Question

我正在尝试刮擦： https://www.loft.com/loft-plus-floral-maxi-shirtdress/514793

我已成功抓取描述。但是，我无法抓取产品图片和建议。我在下面提到的代码先前已用于其他一些与时尚相关的网站，但似乎不适用于此。

#main method
d = webdriver.Chrome('/Users/fatima.arshad/Downloads/chromedriver')
d.get(url)
start = BeautifulSoup(d.page_source, 'html.parser')
Image_URL = self.saveImage("./products/", product_name, start)

recommendations = self.getRecommendations(start, d)

def getRecommendations(self,start,d):

    #code to scroll to the bottom of page
    recommended = []
    s = start.find_all('div', class_='swiper-container swiper-container-horizontal')
    while not s :
        s = start.find_all('div', class_='swiper-container swiper-container-horizontal')
    for data in start.find_all('div', class_='swiper-container swiper-container-horizontal'):
        for a in data.find_all('a'):
            print(a.get('href'))  # for getting link
            print(a.text)  # for getting text between the link
            recommended.append("https://loft.com"+str(a.get('href')))

def saveImage(self, foldername, product_name,start):
    ##some other code

    s = start.find('div', class_='swiper-wrapper')
    for i in start.find_all('div', class_='swiper-wrapper'):

        for img in i.select('img'):

            print(img['src'])

            urllib.request.urlretrieve("http://"+img['src'], foldername + "/" + product_name + str(c) + ".jpg")
            c = c + 1

问题在于这两种方法均未返回任何内容。我将循环放入getRecommendations（）中，以使它最终得到某些东西，但仍然没有任何效果。

Answer 1

链接是动态构建的。您可以在网络标签中查看GET请求，该请求以json格式检索用于构造新图像网址的信息。

您可以模仿这些步骤：

from bs4 import BeautifulSoup as bs
import requests, re, json

p = re.compile(r'\((.*),')

with requests.Session() as s:
    r = s.get('https://www.loft.com/loft-plus-floral-maxi-shirtdress/514793')
    soup = bs(r.content, 'lxml')
    src = soup.select_one('.product-image img')['src'].split('?')[0]   
    r = s.get(f'{src}_IS?req=set,json&callback=s7R_1&handler=s7R_1&_=1')

data = json.loads(p.findall(r.text)[0])
for item in data['set']['item']:
    i = item['i']['n']
    image_url = f'https://anninc.scene7.com/is/image/{i}?$pdp$'
    print(image_url)

尽管存在某些<div>，但无法找到它们

1 个答案: