import requests from bs4 import BeautifulSoup from pprint import pprint import pymysql 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() author = comment.select_one(".comment-info a").get_text().strip() likes = comment.select_one(".votes").get_text().strip() time = comment.select_one(".comment-time").get_text().strip() location = comment.select_one(".comment-location").contents[-1].strip() comments.append({ "content": content, "author": author, "likes": likes, "time": time, "location": location }) pprint(comments) db = pymysql.connect(host="localhost", user="root", password="password", database="test") cursor = db.cursor() for comment in comments: sql = "INSERT INTO comments (content, author, likes, time, location) VALUES (%s, %s, %s, %s, %s)" values = (comment["content"], comment["author"], comment["likes"], comment["time"], comment["location"]) cursor.execute(sql, values) db.commit()，我要爬取前五页的内容

好的，你可以使用一个循环来爬取前五页的内容：

import requests
from bs4 import BeautifulSoup
from pprint import pprint
import pymysql

db = pymysql.connect(host="localhost", user="root", password="password", database="test")
cursor = db.cursor()

for page in range(5):
    url = f"https://movie.douban.com/subject/30391186/comments?start={page*20}&limit=20&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()
        author = comment.select_one(".comment-info a").get_text().strip()
        likes = comment.select_one(".votes").get_text().strip()
        time = comment.select_one(".comment-time").get_text().strip()
        location = comment.select_one(".comment-location").contents[-1].strip()
        comments.append({
            "content": content,
            "author": author,
            "likes": likes,
            "time": time,
            "location": location
        })
        pprint(comments)
        sql = "INSERT INTO comments (content, author, likes, time, location) VALUES (%s, %s, %s, %s, %s)"
        values = (comment["content"], comment["author"], comment["likes"], comment["time"], comment["location"])
        cursor.execute(sql, values)
    db.commit()

db.close()

这段代码会循环5次，每次爬取20条评论，然后将这些评论存储到数据库中。