Search Data

আগে আমরা প্রজেক্ট বানিয়েছিলাম এবার মডেল বানিয়ে বাকি কাজগুলো করবো

এই টিউটোরিয়ালে আমরা এই ওয়েবসাইটের https://subslikescript.com/ যেকোনো পেজ (সিঙ্গেল পেজ না ) এর প্রথম পেজ থেকে লিংক ও টাইটেল স্ক্রাপ করে csv ফাইল আকারে ডাউনলোড করতে পারবো। এজন্য আমাদের pandas ইন্স্টল্ করতে হবে।

pip install pandas

myapp/models.py

from django.db import models

class ScrapedData(models.Model):
    title = models.CharField(max_length=255,default="")
    description = models.TextField(default="")

    def __str__(self):
        return self.title

Migrate Database

python manage.py makemigrations
python manage.py migrate

forms.py

# myapp/forms.py
from django import forms

class ScrapeForm(forms.Form):
    url = forms.CharField(max_length=100, widget=forms.TextInput(attrs={'placeholder': 'Enter URL'}))

myapp/views.py

from django.shortcuts import render
from django.http import HttpResponse
from .forms import ScrapeForm
from .models import ScrapedData
import requests
from bs4 import BeautifulSoup
import pandas as pd

# Create your views here.

def scrape_and_save(request):
    if request.method == 'POST':
        form = ScrapeForm(request.POST)
        if form.is_valid():
            url = form.cleaned_data['url']
            response = requests.get(url)

            if response.status_code == 200:
                soup = BeautifulSoup(response.content, 'html.parser')
                # Extract data from the soup and save to the database
                movie_list = soup.find('ul', class_='scripts-list')
                root = 'https://subslikescript.com'
                link = movie_list.find_all('a', href=True)
                data = []

                for links in link:
                    title = links.text.strip()
                    url = f'{root}{links["href"]}'
                    data.append({'Title': title, 'URL': url})
                    
                # Convert data to DataFrame
                df = pd.DataFrame(data)
                
                # Convert DataFrame to CSV
                csv_data = df.to_csv(index=False)   
                
                             
                # Set up HTTP response
                response = HttpResponse(csv_data, content_type='text/csv')
                response['Content-Disposition'] = 'attachment; filename="scraped_data.csv"'
                
                return response

    else:
        form = ScrapeForm()
        
    return render(request, 'search.html', {'form': form})

templates/search.html

<!-- myapp/templates/scrape.html -->

<form method="post" >
    {% csrf_token %}
    {{ form.as_p }}
    <button type="submit">Scrape and Save</button>
</form>

urls.py

from django.urls import path
from .views import scrape_and_save

urlpatterns = [
        path('scrape/', scrape_and_save, name='scrape_and_save'),

]