Python requests-html 多语言网页内容抓取与翻译实践

# 安装最新预发布版本
pip install googletrans==4.0.0-rc1

# 如果最新版本出现问题，可以尝试卸载并安装稳定版本
# pip uninstall googletrans==4.0.0-rc1
# pip install googletrans==3.0.0

import pandas
from requests_html import HTMLSession
import time
import requests
from requests import get
import re
from googletrans import Translator # 导入 Translator 类

# 目标 URL
url = 'https://pcpalace.com.sa/products/ASUS-Vivobook-GO-E1504GA'

# 实例化 HTMLSession
session = HTMLSession()

# 发起请求，这里可以继续尝试设置 Accept-Language，但主要目的是获取原始HTML
headers = {"Accept-Language": "en"}
r = session.get(url, headers=headers) # 使用 session.get() 获取 HTMLResponse 对象
r.raise_for_status() # 检查请求是否成功

# 确保页面已渲染（如果页面有JS动态加载内容）
# r.html.render() # 如果页面有JavaScript渲染内容，可能需要这行

# 实例化翻译器
translator = Translator()

# 使用 .html.find() 方法查找 title 元素
# first=True 表示只返回第一个匹配的元素
title_element = r.html.find('title', first=True)

# 提取 title 元素的文本内容
# 如果 title_element 不存在，则返回 'Title not found'
original_title_text = title_element.text if title_element else 'Title not found'

# 翻译原始标题文本到英文
# dest='en' 指定目标语言为英文
try:
    translated_title = translator.translate(original_title_text, dest='en').text
except Exception as e:
    translated_title = f"Translation failed: {e}"
    print(f"Error during translation: {e}")

print("Original Title: " + original_title_text)
print("Translated Title: " + translated_title)

# 示例：翻译其他元素，如一个产品名称（假设其CSS选择器为 '.product-name'）
# product_name_element = r.html.find('.product-name', first=True)
# if product_name_element:
#     original_product_name = product_name_element.text
#     translated_product_name = translator.translate(original_product_name, dest='en').text
#     print("Original Product Name: " + original_product_name)
#     print("Translated Product Name: " + translated_product_name)
# else:
#     print("Product name element not found.")

import pandas
from requests_html import HTMLSession
import time
import requests
from requests import get
import re
from googletrans import Translator

# 目标 URL
url = 'https://pcpalace.com.sa/products/ASUS-Vivobook-GO-E1504GA'

# 实例化 HTMLSession
session = HTMLSession()

# 设置请求头，Accept-Language 仅作为参考，实际翻译依赖 googletrans
headers = {"Accept-Language": "en"}

try:
    # 发起请求，获取 HTMLResponse 对象
    r = session.get(url, headers=headers)
    r.raise_for_status() # 检查 HTTP 状态码，如果不是 200 则抛出异常

    # 实例化翻译器
    translator = Translator()

    # --- 提取并翻译页面标题 ---
    title_element = r.html.find('title', first=True)
    original_title_text = title_element.text if title_element else 'Title not found'

    try:
        translated_title = translator.translate(original_title_text, dest='en').text
    except Exception as e:
        translated_title = f"Translation failed: {e}"
        print(f"Error translating title: {e}")

    print("Original Title: " + original_title_text)
    print("Translated Title: " + translated_title)

    # --- 提取并翻译其他内容示例 ---
    # 假设页面上有一个产品名称的元素，其 CSS 类为 'product-name'
    # 请根据实际网页结构调整选择器
    product_name_element = r.html.find('h1.product-title', first=True) # 示例选择器
    if product_name_element:
        original_product_name = product_name_element.text
        try:
            translated_product_name = translator.translate(original_product_name, dest='en').text
        except Exception as e:
            translated_product_name = f"Translation failed: {e}"
            print(f"Error translating product name: {e}")
        print("Original Product Name: " + original_product_name)
        print("Translated Product Name: " + translated_product_name)
    else:
        print("Product name element not found (adjust selector if needed).")

except requests.exceptions.RequestException as e:
    print(f"Request failed: {e}")
except Exception as e:
    print(f"An unexpected error occurred: {e}")