Created
July 17, 2019 03:42
-
-
Save sergiolucero/d8ab6f5430c3e0d24e47aa06da8ac4e4 to your computer and use it in GitHub Desktop.
Scraping CNTV
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
import requests, pandas as pd | |
from bs4 import BeautifulSoup | |
CLIO_DEF = 'https://www.yapo.cl/chile/inmuebles?ca=15_s&l=0&q=casa&cmn=&st=a' | |
def text_search(bs, classname): | |
return [p0.text.strip() | |
for p0 in bs.find_all('span', attrs={'class': classname})] | |
def scrape_yapo(url = CLIO_DEF): | |
bs = BeautifulSoup(requests.get(url).text,'lxml') | |
NmaX = 47 | |
precios = text_search(bs, 'price')[:NmaX] | |
cprecios = text_search(bs, 'convertedPrice')[:NMaX] | |
regiones = text_search(bs, 'region')[:NMaX] | |
comunas = text_search(bs, 'commune')[:NMaX] | |
metros = text_search(bs, 'icons__element-text') | |
metros = [m for m in metros if 'm2' in m][:len(comunas)] # U CHEAT | |
descs = [p0.text for p0 in bs.find_all('a', attrs={'class':'title'})] | |
print([len(x) for x in [precios,cprecios,regiones,comunas,metros]]) | |
df = pd.DataFrame(dict(descripción=descs, region=regiones, comuna=comunas, | |
precio=precios, UF=cprecios, m2=metros)) | |
df['UF_m2'] = [row['UF'].split(' ')[1].split(',')[0].replace('.','') + '/' + | |
row['m2'].split(' ')[0] | |
for _, row in df.iterrows()] | |
return df | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment