Update app.py

app.py

@@ -6,6 +6,7 @@ def link_find(url):
     out = []
     source = requests.get(url)
     if source.status_code ==200:
+        print("YES")
         #soup = bs4.BeautifulSoup(source.content,'lxml')
         soup = bs4.BeautifulSoup(source.content,'html.parser')
         
@@ -15,7 +16,7 @@ def link_find(url):
         rawt=soup.text
         #out.append(rawp)
         #out.append("HTML fragments: ")
-        node1 = ({"URL":url,"TITLE":soup.title,"STRING":soup.description,"TEXT":rawt,"TREE":[]})    
+        node1 = {"URL":url,"TITLE":soup.title,"STRING":soup.description,"TEXT":rawt,"TREE":[]}
 
         q=("a","p","span","content","article")
         for p in soup.find_all("a"):
@@ -23,6 +24,7 @@ def link_find(url):
             #out.append({"URL":p.get('href'),"TITLE":p.get('title'),"STRING":p.string,"TEXT":"","TREE":[]})
     
     else:
+        print("NO")
         pass
     return node1
 #https://huggingface.co/spaces/Omnibus/crawl
@@ -42,7 +44,7 @@ def sitemap(url,level):
                         uri=f'{uri1}//{uri3}'
                         print(uri)
                     out_list=link_find(f"{uri}{ea['URL']}")
-                    #link1[i]['TREE']=out_list
+                    link1['TREE'][i]['TREE']=out_list
                     if level>=3:
                         for n,na in enumerate(link1['TREE'][i]['TREE']):
                             print(na)
@@ -54,7 +56,7 @@ def sitemap(url,level):
                                     uri0=f'{uri11}//{uri33}'
                                     print(uri0)
                                 out_list1=link_find(f"{uri0}{na['URL']}")
-                                #link1[i]['TREE'][n]['TREE']=out_list1
+                                link1['TREE'][i]['TREE'][n]['TREE']=out_list1
                             except Exception as e:
                                 print (e)
                 except Exception as e: