Update app.py

app.py

@@ -35,39 +35,16 @@ def find_all(url):
             source = requests.get(url)
             #source = urllib.request.urlopen(url).read()
             soup = bs4.BeautifulSoup(source.content,'lxml')
-            # title of the page
-            print(soup.title)
-            # get attributes:
-            print(soup.title.name)
-            # get values:
-            print(soup.title.string)
-            # beginning navigation:
-            print(soup.title.parent.name)
-            #rawp.append([tag.name for tag in soup.find_all()] )
-            print([tag.name for tag in soup.find_all()])
-            #rawp=(f'RAW TEXT RETURNED: {soup.text}')
-            rawp=(f'RAW HTML RETURNED: {soup}')
+
+            rawp=(f'RAW TEXT RETURNED: {soup.text}')
+            cnt=0
+            cnt+=len(rawp)
             out.append(rawp)
+            out.append("HTML fragments: ")
             q=("a","p","span","content","article")
-            for p in soup.find_all(q):
-                out.append([{q:p.string,"parent":p.parent.name,"previous":[p.previous],"first-child":[b.name for b in p.children],"content":p}])
-            #print (f'OUT :: {out}')
-            '''
-            c=0
-            out = str(out)
-            rl = len(out)
-            print(f'rl:: {rl}')
-            #for ea in out:
-            for i in str(out):
-                if i == " " or i=="," or i=="\n":
-                    c +=1
-            print (f'c:: {c}')
-            if rl > MAX_DATA:
-                print("compressing...")
-                rawp = compress_data(c,purpose,task,out)    
-            print (rawp)
-            print (f'out:: {out}')
-            '''
+            for p in soup.find_all("a"):
+                out.append([{"LINK TITLE":p.get('title'),"URL":p.get('href'),"STRING":p.string}])
+  
             print(rawp)
             return True, rawp
         else: