Python + Chrome抓取AJAX动态数据的两种方法

import requests
from bs4 import BeautifulSoup

response = requests.get("https://example.com")
soup = BeautifulSoup(response.text, "html.parser")
# 只能获取初始 HTML，无法得到 AJAX 数据！

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
from selenium.webdriver.chrome.options import Options
from webdriver_manager.chrome import ChromeDriverManager
import time

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

# 配置 Chrome 代理
chrome_options = Options()
chrome_options.add_argument(f"--proxy-server=http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}")

# 启动 Chrome
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=chrome_options)
driver.get("https://news.sina.com.cn/")

# 等待 AJAX 内容加载（假设新闻列表通过 AJAX 渲染）
try:
    WebDriverWait(driver, 10).until(
        EC.presence_of_element_located((By.CSS_SELECTOR, ".news-item"))
    )
except:
    print("超时，未找到新闻列表")

# 提取新闻标题和链接
news_items = driver.find_elements(By.CSS_SELECTOR, ".news-item")
for item in news_items:
    title = item.find_element(By.CSS_SELECTOR, "a").text
    link = item.find_element(By.CSS_SELECTOR, "a").get_attribute("href")
    print(f"标题: {title}\n链接: {link}\n")

# 关闭浏览器
driver.quit()

import requests
import json

# 豆瓣电影 AJAX API
url = "https://movie.douban.com/j/search_subjects?type=movie&tag=热门&sort=recommend&page_limit=20&page_start=0"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}

response = requests.get(url, headers=headers)
data = response.json()  # 直接解析 JSON

# 提取电影信息
for movie in data["subjects"]:
    print(f"电影名: {movie['title']}")
    print(f"评分: {movie['rate']}")
    print(f"链接: {movie['url']}\n")