Я новичок в изучении веб-страниц и пытаюсь сделать это на этой странице https://www.metrocuadrado.com/bogota.
Идея состоит в том, чтобы извлечь всю информацию. До сих пор я был в состоянии сделать это только с одной страницей, но я не знаю, как сделать это с нумерацией страниц. Есть ли способ сделать это на основе кода, который у меня уже есть?
from urllib.request import urlopen as uReq
from bs4 import BeautifulSoup as soup
# opening up connection, grabbing html
my_url = 'https://www.metrocuadrado.com/bogota'
uClient = uReq(my_url)
page_html = uClient.read()
uClient.close()
# html parser
page_soup = soup(page_html, "html.parser")
# grabs each product
containers = page_soup.findAll("div",{"class":"detail_wrap"})
filename = "metrocuadrado.csv"
f = open(filename, "w")
headers= "propertytype, businestype, cityname, neighborhood, description, price, area\n"
f.write(headers)
for container in containers:
property_type = container[propertytype]
busines_type = container[businestype]
city_name = container[cityname]
neighborhood_location = container[neighborhood]
description = container.div.a.img["alt"]
price_container = container.findAll("span",{"itemprop":"price"})
price = price_container[0].text
area_container = container.findAll("div",{"class":"m2"})
area = area_container[0].p.span.text
print("property_type: " + property_type)
print("busines_type: " + busines_type)
print("city_name: " + city_name)
print("neighborhood_location: " + neighborhood_location)
print("description: " + description)
print("price: " + price)
print("area: " + area)
f.write(property_type + "," + busines_type + "," + city_name + "," + neighborhood_location + "," + description.replace(",", "|") + "," + price + "," + area + "\n")
f.close()