求助修正每日自动提取指定URL中心图片的Python代码

原代码无法提取图片的核心问题是CSS选择器错误，#click-overlay并非图片标签，而是页面上的交互覆盖层，没有src属性。此外，部分网站会拦截无浏览器标识的请求，需要添加请求头模拟浏览器访问。

以下是修正后的完整代码：

from datetime import datetime, timedelta
import requests
from bs4 import BeautifulSoup
import os
import re

def extract_image_url(page_url, img_selector):
    # 添加请求头模拟浏览器，避免被反爬拦截
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    }
    response = requests.get(page_url, headers=headers)
    response.raise_for_status()  # 检查下载是否成功
    
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # 使用正确的CSS选择器查找图片标签
    img_tag = soup.select_one(img_selector)
    if img_tag and 'src' in img_tag.attrs:
        return img_tag['src']
    else:
        # 备选方案：处理图片作为div背景图的情况
        chart_div = soup.select_one('#chart-image')
        if chart_div and 'style' in chart_div.attrs:
            style_content = chart_div['style']
            img_match = re.search(r'url\((.*?)\)', style_content)
            if img_match:
                return img_match.group(1).strip('\'"')
        raise ValueError("未找到图片或CSS选择器错误")

def download_image(img_url, save_path):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
    }
    # 完善相对路径转绝对路径逻辑
    if not img_url.startswith('http'):
        img_url = f'https://weather.us{img_url}' if img_url.startswith('/') else f'https://weather.us/{img_url}'
            
    response = requests.get(img_url, headers=headers)
    response.raise_for_status()
    
    with open(save_path, 'wb') as f:
        f.write(response.content)
    
    print(f"图片已保存至：{save_path}")

# 日期处理
today = datetime.now().strftime('%Y%m%d')
dia_ahead = (datetime.now() + timedelta(days=16)).strftime('%Y%m%d')

# URL构造（修正原URL中的时间格式错误）
url_base = "https://weather.us/model-charts/standard/"
url_today_00z_complete = f"{url_base}{today}00/brazil/accumulated-precipitation/{dia_ahead}-0000z.html"
url_today_06z_complete = f"{url_base}{today}06/brazil/accumulated-precipitation/{dia_ahead}-0600z.html"

print("\n今日00时完整URL:")
print(url_today_00z_complete)
print("\n今日06时完整URL:")
print(url_today_06z_complete)

urls = [url_today_00z_complete, url_today_06z_complete]
# 替换为目标页面中中心图片的正确选择器
img_selector = "#chart-image img" 

# 提取并下载每个URL中的图片
for url in urls:
    try:
        img_url = extract_image_url(url, img_selector)
        save_path = os.path.join(os.getcwd(), os.path.basename(img_url))
        download_image(img_url, save_path)
    except Exception as e:
        print(f"处理{url}时出错：{e}")

关键修正点： #

• 修正CSS选择器：将无效的#click-overlay替换为#chart-image img，匹配目标页面中的中心图片标签
• 添加请求头：模拟浏览器请求，绕过网站基础反爬拦截
• 完善路径处理：优化相对路径转绝对路径的逻辑，适配不同格式的图片URL
• 兼容背景图场景：增加正则提取背景图URL的备选方案，提升代码兼容性
• 修正URL格式：修复原代码中06z对应的时间参数错误（将0060z改为0600z）

内容的提问来源于stack exchange，提问作者LeoLaboi