Kids Product Scraper Tutorial for FirstCry & Walmart

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

from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from time import sleep import pandas as pd import requests from bs4 import BeautifulSoup browser = webdriver.Chrome() browser.get("https://www.firstcry.com/diapers") sleep(4)

firstcry_records = [] for item in items: try: name = item.find_element(By.CLASS_NAME, "li_title").text except: name = "" try: price = item.find_element(By.CLASS_NAME, "li_final_price").text except: price = "" try: mrp = item.find_element(By.CLASS_NAME, "li_mrp").text except: mrp = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" try: img = item.find_element(By.TAG_NAME, "img").get_attribute("src") except: img = "" firstcry_records.append({ "platform": "FirstCry", "name": name, "price": price, "mrp": mrp, "url": url, "image_url": img })

walmart_records = [] for item in w_items: try: name = item.find_element(By.CLASS_NAME, "product-title-link").text except: name = "" try: price = item.find_element(By.CLASS_NAME, "price-main").text except: price = "" try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") except: url = "" try: img = item.find_element(By.TAG_NAME, "img").get_attribute("src") except: img = "" walmart_records.append({ "platform": "Walmart", "name": name, "price": price, "mrp": "", "url": url, "image_url": img })

def clean_title(t): t = t.lower() remove_words = ["buy now", "discount", "pack of", "pcs", "girls", "boys"] for w in remove_words: t = t.replace(w, "") return t.strip() df["clean_title"] = df["name"].apply(clean_title)

def classify_type(t): t = t.lower() if "diaper" in t: return "Diapers" if "toy" in t or "lego" in t or "puzzle" in t: return "Toys" if "bottle" in t or "sipper" in t: return "Feeding" if "dress" in t or "shirt" in t: return "Kids Apparel" return "Other" df["category"] = df["clean_title"].apply(classify_type)

import os from PIL import Image from io import BytesIO os.makedirs("kid_images", exist_ok=True) def download_image(url, name): if url: response = requests.get(url) img = Image.open(BytesIO(response.content)) img.save(f"kid_images/{name}.jpg") for i, row in df.head(20).iterrows(): # download 20 sample images download_image(row["image_url"], f"product_{i}")

{ "platform": "FirstCry", "name": "Pampers New Baby Diapers - Pack of 72", "price": "₹899", "mrp": "₹1099", "url": "https://www.firstcry.com/...", "image_url": "https://cdn.firstcry.com/...", "clean_title": "pampers new baby diapers 72", "age_group": "new baby", "pack_size": "72", "category": "Diapers" }

{ "platform": "Walmart", "name": "LEGO City Police Car Toy for 5+ Years", "price": "$9.97", "mrp": "", "url": "https://www.walmart.com/...", "image_url": "https://i5.walmartimages.com/...jpg", "clean_title": "lego city police car toy 5 years", "age_group": "5 years", "pack_size": null, "category": "Toys" }

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