Question

我是网络抓取领域的新手。因此希望这个问题是明确的。

我在互联网上找到了一个教程，该教程基于给定的ASIN（唯一的Amazon编号）来刮取Amazon数据。参见：https://www.scrapehero.com/tutorial-how-to-scrape-amazon-product-details-using-python/

运行此代码时（我对代码进行了一些调整）我每次都遇到不同的结果（即使在5秒钟后运行）也遇到了问题。在我的示例中，一次找到标题，但5秒钟后结果为NULL。

我认为原因是因为我通过Google Chrome搜索了XPATH，并且在代码的开头，有

headers = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36'}

我的问题：如何稳定地抓取内容？（例如：通过使用ASIN号获取网页的真实结果）

下面的代码进行再现。您可以通过命令行运行脚本：

python script_name.py

非常感谢您的帮助！

脚本：

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(5)
        try:
            doc = html.fromstring(page.content)

            # Title 
            XPATH_NAME = '//*[@id="productTitle"]/text()'
            XPATH_NAME1 = doc.xpath(XPATH_NAME)
            TITLE =           ' '.join(''.join(XPATH_NAME1).split()) if XPATH_NAME1 else None

            #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 = {
                    'TITLE':TITLE
                    #'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 = [
            'B00AEINQ9K',
            'B00JWP8F3I']
    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_scraped_data.json','w')
    json.dump(extracted_data,f,indent=4)

if __name__ == "__main__":
    ReadAsin()

刮亚马逊时结果不稳定

0 个答案: