爬取大众点评评论信息代码

由于大众点评网站的反爬机制比较严格，因此需要使用一些技巧来避免被封禁。以下是一个使用Python爬取大众点评评论信息的例子：

import requests
import time
from bs4 import BeautifulSoup

def get_comments(url):
    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')

    # 获取评论信息
    comments = []
    comment_list = soup.find_all('div', class_='comment-list')[0].find_all('div', class_='comment')
    for comment in comment_list:
        name = comment.find_all('div', class_='user-info')[0].find_all('a')[0].text.strip()
        star = len(comment.find_all('span', class_='sml-rank-stars')[0].find_all('span', class_='sml-str'))
        content = comment.find_all('div', class_='comment-txt')[0].text.strip()
        comments.append({'name': name, 'star': star, 'content': content})
    return comments

if __name__ == '__main__':
    # 模拟浏览器访问网页，获取cookies
    url = 'https://www.dianping.com/'
    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)
    cookies = response.cookies.get_dict()

    # 爬取评论信息
    url = 'https://www.dianping.com/shop/5343507/review_all'
    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',
        'Cookie': 'xxxxxxx'  # 将获取的cookies填入
    }
    comments = []
    for i in range(1, 11):
        print('正在爬取第%d页评论...' % i)
        url = 'https://www.dianping.com/shop/5343507/review_all/p%d' % i
        response = requests.get(url, headers=headers)
        soup = BeautifulSoup(response.text, 'html.parser')
        if soup.find_all('div', class_='content') != []:
            comments += get_comments(url)
        else:
            break
        time.sleep(2)

    # 保存评论信息到文件
    with open('comments.txt', 'w', encoding='utf-8') as f:
        for comment in comments:
            f.write('姓名：%s，评分：%d，评论：%s\n' % (comment['name'], comment['star'], comment['content']))

需要注意的是，以上代码中需要手动获取cookies，并填入`headers`中，否则会被网站封禁。此外，为了避免被封禁，需要设置合理的访问间隔，这里设置为每爬取一页评论后暂停2秒。