Saya cuba mengekstrak beberapa nilai daripada tapak web (https://carone.com.uy/autos-usados-y-0km?p=21). Ada yang berfungsi dengan baik, tetapi ada yang tidak. Contohnya, saya dapat mengekstrak nama, model, harga dan jenis bahan api, tetapi tidak dapat mengekstrak medan "Tahun" atau "Kilometer" dengan betul, kod itu sentiasa mengembalikan "N/A" sebagai nilai.
Ini adalah kod yang saya gunakan:
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))
Hasilnya kelihatan seperti ini: masukkan penerangan imej di sini
Saya tidak faham mengapa nilai yang disebutkan sentiasa mendapat "N/A" manakala yang lain berfungsi dengan baik, kaedahnya adalah sama.
![[Web front-end] Permulaan pantas Node.js](https://img.php.cn/upload/course/000/000/067/662b5d34ba7c0227.png)
Masalahnya ialah, laman web menggunakan sesuatu selain daripada
Kilómetros，而是Kilómetrosdalam teks elemen (perkara yang sama untuk umur):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)Cetak hasil: