import requests from bs4 import BeautifulSoup url = "https://movie.douban.com/subject/30391186/comments?sort=new_score&status=P" response = requests.get(url) soup = BeautifulSoup(response.text, "html.parser") comments = [] for comment in soup.select(".comment-item"): content = comment.select_one(".comment-content").get_text().strip() # 评论内容 author = comment.select_one(".comment-info a").get_text().strip() # 发布人 likes = comment.select_one(".votes").get_text().strip() # 点赞数 time = comment.select_one(".comment-time").get_text().strip() # 时间 location = comment.select_one(".comment-info").contents[-1].strip() # 地点 comments.append({ "content": content, "author": author, "likes": likes, "time": time, "location": location }) print(comments)，设置请求头

好的，设置请求头的方法如下，可以在请求中添加"User-Agent"等信息：

import requests
from bs4 import BeautifulSoup

url = "https://movie.douban.com/subject/30391186/comments?sort=new_score&status=P"
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"
}
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, "html.parser")

comments = []
for comment in soup.select(".comment-item"):
    content = comment.select_one(".comment-content").get_text().strip() # 评论内容
    author = comment.select_one(".comment-info a").get_text().strip() # 发布人
    likes = comment.select_one(".votes").get_text().strip() # 点赞数
    time = comment.select_one(".comment-time").get_text().strip() # 时间
    location = comment.select_one(".comment-info").contents[-1].strip() # 地点

    comments.append({
        "content": content,
        "author": author,
        "likes": likes,
        "time": time,
        "location": location
    })

print(comments)

在这个例子中，我们添加了一个名为"User-Agent"的请求头，值为一个模拟Chrome浏览器的User-Agent字符串，这样可以模拟浏览器访问网站，绕过反爬虫机制。