Implemetacion del scraping ya funcional

This commit is contained in:
Santiago Parra 2024-12-13 23:39:52 +01:00
parent 332d0465b6
commit b44271753d
5 changed files with 113 additions and 1 deletions

View File

@ -13,6 +13,7 @@ from app.widgets.TicTacToeTab import TicTacToeTab
from app.widgets.TodoTab import TodoTab
from app.widgets.UsageLabels import CPULabel, RAMLabel, BatteryLabel, NetworkLabel
from app.widgets.WeatherTab import WeatherTab
from app.widgets.WebScrapingTab import WebScrapingTab
stop_event = threading.Event()
@ -133,6 +134,11 @@ tic_tac_toe_tab = TicTacToeTab(notebook, stop_event=stop_event)
tic_tac_toe_tab.pack(fill="both", expand=True)
notebook.add(tic_tac_toe_tab, text="Tic Tac Toe")
# Add the TodoTab to the notebook
web_scraping_tab = WebScrapingTab(notebook, stop_event=stop_event)
web_scraping_tab.pack(fill="both", expand=True)
notebook.add(web_scraping_tab, text="Web Scraping")
# Create the chat and music player frames within the right frame
frame_chat = tk.Frame(frame_right, bg="lightgreen")
frame_music_player = tk.Frame(frame_right)

View File

@ -0,0 +1,105 @@
import tkinter as tk
from tkinter import Frame, Button, Label, Entry, Listbox, StringVar, messagebox
import mysql.connector
import requests
from bs4 import BeautifulSoup
from app.widgets.abc import ThreadedTab
class WebScrapingTab(ThreadedTab):
def __init__(self, root: Frame | tk.Tk, stop_event, **kwargs):
# Inicializa los atributos necesarios antes de llamar a la clase base
self.url = StringVar()
self.data = []
self.conn = None # La conexión se inicializa después
super().__init__(root, stop_event, **kwargs) # Llama al constructor de ThreadedTab
self.conn = self.create_database() # Crea o conecta a la base de datos
def build(self):
# Main frame
self.scraping_frame = Frame(self)
self.scraping_frame.pack(fill="both", expand=True)
# Input field for URL
Label(self.scraping_frame, text="Enter URL:", font=("Arial", 12)).pack(pady=5)
Entry(self.scraping_frame, textvariable=self.url, font=("Arial", 12), width=50).pack(pady=5)
# Buttons for actions
Button(self.scraping_frame, text="Scrape", command=self.scrape_website).pack(pady=5)
Button(self.scraping_frame, text="View Data", command=self.view_data).pack(pady=5)
# Listbox to display scraped data
self.data_listbox = Listbox(self.scraping_frame, font=("Arial", 10), width=80, height=20)
self.data_listbox.pack(pady=10)
def create_database(self):
# Connect to MySQL database
conn = mysql.connector.connect(
host="127.0.0.1 ",
user="santipy",
password="1234",
database="scraping_db"
)
cursor = conn.cursor()
# Crear la tabla si no existe
cursor.execute("""
CREATE TABLE IF NOT EXISTS scraped_data (
id INT AUTO_INCREMENT PRIMARY KEY,
title VARCHAR(255),
link TEXT
)
""")
conn.commit()
return conn
def save_to_database(self):
cursor = self.conn.cursor()
query = "INSERT INTO scraped_data (title, link) VALUES (%s, %s)"
cursor.executemany(query, self.data)
self.conn.commit()
def scrape_website(self):
url = self.url.get()
if not url:
messagebox.showwarning("Warning", "Please enter a URL.")
return
try:
response = requests.get(url)
response.raise_for_status()
except requests.RequestException as e:
messagebox.showerror("Error", f"Failed to fetch URL: {e}")
return
soup = BeautifulSoup(response.text, "html.parser")
items = soup.select("h2 a") # Modify selector based on website structure
self.data = [(item.get_text(strip=True), item.get("href")) for item in items]
if self.data:
self.save_to_database()
messagebox.showinfo("Success", f"Scraped {len(self.data)} items and saved to database.")
else:
messagebox.showinfo("No Data", "No data found on the page.")
self.update_listbox()
def update_listbox(self):
self.data_listbox.delete(0, "end")
for title, link in self.data:
self.data_listbox.insert("end", f"Title: {title} | Link: {link}")
def view_data(self):
cursor = self.conn.cursor()
cursor.execute("SELECT title, link FROM scraped_data")
rows = cursor.fetchall()
self.data_listbox.delete(0, "end")
for title, link in rows:
self.data_listbox.insert("end", f"Title: {title} | Link: {link}")
def task(self):
# Placeholder for any background task
pass

View File

@ -1,4 +1,5 @@
from .ClockLabel import ClockLabel
from .UsageLabels import CPULabel, RAMLabel
from .WebScrapingTab import WebScrapingTab
__all__ = ['ClockLabel', 'CPULabel', 'RAMLabel']
__all__ = ['ClockLabel', 'CPULabel', 'RAMLabel', 'WebScrapingTab']

Binary file not shown.