Updated Project, reads files and extracts links, but problems with threads
This commit is contained in:
parent
902f347771
commit
220045b92b
|
|
@ -0,0 +1,69 @@
|
|||
import os
|
||||
import threading
|
||||
import queue
|
||||
import time
|
||||
from WebFileReader import WebFileReader
|
||||
|
||||
print("Directorio actual:", os.getcwd())
|
||||
|
||||
# Inicializa colas para la comunciación entre hilos
|
||||
data_queue = queue.Queue()
|
||||
link_queue = queue.Queue()
|
||||
|
||||
# Instancia de WebFileReader
|
||||
reader = WebFileReader()
|
||||
|
||||
# Hilo A: Lee el archivos HTML y los coloca en data_queue
|
||||
def hilo_a():
|
||||
filenames = ["index.html", "1.html", "2.html"]
|
||||
for filename in filenames:
|
||||
print(f"[Hilo A] Leyendo archivo: {filename}")
|
||||
content = reader.read_file(filename)
|
||||
if content:
|
||||
data_queue.put((filename, content))
|
||||
time.sleep(1) #Simulacion del tiempo de espera
|
||||
|
||||
# Hilo B: Extrae los enlaces del contenido HTML y los coloca en link_queue
|
||||
def hilo_b():
|
||||
while True:
|
||||
if not data_queue.empty():
|
||||
filename, html_content = data_queue.get()
|
||||
print(f"[Hilo B] Extrayendo enlaces de: {filename}")
|
||||
links = reader.extract_links(html_content)
|
||||
for link in links:
|
||||
link_queue.put(link)
|
||||
|
||||
# Hilo C: Guarda el contenido de los archivos en archivos de texto en la carpeta resources
|
||||
def hilo_c():
|
||||
while True:
|
||||
if not data_queue.empty():
|
||||
filename, html_content = data_queue.get()
|
||||
save_path = f"EjerciciosConHilos/Ejercicio04_WebScrapper/resources/output/{filename.replace('.html', '')}_content.txt"
|
||||
with open(save_path, 'w', encoding='utf-8') as file:
|
||||
file.write(html_content)
|
||||
print(f"[Hilo C] Guardando contenido de {filename} en {save_path}")
|
||||
|
||||
# Hilo D: Guarda los enlaces extraídos en un archivo de texto para análisis
|
||||
def hilo_d():
|
||||
while True:
|
||||
if not link_queue.empty():
|
||||
link = link_queue.get()
|
||||
with open("EjerciciosConHilos/Ejercicio04_WebScrapper/resources/output/extracted_links.txt", 'a', encoding='utf-8') as file:
|
||||
file.write(link + "\n")
|
||||
print(f"[Hilo D] Enlace guardado: {link}")
|
||||
|
||||
thread_a = threading.Thread(target=hilo_a, daemon=True)
|
||||
thread_b = threading.Thread(target=hilo_b, daemon=True)
|
||||
thread_c = threading.Thread(target=hilo_c, daemon=True)
|
||||
thread_d = threading.Thread(target=hilo_d, daemon=True)
|
||||
|
||||
thread_a.start()
|
||||
thread_b.start()
|
||||
thread_c.start()
|
||||
thread_d.start()
|
||||
|
||||
try:
|
||||
while True:
|
||||
time.sleep(1)
|
||||
except KeyboardInterrupt:
|
||||
print("Programa terminado")
|
||||
|
|
@ -1 +1,31 @@
|
|||
import mysql.connector
|
||||
import os
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
class WebFileReader:
|
||||
def __init__(self, base_path="EjerciciosConHilos/Ejercicio04_WebScrapper/resources/input_html"):
|
||||
self.base_path = base_path
|
||||
|
||||
def read_file(self, filename):
|
||||
"""
|
||||
Lee un archivo HTML y devuelve su contenido como texto.
|
||||
"""
|
||||
filepath = os.path.join(self.base_path, filename)
|
||||
try:
|
||||
with open(filepath, 'r', encoding='utf-8') as file:
|
||||
return file.read()
|
||||
except FileNotFoundError:
|
||||
print(f"[WebFileReader] Archivo no encontrado: {filepath}")
|
||||
return None
|
||||
except Exception as e:
|
||||
print(f"[WebFileReader] Error al leer el archivo {filepath}: {str(e)}")
|
||||
return None
|
||||
|
||||
def extract_links(self, html_content):
|
||||
"""
|
||||
Extrae todos los enlaces de un contenido HTML dado.
|
||||
"""
|
||||
soup = BeautifulSoup(html_content, 'html.parser')
|
||||
links = [a['href'] for a in soup.find_all('a', href=True)]
|
||||
return links
|
||||
|
||||
|
||||
|
|
|
|||
Binary file not shown.
|
|
@ -0,0 +1,11 @@
|
|||
<html lang="es">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Página 1</title>
|
||||
</head>
|
||||
<BODY>
|
||||
<a href="2.html">Ir a página 2</a>
|
||||
<br>
|
||||
<a href="index.html">Volver</a>
|
||||
</BODY>
|
||||
</html>
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
<html lang="es">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Página 2</title>
|
||||
</head>
|
||||
<BODY>
|
||||
<a href="1.html">Ir a página 1</a>
|
||||
<br>
|
||||
<a href="index.html">Volver</a>
|
||||
</BODY>
|
||||
</html>
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
<html lang="es">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Inicio</title>
|
||||
</head>
|
||||
<BODY>
|
||||
<a href="1.html">Ir a página 1</a>
|
||||
</BODY>
|
||||
</html>
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
<html lang="es">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Página 1</title>
|
||||
</head>
|
||||
<BODY>
|
||||
<a href="2.html">Ir a página 2</a>
|
||||
<br>
|
||||
<a href="index.html">Volver</a>
|
||||
</BODY>
|
||||
</html>
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
2.html
|
||||
index.html
|
||||
1.html
|
||||
index.html
|
||||
1.html
|
||||
1.html
|
||||
index.html
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
<html lang="es">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Inicio</title>
|
||||
</head>
|
||||
<BODY>
|
||||
<a href="1.html">Ir a página 1</a>
|
||||
</BODY>
|
||||
</html>
|
||||
Loading…
Reference in New Issue