使用BeautifulSoup进行网络爬虫时，find_previous_sibling功能无法正常运行的问题

Question

我正在尝试从网站（https://carone.com.uy/autos-usados-y-0km?p=21）中提取几个值。有些工作正常，但有些不工作。例如，我能够提取名称、型号、价格和燃料类型，但无法正确提取“年份”或“公里数”字段，代码始终返回“N/A”作为值。

这是我正在使用的代码：

import pandas as pd
from datetime import date
import os
import socket
import requests
from bs4 import BeautifulSoup

def scrape_product_data(url):
    try:
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
        }

        product_data = []

        # Make the request to get the HTML content
        response = requests.get(url, headers=headers)
        response.raise_for_status()  # Check if the request was successful

        soup = BeautifulSoup(response.text, 'html.parser')
        product_elements = soup.find_all('div', class_='product-item-info')
        for product_element in product_elements:
            # Extract product name, price, model, and attributes as before (same code as previous version)
            product_name_element = product_element.select_one('p.carone-car-info-data-brand.cursor-pointer')
            product_name = product_name_element.text.strip() if product_name_element else "N/A"

            product_price_element = product_element.find('span', class_='price')
            product_price = product_price_element.text.strip() if product_price_element else "N/A"

            product_model_element = product_element.select_one('p.carone-car-info-data-model')
            product_model = product_model_element.get('title').strip() if product_model_element else "N/A"

            # Extract product attributes
            attributes_div = product_element.find('div', class_='carone-car-attributes')
            
            year_element = attributes_div.find('p', class_='carone-car-attribute-title', text='Año')
            year_value = year_element.find_previous_sibling('p', class_='carone-car-attribute-value').text if year_element else "N/A"

            kilometers_element = attributes_div.find('p', class_='carone-car-attribute-title', text='Kilómetros')
            kilometers_value = kilometers_element.find_previous_sibling('p', class_='carone-car-attribute-value').text if kilometers_element else "N/A"

            fuel_element = attributes_div.find('p', class_='carone-car-attribute-title', text='Combustible')
            fuel_value = fuel_element.find_previous_sibling('p', class_='carone-car-attribute-value').text if fuel_element else "N/A"

            # Append product data as a tuple (name, price, model, year, kilometers, fuel) to the list
            product_data.append((product_name, product_price, product_model, year_value, kilometers_value, fuel_value))

结果看起来像这样：enter image description here

我不明白为什么提到的值总是得到“N/A”，而其他的工作正常，方法是相同的。

Answer 1

问题是，该网站在元素的文本中使用的不是Kilómetros，而是Kil&oacutemetros（年龄也是同样的情况）：

def scrape_product_data(url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
    }

    product_data = []

    response = requests.get(url, headers=headers)
    response.raise_for_status()

    soup = BeautifulSoup(response.text, "html.parser")
    product_elements = soup.find_all("div", class_="product-item-info")
    for product_element in product_elements:
        product_name_element = product_element.select_one(
            "p.carone-car-info-data-brand.cursor-pointer"
        )
        product_name = (
            product_name_element.text.strip() if product_name_element else "N/A"
        )

        product_price_element = product_element.find("span", class_="price")
        product_price = (
            product_price_element.text.strip() if product_price_element else "N/A"
        )

        product_model_element = product_element.select_one(
            "p.carone-car-info-data-model"
        )
        product_model = (
            product_model_element.get("title").strip()
            if product_model_element
            else "N/A"
        )

        attributes_div = product_element.find("div", class_="carone-car-attributes")

        year_element = attributes_div.find(
            "p", class_="carone-car-attribute-title", string="Año"
        )
        year_value = (
            year_element.find_previous_sibling(
                "p", class_="carone-car-attribute-value"
            ).text
            if year_element
            else "N/A"
        )

        kilometers_element = attributes_div.find(
            "p", class_="carone-car-attribute-title", string="Kilómetros"
        )
        kilometers_value = (
            kilometers_element.find_previous_sibling(
                "p", class_="carone-car-attribute-value"
            ).text
            if kilometers_element
            else "N/A"
        )

        fuel_element = attributes_div.find(
            "p", class_="carone-car-attribute-title", string="Combustible"
        )
        fuel_value = (
            fuel_element.find_previous_sibling(
                "p", class_="carone-car-attribute-value"
            ).text
            if fuel_element
            else "N/A"
        )

        product_data.append(
            (
                product_name,
                product_price,
                product_model,
                year_value,
                kilometers_value,
                fuel_value,
            )
        )

    return pd.DataFrame(
        product_data, columns=["Name", "Price", "Model", "Year", "KM", "Fuel"]
    )


df = scrape_product_data("https://carone.com.uy/autos-usados-y-0km?p=2")
print(df)

打印结果：

                 Name      Price                                 Model  Year      KM   Fuel
0        Renault Kwid  US.000               KWID 1.0 INTENSE TACTIL  2018  82.390  NAFTA
1      Chevrolet Onix  US.800                   NEW ONIX 1.0T RS MT  2021  46.000  NAFTA
2        Suzuki Swift  US.800                 NUEVO SWIFT 1.2 GL AT  2020  63.641  NAFTA
3           Fiat Toro  US.800                TORO 1.8 FREEDOM DC MT  2021  15.330  NAFTA
4       Renault Oroch  US.300  NEW OROCH INTENS OUTSIDER 1.3T DC AT  2023  21.360  NAFTA
5     Renault Stepway  US.100                 STEPWAY PRIVILEGE 1.6  2017  60.010  NAFTA
6        Renault Kwid  US.100                         KWID 1.0 LIFE  2022      14  NAFTA
7      Chevrolet Onix  US.800              NEW ONIX 1.0T PREMIER AT  2021  14.780  NAFTA
8   Nissan SENTRA B18  US.000           SENTRA B18 2.0 EXCLUSIVE AT  2022  30.430  NAFTA
9        Renault Kwid  US.500                   KWID 1.0 INTENSE MT  2020  37.660  NAFTA
10  Chevrolet Tracker  US.300                TRACKER 1.8 LTZ 4X4 AT  2014  91.689  NAFTA
11     Chevrolet Onix  US.600            NEW ONIX PLUS 1.2 LS 4P MT  2022  24.658  NAFTA