Created
October 2, 2018 17:46
-
-
Save antoniocuga/b3e794caf6e82c128ce86428aa064593 to your computer and use it in GitHub Desktop.
Descarga de productos usando un screenscrapper con selenium webdriver, BeautifulSoup y Pandas.
This file contains 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
from bs4 import BeautifulSoup as bs | |
import requests as rq | |
import json | |
from selenium import webdriver | |
from selenium.webdriver.common.keys import Keys | |
import pandas as pd | |
import time | |
base_path = "http://www.fischelenlinea.com/" | |
search_url = "Catalogo.aspx?Busqueda=Sqg&Categoria=Sqgnooj" | |
prices_url = "Catalogo.aspx/_productGetPrecioPresentacion" | |
productos_final = [] | |
def call_page_pagination(): | |
url = base_path + search_url | |
# create a new Firefox session | |
driver = webdriver.Firefox() | |
driver.get(url) | |
driver.implicitly_wait(60) | |
print "--- Init download ---" | |
for npage in range(1,3): | |
driver.execute_script("__doPostBack('uc_Paginador$btSiguiente','')") | |
driver.implicitly_wait(35) | |
process_page(driver.page_source) | |
time.sleep(10) | |
return False | |
def get_price(producto_id, presentacion_id): | |
headers = {"X-Requested-With": 'XMLHttpRequest', | |
"Content-Type": 'application/json; charset=utf-8'} | |
data = '{"_idProducto":"%s","_idPresentacion":"%s","_signoMoneda":""}' % (producto_id, presentacion_id) | |
x = rq.post(base_path + prices_url, data=data, headers=headers) | |
price = json.loads(x.text) | |
print "Descargando precios para producto %s" % producto_id | |
return price["d"] | |
def process_page(response): | |
#load_page(base_path + search_url) | |
response = bs(response, 'html.parser') | |
lista_productos = response.find_all( | |
"div", class_="catalogoprductos" | |
) | |
for p in lista_productos: | |
values = p.find_all(class_="textocatalogo") | |
producto_id = p.find("a", class_="texcata")["id"] | |
producto_id = producto_id.replace("_lbl_NombreProducto", "_hf_CodigoProducto") | |
producto_id = response.find(id=producto_id)["value"] | |
npage = response.find(id="uc_Paginador_cont_bot_numeros") | |
npage = npage.find(class_="b-numero1").text | |
producto = { | |
"producto_id": producto_id, | |
"url": (("%s%s") % (base_path, p.find("a", class_="texcata")["href"])).encode('utf8'), | |
"nombre":( p.find("a", class_="texcata").text).encode('utf8'), | |
"imagen": (("%s%s") % (base_path,p.find("img")['src'])).encode('utf8'), | |
"marca": (values[0].text).encode('utf8'), | |
"descripcion": (p.find("div", class_="textocatalogo2").text).encode('utf8'), | |
"pagina": npage, | |
#"suelto": get_price(producto_id, "2"), | |
#"caja": get_price(producto_id, "3") | |
} | |
productos_final.append(producto) | |
#Message after download | |
print("Download page %s" % npage) | |
def download_products(filename): | |
#Init download | |
call_page_pagination() | |
#Guardar archivos sin precio | |
pd.DataFrame(productos_final).to_csv(filename, sep=',', na_rep='') | |
def process_prices(filename): | |
#Archivo de productos sin precio | |
lista_productos = pd.read_csv(filename) | |
#Presentacion_id: 2 para precio suelto | |
lista_productos['precio_suelto'] = lista_productos.apply(lambda x: get_price(x['producto_id'], "2"), axis=1) | |
#Presentacion_id: 3 para precio caja | |
lista_productos['precio_caja'] = lista_productos.apply(lambda x: get_price(x['producto_id'], "3"), axis=1) | |
#Actualizar nuevo archivo con precios | |
lista_productos.to_csv("precios_%s" % filename, sep=',', na_rep='') | |
return False | |
if __name__ == '__main__': | |
#Nombre del archivo para guardar los productos descargados | |
filename = "final_206.csv" | |
#To download products | |
#download_products(filename) | |
#Descargar precios usando la lista de productos descargados. El archivo final sera "precios_(filename)" | |
process_prices(filename) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment