diff --git a/sample_data.xlsx b/sample_data.xlsx
new file mode 100644
index 000000000..4d3b3f5a0
Binary files /dev/null and b/sample_data.xlsx differ
diff --git a/scripts/preprocessing.py b/scripts/preprocessing.py
new file mode 100644
index 000000000..131be10fe
--- /dev/null
+++ b/scripts/preprocessing.py
@@ -0,0 +1,37 @@
+import pandas as pd
+import string, re
+from nltk.tokenize import word_tokenize
+from nltk.corpus import stopwords
+import nltk
+from nltk.stem import PorterStemmer, WordNetLemmatizer
+from sentence_transformers import SentenceTransformer
+
+nltk.download('wordnet')
+nltk.download('punkt_tab')
+nltk.download('stopwords')
+
+stop_words = set(stopwords.words('english'))
+
+stemmer = PorterStemmer()
+lemmatizer = WordNetLemmatizer()
+
+model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+
+df = pd.read_excel('C:\\Users\\ishaa\\OneDrive\\Documents\\MSU\\Spring 2026\\Data mining\\Project\\sample_data.xlsx', engine='openpyxl')
+
+def clean_text(text):
+    text = text.lower()
+    text = text.translate(str.maketrans('', '', string.punctuation))  # Remove punctuation
+    text = re.sub(r'\W', ' ', text)  # Remove special characters
+    text = ([word for word in word_tokenize(text) if word not in stop_words])
+    text = [stemmer.stem(word) for word in text]
+    text = ' '.join(lemmatizer.lemmatize(word) for word in text)
+    return text
+# print(df.columns)
+
+df['preprocessed'] = df['Plot'].apply(clean_text)
+sample_plot = df['preprocessed'][0]
+print(sample_plot)
+
+embeddings = model.encode(sample_plot)
+print(embeddings)
\ No newline at end of file
diff --git a/scripts/scrape.py b/scripts/scrape.py
index fb9f976ac..ac0a44926 100644
--- a/scripts/scrape.py
+++ b/scripts/scrape.py
@@ -9,8 +9,8 @@ headers = {
 params = {
     "action": "query",
     "format": "json",
+    "titles": "Godfather",
     "prop": "extracts",
-    "titles": "Interstellar",
     "explaintext": True,
     "redirects": 1
 }
@@ -19,12 +19,14 @@ response = requests.get(url, headers=headers, params=params)
 
 print("Status:", response.status_code)
 print("Content-Type:", response.headers.get("content-type"))
-print("First 200 chars:\n", response.text[:200])
+print("First 200 chars:\n", response.text[:1000])
 
 data = response.json()
 
+
+
 pages = data["query"]["pages"]
 page = next(iter(pages.values()))
 
 print("\nTitle:", page["title"])
-print("\nPreview:\n", page["extract"][:500])
+print("\nPreview:\n", page["extract"])