其他分享
首页 > 其他分享> > 爬取豆瓣top250电影

爬取豆瓣top250电影

作者:互联网

爬取思路:
1、使用selenium来获取页面源码,实现翻页功能。
2、获取页面源码后可以获取每个电影对应页面的url。
3、然后请求电影页面的url信息,将需要的保存起来即可。
code:

import requests
from selenium import webdriver 
from bs4 import BeautifulSoup
import os
import time 

class Spide_douban():
    def __init__(self):
        self.headers = {
            "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36"
        }                
        self.url = "https://movie.douban.com/top250?"
        self.driver = None
        self.film_url = []
        self.film_name = []
        self.film_seq = []
        
        
        
    def get_film_url(self,html):
        soup = BeautifulSoup(html,"html.parser")
        film_url_list = soup.find("ol",attrs = {"class":"grid_view"}).find_all("div",attrs = {"class":"pic"})
        for div in film_url_list:
            self.film_url.append(div.find("a").attrs["href"])
            self.film_name.append(div.find("img").attrs["alt"])
    def deal_actor_img(self,soup_img):
        img_url = soup_img.find("div").attrs["style"]
        img_name = soup_img.find("span").text
        img_name_role = soup_img.find("span",attrs = {"class":"role"}).text
        return img_url[22:-1],img_name,img_name_role
    
    def deal_actor_role(self,img_name,img_name_role,num):
        file = open("D:\\项目案例\\{}\\{}的简介.txt".format(self.film_name[num],self.film_name[num]),"a",encoding=("utf-8"))
        file.write("\n")
        file.write(img_name)
        file.write("  ")
        file.write(img_name_role)
        file.close()
    
        
    def deal_url(self,url,num):
        try:
            os.mkdir("D:\\项目案例\\{}".format(self.film_name[num]))
            print("正在处理电影  {}".format(self.film_name[num]))
        except Exception as e:
            print("正在处理电影  {}".format(self.film_name[num]))
        
        
        res = requests.get(url,headers = self.headers)
        
        time.sleep(2)
        
        soup = BeautifulSoup(res.text,"html.parser")
        file = open("D:\\项目案例\\{}\\{}的简介.txt".format(self.film_name[num],self.film_name[num]),"w",encoding=("utf-8"))
        
        #添加电影评分
        soup_comment = soup.find("div",attrs = {"id":"interest_sectl"})
        grad = soup_comment.find("strong",attrs = {"class":"ll rating_num"}).string
        vote = soup_comment.find("span",attrs = {"property":"v:votes"}).string
        file.write("电影豆瓣评分:{}".format(grad))
        file.write("   {}人评价\n".format(vote))
        
        F = soup.find("div",attrs = {"id":"info"})
        
        #添加片长
        time1 = F.find("span",attrs = {"property":"v:runtime"})
        file.write("电影时长:{}\n\n".format(time1.string))
        
        #添加电影类型
        
        label_list = F.find_all("span",attrs = {"property":"v:genre"})
        l= len(label_list)
        file.write("电影类型:")
        for i in range(l):
            file.write(label_list[i].string)
            if(i+1 != l):
                file.write("、")
        file.write("\n")
        
        
        #添加上映日期
        data_list = F.find_all("span",attrs = {"property":"v:initialReleaseDate"})
        l = len(data_list)
        file.write("电影上映日期:")
        for i in range(l):
            file.write(data_list[i].string)
            if(i+1 != l):
                file.write("、")
        file.write("\n")
        
        
        
        
        #添加电影简介
        file.write("电影简介:\n")
        soup_text = soup.find("div",attrs = {"id":"link-report"}).find("span",attrs = {"property":"v:summary"}).text.strip()
        soup_text_list = soup_text.split()
        text = ""
        for str_i in soup_text_list:
            number = 0
            for j in str_i:
                number +=1
                if(number %30==0):
                    text+='\n'
                text+=j
        file.write(text)
        file.write("\n")
        file.close()
        

        
        
        #保存电影海报
        file = open("D:\\项目案例\\{}\\{}.jpg".format(self.film_name[num],self.film_name[num]),"wb")
        
        img_url = soup.find("div",attrs = {"id":"mainpic"}).find("img").attrs["src"]
        res_img = requests.get(img_url,headers = self.headers)
        file.write(res_img.content)
        file.close()
        
        
            
        
        
        #保存主演的照片
        soup_actor_list = soup.find("div",attrs = {"id":"celebrities"}).find_all("li")
        for actor in soup_actor_list:
            img_url,img_name,img_name_role = self.deal_actor_img(actor)
            file = open("D:\\项目案例\\{}\\{}.jpg".format(self.film_name[num],img_name),"wb")
            res = requests.get(img_url,headers = self.headers)
            file.write(res.content)
            file.close()
            self.deal_actor_role(img_name,img_name_role,num)

    def move(self):
        for i in range(30):
            js = "var q=document.documentElement.scrollTop={}".format(i*100)  #javascript语句
            self.driver.execute_script(js)
            time.sleep(0.25)
    
    def run(self):        
        self.driver = webdriver.Chrome(executable_path="D:\chromedriver.exe")     
        self.driver.get(self.url)
        #滑动当前页面,使页面充分加载
        time.sleep(2)
        self.move()
        # html = self.driver.page_source
        # self.get_film_url(html)
        flag = True
        while(flag):
            html = self.driver.page_source
            self.get_film_url(html)
            soup = BeautifulSoup(html,"html.parser")
            next_soup = soup.find("span",attrs = {"class":"next"})
            if(next_soup.find("a")==None):
                break
            self.driver.find_element_by_css_selector('#content > div > div.article > div.paginator > span.next > a').click()
            self.move()
        #控制翻页,获得每个页面的HTML源码。
        # 判断是否有a标签,有的话就点,是None的话说明当前是最后一页了。
        #得到的每个电影的url,然后在处理每个电影。
        for num,url in enumerate(self.film_url):
            try:
                self.deal_url(url,num)
            except Exception as E:
                print("{} 电影信息获取出错,等待进行二次获取".format(self.film_name[num]))
                self.film_seq.append(num)
        for i in film_seq:
            try:
                print("尝试二次获取电影:{}的信息".format(self.film_name[i]))
                self.deal_url(self.film_url[i], self.film_name[i])
            except Exception as e:
                print("{} 电影二次获取信息仍然失败".format(self.film_name[i]))
    
Sd = Spide_douban()
Sd.run()

豆瓣网的反爬机制就是如果频繁访问的话会对ip进行封禁,下次再访问的时候需要登录才能访问。

标签:name,img,url,self,爬取,豆瓣,file,top250,film
来源: https://blog.csdn.net/qq_44805233/article/details/121055945