CarWale & Yalla Motors Spec Mapping Tutorial

Array ( [as_domain] => amazon.com [as_name] => Amazon.com, Inc. [asn] => AS16509 [continent] => North America [continent_code] => NA [country] => United States [country_code] => US )

Start Your Project

import undetected_chromedriver as uc from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from time import sleep browser = uc.Chrome() browser.get("https://www.carwale.com/new-cars/") sleep(4)

for card in launch_cards: try: name = card.find_element(By.CLASS_NAME, "o-bkmzIL").text except: name = "" try: price = card.find_element(By.CLASS_NAME, "o-bkzfWJ").text except: price = "" try: launch_date = card.find_element(By.CLASS_NAME, "o-cpnuEd").text except: launch_date = "" try: url = card.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" carwale_launches.append({ "platform": "CarWale", "model_name": name, "expected_price": price, "launch_date": launch_date, "url": url })

import requests from bs4 import BeautifulSoup def scrape_carwale_specs(url): try: html = requests.get(url, timeout=10).text soup = BeautifulSoup(html, "lxml") spec_block = soup.find("div", {"id": "specifications"}) if not spec_block: return {} specs = {} rows = spec_block.find_all("tr") for row in rows: cols = row.find_all("td") if len(cols) == 2: key = cols[0].text.strip() val = cols[1].text.strip() specs[key] = val return specs except: return {}

for item in cards: try: name = item.find_element(By.CLASS_NAME, "model-title").text except: name = "" try: price = item.find_element(By.CLASS_NAME, "model-price").text except: price = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" yalla_records.append({ "platform": "Yalla Motors", "model_name": name, "price": price, "url": url })

def scrape_yalla_specs(url): try: html = requests.get(url, timeout=10).text soup = BeautifulSoup(html, "lxml") specs_table = soup.find("table", {"class": "specs-table"}) if not specs_table: return {} specs = {} rows = specs_table.find_all("tr") for row in rows: cols = row.find_all("td") if len(cols) == 2: specs[cols[0].text.strip()] = cols[1].text.strip() return specs except: return {}

import re def extract_engine(val): match = re.search(r"(\d+)\s?cc", val.lower()) return int(match.group(1)) if match else None Apply: df["engine_cc"] = df["specifications"].apply(lambda x: extract_engine(x.get("Engine", "")) if isinstance(x, dict) else None) Extract power (hp / bhp) def extract_hp(val): match = re.search(r"(\d+)\s?(hp|bhp)", val.lower()) return int(match.group(1)) if match else None Extract mileage / fuel economy def extract_mileage(val): match = re.search(r"(\d+\.?\d*)\s?(km\/l|mpg)", val.lower()) return float(match.group(1)) if match else None

Array ( [as_domain] => amazon.com [as_name] => Amazon.com, Inc. [asn] => AS16509 [continent] => North America [continent_code] => NA [country] => United States [country_code] => US )

Start Your Project

Our Data Drives Impact - Real Client Stories