Created
February 25, 2018 17:52
-
-
Save fransafu/3e5865ae1da7a88e38f40ad72c264b27 to your computer and use it in GitHub Desktop.
Web scraping of site web informeperros.com
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
from pprint import pprint | |
from bs4 import BeautifulSoup | |
import requests | |
import json | |
URL = 'http://informeperros.com/lista-de-todas-las-razas-de-perros-por-orden-alfabetico/' | |
def main(): | |
# Realizamos un GET a la pagina web | |
req = requests.get(URL) | |
# Utilizamos un parse con el formato lxml | |
soup = BeautifulSoup(req.text, "lxml") | |
# Buscamos todos los <td></td> que existan en el sitio web | |
columnas = soup.find_all('td') | |
# Crear diciconario de almacenamiento | |
diccionarioRazas = [] | |
# Objeto auxiliar | |
dicAux = {} | |
for columna in columnas: | |
# Buscamos el tag <img> dentro de los datos ya filtrados por <td> | |
imagen = columna.find('img') | |
if (imagen != None): | |
urlImagen = imagen["src"] | |
nombreImagen = urlImagen.split("/")[len(urlImagen.split("/")) - 1] | |
# Descargar imagenes | |
with open("imagenes/" + nombreImagen, "wb") as archivo: | |
img = requests.get(urlImagen, stream=True) | |
archivo.write(img.content) | |
dicAux["urlImagen"] = imagen["src"] | |
dicAux["raza"] = imagen["title"] | |
diccionarioRazas.append(dicAux) | |
dicAux = {} | |
# Grabar archivo con las razas | |
with open("razas.json", "w") as archivoRazas: | |
jsonText = json.dumps(diccionarioRazas, indent=4, sort_keys=True) | |
archivoRazas.write(jsonText) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment