Update app.py

app.py

@@ -15,6 +15,80 @@ logistic_model = joblib.load("Logistic_Model.joblib") # Logistic
 vectorizer = joblib.load('vectorizer.joblib') # global vocabulary
 tokenizer = joblib.load('tokenizer.joblib')
 
+def crawURL(url):
+    print(f"Crawling page: {url}")
+    # Fetch the sitemap
+    response = requests.get(sitemap_url)
+    # Parse the sitemap HTML
+    soup = BeautifulSoup(response.content, 'html.parser')
+
+    # Find all anchor tags that are children of span tags with class 'sitemap-link'
+    urls = [span.a['href'] for span in soup.find_all('span', class_='sitemap-link') if span.a]
+
+    # Crawl pages and extract data
+            try:
+                print(f"Crawling page: {url}")
+                # Fetch page content
+                page_response = requests.get(url)
+                page_content = page_response.content
+
+                # Parse page content with BeautifulSoup
+                soup = BeautifulSoup(page_content, 'html.parser')
+
+                # Extract data you need from the page
+                author = soup.find("meta", {"name": "author"}).attrs['content'].strip()
+                date_published = soup.find("meta", {"property": "article:published_time"}).attrs['content'].strip()
+                article_section = soup.find("meta", {"name": "meta-section"}).attrs['content']
+                url = soup.find("meta", {"property": "og:url"}).attrs['content']
+                headline = soup.find("h1", {"data-editable": "headlineText"}).text.strip()
+                description = soup.find("meta", {"name": "description"}).attrs['content'].strip()
+                keywords = soup.find("meta", {"name": "keywords"}).attrs['content'].strip()
+                text = soup.find(itemprop="articleBody")
+                # Find all <p> tags with class "paragraph inline-placeholder"
+                paragraphs = text.find_all('p', class_="paragraph inline-placeholder")
+
+                # Initialize an empty list to store the text content of each paragraph
+                paragraph_texts = []
+
+                # Iterate over each <p> tag and extract its text content
+                for paragraph in paragraphs:
+                    paragraph_texts.append(paragraph.text.strip())
+
+                # Join the text content of all paragraphs into a single string
+                full_text = ''.join(paragraph_texts)
+                return full_text
+
+            except Exception as e:
+                print(f"Failed to crawl page: {url}, Error: {str(e)}")
+                return null
+
+def process_api(text):
+    # Vectorize the text data
+    processed_text = vectorizer.transform([text])
+    sequence = tokenizer.texts_to_sequences([text])
+    padded_sequence = pad_sequences(sequence, maxlen=1000, padding='post')
+    # Get the predicted result from models
+    # Seq_Predicted = Seq_model.predict(padded_sequence)
+    SVM_Predicted = SVM_model.predict(processed_text).tolist()
+    Logistic_Predicted = logistic_model.predict(processed_text).tolist()
+
+    # predicted_label_index = np.argmax(Seq_Predicted)
+    return {
+            'Article_Content': text,
+            'SVM_Predicted': int(SVM_Predicted[0]),
+            'Logistic_Predicted': int(Logistic_Predicted[0])
+        }
+
+# Using Model to handle and return Category Route
+def categorize(url):
+    try:
+        article_content = crawURL(url)
+        result = process_api(article_content)
+        return result
+    except:
+        return "No text found in the response body"
+
+url = st.text_input("enter your CNN's URL here")
 # Test
 x = st.slider('Select a value')
 st.write(x, 'squared is', x * x)