Scrapes "Car Cover" listings from OLX India, saving title, price, location, and link to a CSV file. Skips incomplete listings.

olx_scrape.py

import csv

import requests
from bs4 import BeautifulSoup

# URL for OLX search for "Car Cover"
url = "https://www.olx.in/items/q-car-cover"

# Send GET request with user-agent to avoid blocking
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
response = requests.get(url, headers=headers)

# Check if the request was successful
if response.status_code == 200:
    soup = BeautifulSoup(response.text, "html.parser")

    # Find the list of items using data-aut-id
    listings = soup.find("ul", {"data-aut-id": "itemsList1"})
    if listings:
        results = []
        for item in listings.find_all("li"):
            title = item.find("span", {"data-aut-id": "itemTitle"})
            price = item.find("span", {"data-aut-id": "itemPrice"})
            location = item.find("span", {"data-aut-id": "item-location"})
            link_tag = item.find("a")

            # Skip the item if any required field is missing
            if not (title and price and location and link_tag):
                continue

            title = title.text.strip()
            price = price.text.strip()
            location = location.text.strip()
            link = "https://www.olx.in" + link_tag.get("href", "")

            results.append([title, price, location, link])

        # Save results to CSV
        with open(
            "olx_car_cover_results.csv", "w", newline="", encoding="utf-8"
        ) as file:
            writer = csv.writer(file)
            writer.writerow(["Title", "Price", "Location", "Link"])
            writer.writerows(results)

        print("Scraping completed. Results saved to olx_car_cover_results.csv")
    else:
        print("No listings found.")
else:
    print(f"Failed to connect. Status code: {response.status_code}")