A Python script for scraping reviews from Amazon given one or more product ASIN codes.

reviews.py

from playwright.sync_api import sync_playwright
from selectolax.parser import HTMLParser
from dataclasses import dataclass
import time
import csv
from loguru import logger

@dataclass
class Item:
	asin: str 
	product: str 
	title: str 
	rating: str 
	body: str 


class Reviews(object):

	def __init__(self):
		self.parser = HTMLParser
		self.pw = sync_playwright().start()
		self.browser = self.pw.chromium.launch()
		logger.debug("Reviews object initialized")

	def __enter__(self):
		logger.debug("Reviews object entered")
		return self

	def __exit__(self, xc_type, exc_value, traceback):
		self.browser.close()
		self.pw.stop()
		logger.debug("Reviews object exited")

	def __get_html(self, page, asin, nr):
		url = f"https://www.amazon.com/product-reviews/{asin}/ref=cm_cr_arp_d_viewopt_srt?reviewerType=avp_only_reviews&sortBy=recent&pageNumber="
		page.goto(url + str(nr))
		html = self.parser(page.content())
		rv = html.css_matches("div[data-hook=review]")
		if rv:
			logger.debug(f"Getting the HTML review page nr. {nr} for ASIN: {asin}")
			return html
		else:
			logger.debug(f"No more HTML review pages for ASIN: {asin}")
			return False

	def __parse_html(self, html, asin):
		logger.debug(f"Parsing an HTML review page for ASIN: {asin}")
		product = html.css_first("a[data-hook=product-link]").text(strip=True)
		reviews = html.css("div[data-hook=review]")
		items = []
		for r in reviews:
			title = r.css_first("a[data-hook=review-title]").css_first("span:nth-child(3)").text(strip=True)
			rating = r.css_first("i[data-hook=review-star-rating] span").text(strip=True)[:3]
			body = r.css_first("span[data-hook=review-body] span").text(strip=True).replace("\n","")
			item = Item(asin=asin, product=product, title=title, rating=rating, body=body)
			items.append(item)
		return items

	def read_csv(self, file_path):
		logger.debug(f"Reading ASINs from csv file: {file_path}")
		with open(file_path, "r") as f:
			reader = csv.reader(f)
			return [item[0] for item in reader]

	def to_csv(self, reviews, file_path):
		logger.debug(f"Writing reviews to csv file: {file_path}")
		with open(file_path, "w", newline='', encoding="utf-8") as f:
			writer = csv.writer(f)
			for r in reviews:
				row = (r.asin, r.product, r.title, r.rating, r.body)
				writer.writerow(row)

	def run_single(self, asin):
		page = self.browser.new_page()
		logger.debug(f"Getting the all the available Amazon reviews for ASIN: {asin}")
		reviews_list = self.__run(page, asin)
		return reviews_list

	def run_multiple(self, asin_list):
		page = self.browser.new_page()
		all_products_reviews = []
		for asin in asin_list:
			logger.debug(f"Getting the all the available Amazon reviews for ASIN: {asin}")
			reviews_list = self.__run(page, asin)
			all_products_reviews = all_products_reviews + reviews_list
			time.sleep(5)
		return all_products_reviews

	def __run(self, page, asin):
		reviews_found = True
		reviews_list = []
		ix = 1
		while reviews_found:
			html = self.__get_html(page, asin, nr=ix)
			ix += 1
			if html:
				reviews = self.__parse_html(html, asin)
				reviews_list = reviews_list + reviews
			else:
				reviews_found = False
				break
		return reviews_list

def main():

	with Reviews() as rv:

		asin = "B01N5IB20Q"
		result = rv.run_single(asin)
		rv.to_csv(result, "result_single.csv")

		file_path = "products.csv"
		asins = rv.read_csv(file_path)
		result = rv.run_multiple(asins)
		rv.to_csv(result, "result_multiple.csv")

if __name__ == '__main__':
	main()