Retrieve Amazon Reviews for a particular product

Question

I'm currently working on a research project which need to analyze reviews of a particular product and get an overall idea about the product.

I heard that amazon is a good place to get product reviews/comments. Is there any way to retrieve those user reviews/comments from Amazon via an API?? I tried several python codes but it doesn't work.. Do i need to write a spider if there is no API to retrieve data?

Are there any approaches/places to retrieve user reviews for a given product?

Answer 1

www.Scrapehero.com has a great tutorial on how to scrape Amazon product details: How To Scrape Amazon Product Details and Pricing using Python

The complete plain text code they use is ... Products are identified by their ASIN so change the array values to the products you are interested in watching.

from lxml import html  
import csv,os,json
import requests
from exceptions import ValueError
from time import sleep

def AmzonParser(url):
    headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64)    AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36'}
page = requests.get(url,headers=headers)
while True:
    sleep(3)
    try:
        doc = html.fromstring(page.content)
        XPATH_NAME = '//h1[@id="title"]//text()'
        XPATH_SALE_PRICE = '//span[contains(@id,"ourprice") or contains(@id,"saleprice")]/text()'
        XPATH_ORIGINAL_PRICE = '//td[contains(text(),"List Price") or contains(text(),"M.R.P") or contains(text(),"Price")]/following-sibling::td/text()'
        XPATH_CATEGORY = '//a[@class="a-link-normal a-color-tertiary"]//text()'
        XPATH_AVAILABILITY = '//div[@id="availability"]//text()'

        RAW_NAME = doc.xpath(XPATH_NAME)
        RAW_SALE_PRICE = doc.xpath(XPATH_SALE_PRICE)
        RAW_CATEGORY = doc.xpath(XPATH_CATEGORY)
        RAW_ORIGINAL_PRICE = doc.xpath(XPATH_ORIGINAL_PRICE)
        RAw_AVAILABILITY = doc.xpath(XPATH_AVAILABILITY)

        NAME = ' '.join(''.join(RAW_NAME).split()) if RAW_NAME else None
        SALE_PRICE = ' '.join(''.join(RAW_SALE_PRICE).split()).strip() if RAW_SALE_PRICE else None
        CATEGORY = ' > '.join([i.strip() for i in RAW_CATEGORY]) if RAW_CATEGORY else None
        ORIGINAL_PRICE = ''.join(RAW_ORIGINAL_PRICE).strip() if RAW_ORIGINAL_PRICE else None
        AVAILABILITY = ''.join(RAw_AVAILABILITY).strip() if RAw_AVAILABILITY else None

        if not ORIGINAL_PRICE:
            ORIGINAL_PRICE = SALE_PRICE

        if page.status_code!=200:
            raise ValueError('captha')
        data = {
                'NAME':NAME,
                'SALE_PRICE':SALE_PRICE,
                'CATEGORY':CATEGORY,
                'ORIGINAL_PRICE':ORIGINAL_PRICE,
                'AVAILABILITY':AVAILABILITY,
                'URL':url,
                }

        return data
    except Exception as e:
        print e

def ReadAsin():
# AsinList = csv.DictReader(open(os.path.join(os.path.dirname(__file__),"Asinfeed.csv")))
AsinList = ['B0046UR4F4',
'B00JGTVU5A',
'B00GJYCIVK',
'B00EPGK7CQ',
'B00EPGKA4G',
'B00YW5DLB4',
'B00KGD0628',
'B00O9A48N2',
'B00O9A4MEW',
'B00UZKG8QU',]
extracted_data = []
for i in AsinList:
    url = "http://www.amazon.com/dp/"+i
    print "Processing: "+url
    extracted_data.append(AmzonParser(url))
    sleep(5)
f=open('data.json','w')
json.dump(extracted_data,f,indent=4)


if __name__ == "__main__":
ReadAsin()