# IR Prac

```python
******************************Practical 6**************************************

Aim: Write a program for Pre-processing of a Text Document: stop word removal.

Stopwords.py
import nltk
nltk.download('stopwords')
nltk.download('punkt')
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
file=open('sample.txt')
send=file.read()
stop=(stopwords.words('english'))
token=word_tokenize(send)
a=[]
for w in token:
    if w not in stop:
        a.append(w)
        print("Original sentence:",token)
        print("========================")
        print("stop words:",stop)
        print("=================")
        print("Stop words removal:",a)
        print("======================")
        print("".join(a))

OUTPUT:
   
****************************Practical 8****************************************

Aim: Write a program to implement simple web crawler.

a. 
import requests
x=requests.get("https://open.spotify.com/")
print(x.text)
print(x.headers)

b. 
import requests
from bs4 import BeautifulSoup
plain_text=requests.get('https://www.formula1.com/').text
s=BeautifulSoup(plain_text,"html.parser")
for link in s.findAll("img"):
    tet=link.getText()
    print(tet)
    print(link)
    print(plain_text)

print("")
print(s.text)
print(s.status_code)

OUTPUT:

 

 
 
 

```