基于Selenium的Python爬虫抓取动态App图片

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
import os

# 设置ChromeDriver路径（根据实际情况修改）
driver_path = "chromedriver.exe"  # 或指定绝对路径
service = Service(driver_path)
options = webdriver.ChromeOptions()

# 可选项：无头模式（不显示浏览器界面）
# options.add_argument("--headless")

# 初始化浏览器
driver = webdriver.Chrome(service=service, options=options)

dfrom selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.proxy import Proxy, ProxyType
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time

# 设置代理信息
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"

# 配置代理
proxy = Proxy()
proxy.proxy_type = ProxyType.MANUAL
proxy.http_proxy = f"{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"
proxy.ssl_proxy = f"{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"

# 初始化 WebDriver，使用代理
options = webdriver.ChromeOptions()
options.proxy = proxy
driver = webdriver.Chrome(options=options)

def scroll_to_bottom(driver, max_scrolls=10, delay=2):
    """模拟滚动加载更多内容"""
    last_height = driver.execute_script("return document.body.scrollHeight")
    scroll_count = 0
    
    while scroll_count < max_scrolls:
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        time.sleep(delay)  # 等待新内容加载
        new_height = driver.execute_script("return document.body.scrollHeight")
        
        if new_height == last_height:
            break  # 已到底部
        last_height = new_height
        scroll_count += 1

# 示例：访问 Pinterest（需替换为目标 App 的 URL）
url = "https://www.pinterest.com/search/pins/?q=cats"

try:
    driver.get(url)

    # 等待页面加载
    WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.TAG_NAME, "img"))
    )

    # 模拟滚动加载更多图片
    scroll_to_bottom(driver, max_scrolls=5)

except Exception as e:
    print(f"加载网页时遇到问题：{e}")
    print("请检查网页链接的合法性，确保网络连接正常。如果问题仍然存在，请稍后重试。")

finally:
    driver.quit()

import requests
from PIL import Image
from io import BytesIO

def download_image(url, save_dir="images"):
    """下载图片并保存到本地"""
    if not os.path.exists(save_dir):
        os.makedirs(save_dir)
    
    try:
        response = requests.get(url, stream=True)
        if response.status_code == 200:
            img = Image.open(BytesIO(response.content))
            img_name = url.split("/")[-1].split("?")[0]  # 提取文件名
            img_path = os.path.join(save_dir, img_name)
            img.save(img_path)
            print(f"下载成功: {img_path}")
    except Exception as e:
        print(f"下载失败: {url}, 错误: {e}")

# 获取所有图片元素
images = driver.find_elements(By.TAG_NAME, "img")

# 提取src并下载
for img in images:
    img_url = img.get_attribute("src")
    if img_url and "http" in img_url:  # 过滤无效URL
        download_image(img_url)