[Python 爬虫]爬取豆瓣官网电影名称、评分、简介等信息_爬取电影页面的电影名称和评分怎么写-CSDN博客

本文链接：https://blog.csdn.net/qq_34916678/article/details/106960393

本文介绍了一种使用Python爬取豆瓣电影数据的方法，包括获取电影名称、评分和简介等信息。通过发送请求、解析JSON响应和使用正则表达式提取所需数据，实现了自动化抓取功能。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

黑框程序效果截图：

在这里插入图片描述

应用到QQ机器人效果截图：
黑框程序代码：

from selenium import webdriver
from lxml import html
from PIL import Image
from selenium.webdriver.support.select import Select
from lxml import etree
import requests
import re
import urllib
import time
import cv2
import pytesseract
import socket
import numpy as np

Url_Get_MovieID = 'https://movie.douban.com/j/subject_suggest?q='
Url_DouBan = 'https://movie.douban.com/subject/'

def MidString(content,startStr,endStr):                     
    startIndex = content.index(startStr)                    
    if startIndex>=0:                                       
        startIndex += len(startStr)                         
        endIndex = content.index(endStr)                    
        return content[startIndex:endIndex]                 

def html():
    Movie_Name = input("电影名字：")
    #伪装成浏览器访问，直接访问的话会拒绝
    user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
    headers = {'User-Agent':user_agent}
    r_1 = requests.get(Url_Get_MovieID + Movie_Name,headers=headers)
    JSON = str(r_1.json)
    GetTxt = r_1.text
    #定义正则，目的是从html中提取想要的信息
    str_title = '"title":"' + Movie_Name + '"'  
    Get_Name = re.search(str_title,GetTxt)
    str_id = '"id":"'+ '[0-9]*'
    Get_Id = re.search(str_id,GetTxt)
    if Get_Name == None and Get_Id == None:
        print("?????????")
    else:
        ID = MidString(str(Get_Id),"id\":\"","'>")
        r_2 = requests.get(Url_DouBan + ID,headers=headers)
        s_1 = etree.HTML(r_2.text)
        #xpath的自动生成路径
        Movie_Called = s_1.xpath('/html/body/div[3]/div[1]/h1/span[1]/text()')
        print(Movie_Called[0])
        Movie_Score = s_1.xpath('//*[@id="interest_sectl"]/div[1]/div[2]/strong/text()')
        print(Movie_Score[0])
        Movie_Inter = s_1.xpath('//*[@id="link-report"]/span[1]/span/text()[1]')#钢铁侠    
        if len(Movie_Inter) == 0:
            print("11111")
                                        #//*[@id="link-report"]/span/text()#黑水
            Movie_Inter = s_1.xpath('//*[@id="link-report"]/span[1]/text()[1]')#流浪地球  
            if len(Movie_Inter) == 0:
                print("??????????????????")
            else:
                print(Movie_Inter[0].lstrip())
        else:
            print("22222")
            print(Movie_Inter[0].lstrip())



if __name__ == "__main__":
    #SATRT()
    html()