AttributeError：抓取 Ebay 产品标题时，“NoneType”对象没有属性“text”

Question

按照本教程使用 Python 创建 Ebay 价格跟踪器，在尝试从 Ebay 的搜索结果页面获取产品标题时，我遇到了 AttributeError: 'NoneType' 对象没有属性 'text'。

这个班级是正确的，正如您在这里看到的：

'title': item.find('h3', {'class': 's-item__title s-item__title--has-tags'}).text, 知道为什么我会收到此错误以及如何绕过它吗？

完整代码如下：

import requests
from bs4 import BeautifulSoup
import pandas as pd

searchterm = 'screen'

def get_data(searchterm):
    url = f'https://www.ebay.com/sch/i.html?_from=R40&_trksid=p2380057.m570.l1313&_nkw={searchterm}&_sacat=0&LH_PrefLoc=1&LH_Auction=1&rt=nc&LH_Sold=1&LH_Complete=1'
    r = requests.get(url)
    soup = BeautifulSoup(r.text, 'html.parser')
    return soup

def parse(soup):
    productslist = []
    results = soup.find_all('div',{'class': 's-item__info clearfix'})
    for item in results:
        product = {
            'title': item.find('h3', {'class': 's-item__title s-item__title--has-tags'}).text,
            'soldprice': float(item.find('span', {'class': 's-item__price'}).text.replace('$','').replace(',','').strip()),
            'solddate': item.find('span', {'class': 's-item__title--tagblock__COMPLETED'}).find('span',{'class': 'POSITIVE'}.text),
            'bids': item.find('span', {'class': 's-item__bids'}).text,
            'link': item.find('a', {'class': 's-item__link'})['href'],
        }
        productslist.append(product)
    return productslist

def output (productslist, searchterm):
    productsdf = pd.DataFrame(productslist)
    productsdf.to_csv(searchterm + 'ebaytrackeroutput.csv', index=False)
    print('Saved to CSV')
    return

soup = get_data(searchterm)
productslist = parse(soup)
output(productslist, searchterm)

                           

谢谢您的帮助！

Answer 1

有些商品没有标题或售价。他们不会返回任何东西。你会得到这个错误。所以你需要跳过它们。

另一件事是

item.find('span', {'class': 's-item__title--tagblock__COMPLETED'})

这条线总是不返回任何内容。所以你需要检查一下原因。

学习：

如何调试小程序

import requests
from bs4 import BeautifulSoup
import pandas as pd

searchterm = 'screen'

def get_data(searchterm):
    url = f'https://www.ebay.com/sch/i.html?_from=R40&_trksid=p2380057.m570.l1313&_nkw={searchterm}&_sacat=0&LH_PrefLoc=1&LH_Auction=1&rt=nc&LH_Sold=1&LH_Complete=1'
    r = requests.get(url)
    soup = BeautifulSoup(r.text, 'html.parser')
    return soup

def parse(soup):
    productslist = []
    results = soup.find_all('div',{'class': 's-item__info clearfix'})
    for item in results:
        title = item.find('h3', {'class': 's-item__title s-item__title--has-tags'})
        soldprice = item.find('span', {'class': 's-item__price'})
        if title == None or soldprice == None: # if these are none just skip them.
            continue
        # solddate is always returning none you need to check why
        product = {
            'title': title.text,
            'soldprice': float(soldprice.text.replace('$','').replace(',','').strip()),
            # 'solddate': item.find('span', {'class': 's-item__title--tagblock__COMPLETED'}).find('span',{'class': 'POSITIVE'}.text),
            'bids': item.find('span', {'class': 's-item__bids'}).text,
            'link': item.find('a', {'class': 's-item__link'})['href'],
        }
        productslist.append(product)
    return productslist

def output (productslist, searchterm):
    productsdf = pd.DataFrame(productslist)
    productsdf.to_csv(searchterm + 'ebaytrackeroutput.csv', index=False)
    print('Saved to CSV')
    return

soup = get_data(searchterm)
productslist = parse(soup)
output(productslist, searchterm)