python - 检索特定产品的亚马逊评论

Question

我目前正在开展一个研究项目，该项目需要分析特定产品的评论并获得有关该产品的整体想法。

我听说亚马逊是获取产品评论/评论的好地方。有什么方法可以通过 API 从亚马逊检索这些用户评论/评论吗？我尝试了几个Python代码，但它不起作用。如果没有API来检索数据，我是否需要编写一个蜘蛛？

是否有任何方法/位置可以检索给定产品的用户评论？

Answer 1

www.Scrapehero.com 有一个关于如何抓取亚马逊产品详细信息的精彩教程:How To Scrape Amazon Product Details and Pricing using Python

他们使用的完整纯文本代码是......产品通过其 ASIN 进行标识，因此请将数组值更改为您有兴趣观看的产品。

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()