main__':
     htmlcode=get_html_javbus(number) #获取的HTML代码
     creatFolder(htmlcode,number) #创建文件夹
     imageDownload(htmlcode,filepath,number) #creatFoder会返回番号路径
-    PrintFiles(htmlcode, path)#打印文件
+    PrintFiles(htmlcode, path,number)#打印文件
     cutImage(number) #裁剪图
     pasteFileToFolder(filepath,number,path) #移动文件