- Base de datos SQLite con información de vehículos - Dashboard web con Flask y Bootstrap - Scripts de web scraping para RockAuto - Interfaz CLI para consultas - Documentación completa del proyecto Incluye: - 12 marcas de vehículos - 10,923 modelos - 10,919 especificaciones de motores - 12,075 combinaciones modelo-año-motor
241 lines
7.9 KiB
Python
241 lines
7.9 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Scraper de Toyota para Windows
|
|
- Procesa de 3 en 3 años
|
|
- Espera 60 segundos entre lotes para activar VPN
|
|
- Años faltantes: 1975-2003
|
|
"""
|
|
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
import sqlite3
|
|
import time
|
|
import re
|
|
import os
|
|
import sys
|
|
from urllib.parse import unquote
|
|
|
|
# Detectar ruta base del proyecto
|
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
# Si estamos en vehicle_scraper, subir un nivel
|
|
if os.path.basename(SCRIPT_DIR) == "vehicle_scraper":
|
|
BASE_DIR = os.path.dirname(SCRIPT_DIR)
|
|
else:
|
|
BASE_DIR = SCRIPT_DIR
|
|
DB_PATH = os.path.join(BASE_DIR, "vehicle_database", "vehicle_database.db")
|
|
|
|
BASE_URL = "https://www.rockauto.com/en/catalog"
|
|
|
|
# Años que faltan por scrapear
|
|
MISSING_YEARS = [
|
|
2003, 2002, 2001, 2000, 1999, 1998, 1997, 1996, 1995, 1994,
|
|
1993, 1992, 1991, 1990, 1989, 1988, 1987, 1986, 1985, 1984,
|
|
1983, 1982, 1981, 1980, 1979, 1978, 1977, 1976, 1975
|
|
]
|
|
|
|
session = requests.Session()
|
|
session.headers.update({
|
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
|
'Accept': 'text/html,application/xhtml+xml',
|
|
'Accept-Language': 'en-US,en;q=0.9',
|
|
})
|
|
|
|
def clean_name(name):
|
|
name = unquote(name.replace('+', ' '))
|
|
return re.sub(r'\s+', ' ', name).strip().upper()
|
|
|
|
def get_soup(url, retries=3):
|
|
for attempt in range(retries):
|
|
try:
|
|
time.sleep(0.5)
|
|
response = session.get(url, timeout=15)
|
|
if response.status_code == 200:
|
|
return BeautifulSoup(response.content, 'html.parser')
|
|
elif response.status_code == 403:
|
|
print(f"\n [!] Bloqueado (403) - Cambia el VPN")
|
|
return None
|
|
except Exception as e:
|
|
if attempt < retries - 1:
|
|
time.sleep(3)
|
|
else:
|
|
print(f"\n Error: {e}")
|
|
return None
|
|
|
|
def get_models(brand, year):
|
|
brand_url = brand.lower().replace(' ', '+')
|
|
soup = get_soup(f"{BASE_URL}/{brand_url},{year}")
|
|
if not soup:
|
|
return []
|
|
|
|
models = set()
|
|
for link in soup.find_all('a', href=True):
|
|
pattern = rf'/catalog/{re.escape(brand_url)},{year},([^,/]+)'
|
|
match = re.search(pattern, link['href'], re.I)
|
|
if match:
|
|
model = clean_name(match.group(1))
|
|
if model and not model.isdigit() and len(model) > 1:
|
|
models.add(model)
|
|
return sorted(models)
|
|
|
|
def get_engines(brand, year, model):
|
|
brand_url = brand.lower().replace(' ', '+')
|
|
model_url = model.lower().replace(' ', '+')
|
|
soup = get_soup(f"{BASE_URL}/{brand_url},{year},{model_url}")
|
|
if not soup:
|
|
return ['STANDARD']
|
|
|
|
engines = set()
|
|
for link in soup.find_all('a', href=True):
|
|
pattern = rf'/catalog/{re.escape(brand_url)},{year},{re.escape(model_url)},([^,/]+)'
|
|
match = re.search(pattern, link['href'], re.I)
|
|
if match:
|
|
engine = clean_name(match.group(1))
|
|
if engine and re.search(r'\d+\.?\d*L|V\d|I\d|H\d|HYBRID|ELECTRIC|DIESEL', engine, re.I):
|
|
engines.add(engine)
|
|
return sorted(engines) if engines else ['STANDARD']
|
|
|
|
def save_to_db(conn, brand, year, model, engine):
|
|
cursor = conn.cursor()
|
|
try:
|
|
cursor.execute("INSERT OR IGNORE INTO brands (name) VALUES (?)", (brand,))
|
|
cursor.execute("SELECT id FROM brands WHERE name = ?", (brand,))
|
|
brand_id = cursor.fetchone()[0]
|
|
|
|
cursor.execute("INSERT OR IGNORE INTO years (year) VALUES (?)", (year,))
|
|
cursor.execute("SELECT id FROM years WHERE year = ?", (year,))
|
|
year_id = cursor.fetchone()[0]
|
|
|
|
cursor.execute("INSERT OR IGNORE INTO engines (name) VALUES (?)", (engine,))
|
|
cursor.execute("SELECT id FROM engines WHERE name = ?", (engine,))
|
|
engine_id = cursor.fetchone()[0]
|
|
|
|
cursor.execute("INSERT OR IGNORE INTO models (brand_id, name) VALUES (?, ?)", (brand_id, model))
|
|
cursor.execute("SELECT id FROM models WHERE brand_id = ? AND name = ?", (brand_id, model))
|
|
model_id = cursor.fetchone()[0]
|
|
|
|
cursor.execute(
|
|
"INSERT OR IGNORE INTO model_year_engine (model_id, year_id, engine_id) VALUES (?, ?, ?)",
|
|
(model_id, year_id, engine_id)
|
|
)
|
|
return cursor.rowcount > 0
|
|
except Exception as e:
|
|
print(f" DB Error: {e}")
|
|
return False
|
|
|
|
def get_existing_years(conn, brand):
|
|
"""Obtiene los años que ya existen para esta marca"""
|
|
cursor = conn.cursor()
|
|
cursor.execute("""
|
|
SELECT DISTINCT y.year
|
|
FROM years y
|
|
JOIN model_year_engine mye ON y.id = mye.year_id
|
|
JOIN models m ON mye.model_id = m.id
|
|
JOIN brands b ON m.brand_id = b.id
|
|
WHERE b.name = ?
|
|
""", (brand,))
|
|
return set(row[0] for row in cursor.fetchall())
|
|
|
|
def process_batch(conn, brand, years_batch, batch_num, total_batches):
|
|
"""Procesa un lote de 3 años"""
|
|
print(f"\n{'='*60}")
|
|
print(f"LOTE {batch_num}/{total_batches}: Años {years_batch}")
|
|
print('='*60)
|
|
|
|
batch_saved = 0
|
|
batch_total = 0
|
|
|
|
for year in years_batch:
|
|
print(f"\n[Año {year}] Obteniendo modelos... ", end="", flush=True)
|
|
models = get_models(brand, year)
|
|
print(f"{len(models)} modelos encontrados")
|
|
|
|
if not models:
|
|
print(f" No se encontraron modelos para {year}")
|
|
continue
|
|
|
|
for model in models:
|
|
engines = get_engines(brand, year, model)
|
|
for engine in engines:
|
|
batch_total += 1
|
|
if save_to_db(conn, brand, year, model, engine):
|
|
batch_saved += 1
|
|
print(f" {model} - {engine}")
|
|
|
|
# Guardar cambios del lote
|
|
conn.commit()
|
|
print(f"\n>> Lote {batch_num} completado: {batch_saved} nuevos de {batch_total} encontrados")
|
|
return batch_saved, batch_total
|
|
|
|
def main():
|
|
brand = "TOYOTA"
|
|
|
|
print("="*60)
|
|
print(" SCRAPER TOYOTA - WINDOWS")
|
|
print(" Procesa 3 años, guarda, espera 60s para VPN")
|
|
print("="*60)
|
|
|
|
# Verificar base de datos
|
|
if not os.path.exists(DB_PATH):
|
|
print(f"\n[ERROR] Base de datos no encontrada: {DB_PATH}")
|
|
print("Verifica que la ruta sea correcta.")
|
|
sys.exit(1)
|
|
|
|
print(f"\nBase de datos: {DB_PATH}")
|
|
|
|
conn = sqlite3.connect(DB_PATH)
|
|
|
|
# Verificar qué años ya existen
|
|
existing = get_existing_years(conn, brand)
|
|
print(f"Años existentes de {brand}: {sorted(existing)}")
|
|
|
|
# Filtrar solo los que faltan
|
|
years_to_process = [y for y in MISSING_YEARS if y not in existing]
|
|
|
|
if not years_to_process:
|
|
print("\n[OK] Todos los años ya están en la base de datos!")
|
|
conn.close()
|
|
return
|
|
|
|
print(f"\nAños por procesar: {years_to_process}")
|
|
print(f"Total: {len(years_to_process)} años")
|
|
|
|
# Dividir en lotes de 3
|
|
batches = [years_to_process[i:i+3] for i in range(0, len(years_to_process), 3)]
|
|
total_batches = len(batches)
|
|
|
|
print(f"Lotes de 3 años: {total_batches} lotes")
|
|
input("\nPresiona ENTER para comenzar...")
|
|
|
|
total_saved = 0
|
|
total_found = 0
|
|
|
|
for i, batch in enumerate(batches, 1):
|
|
saved, found = process_batch(conn, brand, batch, i, total_batches)
|
|
total_saved += saved
|
|
total_found += found
|
|
|
|
# Si no es el último lote, esperar para cambiar VPN
|
|
if i < total_batches:
|
|
print(f"\n{'*'*60}")
|
|
print(f" PAUSA DE 60 SEGUNDOS - ACTIVA/CAMBIA EL VPN AHORA")
|
|
print(f" Lotes restantes: {total_batches - i}")
|
|
print(f"{'*'*60}")
|
|
|
|
for sec in range(60, 0, -1):
|
|
print(f"\r Continuando en {sec} segundos... ", end="", flush=True)
|
|
time.sleep(1)
|
|
print()
|
|
|
|
conn.close()
|
|
|
|
print("\n" + "="*60)
|
|
print(" RESUMEN FINAL - TOYOTA")
|
|
print("="*60)
|
|
print(f" Años procesados: {len(years_to_process)}")
|
|
print(f" Vehículos encontrados: {total_found}")
|
|
print(f" Nuevos guardados: {total_saved}")
|
|
print("="*60)
|
|
|
|
if __name__ == "__main__":
|
|
main()
|