Python Ebay价格追踪器爬虫报错：'NoneType' object has no attribute 'text'

我跟着教程用Python开发Ebay价格追踪器，爬取Ebay搜索结果页商品标题时，遇到AttributeError: 'NoneType' object has no attribute 'text'错误。出错的代码行是：

'title': item.find('h3', {'class': 's-item__title s-item__title--has-tags'}).text,

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)

1. 元素匹配失败：item.find()返回None，说明当前遍历的item里没有找到指定class的h3标签。部分商品的标题class可能不带s-item__title--has-tags后缀，导致匹配失败。
2. 页面结构变更：Ebay的页面结构可能和教程发布时不同，原有的class选择器不再适配所有元素。
3. 多处存在风险：除了标题，solddate、bids等字段都直接调用.text或取['href']，只要find()返回None就会触发类似错误；另外solddate的代码还有语法错误：find('span',{'class': 'POSITIVE'}.text)应该是find('span',{'class': 'POSITIVE'}).text。

核心逻辑是先判断元素是否存在，再访问其属性，避免直接对None调用方法或属性：

1. 放宽标题的class匹配，只用基础classs-item__title覆盖所有商品标题。
2. 对每个字段添加空值判断，不存在时赋值为None或跳过该商品。
3. 修复solddate的语法错误。
4. 跳过搜索结果顶部可能被误匹配的占位元素（比如"Shop by category"模块）。

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'})
    # 跳过第一个可能的占位元素
    for item in results[1:]:
        # 处理标题
        title_elem = item.find('h3', {'class': 's-item__title'})
        title = title_elem.text.strip() if title_elem else None
        
        # 处理售价
        price_elem = item.find('span', {'class': 's-item__price'})
        soldprice = float(price_elem.text.replace('$','').replace(',','').strip()) if price_elem else None
        
        # 处理售出日期
        tag_block = item.find('span', {'class': 's-item__title--tagblock__COMPLETED'})
        date_elem = tag_block.find('span', {'class': 'POSITIVE'}) if tag_block else None
        solddate = date_elem.text.strip() if date_elem else None
        
        # 处理竞价数
        bids_elem = item.find('span', {'class': 's-item__bids'})
        bids = bids_elem.text.strip() if bids_elem else None
        
        # 处理商品链接
        link_elem = item.find('a', {'class': 's-item__link'})
        link = link_elem['href'] if link_elem else None
        
        # 只保留有核心信息的商品
        if title and soldprice and link:
            product = {
                'title': title,
                'soldprice': soldprice,
                'solddate': solddate,
                'bids': bids,
                'link': link,
            }
            productslist.append(product)
    return productslist

def output(productslist, searchterm):
    productsdf = pd.DataFrame(productslist)
    productsdf.to_csv(f'{searchterm}_ebaytrackeroutput.csv', index=False)
    print('Saved to CSV')
    return

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

内容的提问来源于stack exchange，提问作者EXB