猫眼电影爬取

最新推荐文章于 2025-02-28 09:46:45 发布

转载最新推荐文章于 2025-02-28 09:46:45 发布 · 339 阅读

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/yuxiangyang/p/11212544.html

本文介绍了一个Python爬虫项目，该项目用于抓取猫眼电影网站上的Top100电影数据，并将这些数据保存到CSV文件中。爬虫使用了随机User-Agent来模拟不同的浏览器请求，通过正则表达式解析网页内容并提取电影名称、主演和上映时间等信息。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

'''爬取猫眼电影TOP100，并将其保存'''
from urllib import request
import re
import csv
import time
import random
import os


class MaoyanSpider:
    def __init__(self):
        self.url = 'https://maoyan.com/board/4?offset={}'
        self.ua_list = [
            'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
            'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0',
            'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
            'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; GTB7.0)',
            'Mozilla/5.0 (Windows; U; Windows NT 6.1; ) AppleWebKit/534.12 (KHTML, like Gecko) Maxthon/3.0 Safari/534.12',
            'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.472.33 Safari/534.3 SE 2.X MetaSr 1.0',
            'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.41 Safari/535.1 QQBrowser/6.9.11079.201'
        ]

    # 获取页面
    def get_page(self, url):
        # 每次使用随机的User-Agent
        headers = {'User-Agent': random.choice(self.ua_list)}
        req = request.Request(url=url, headers=headers)
        res = request.urlopen(req)
        html = res.read().decode('utf-8')
        # 调用解析函数
        self.parse_page(html)

    # 解析页面
    def parse_page(self, html):
        pattern = re.compile(
            r'<div class="movie-item-info">.*?title="(.*?)".*?class="star">(.*?)</p>.*?class="releasetime">(.*?)</p>',
            re.S)
        r_list = pattern.findall(html)
        self.save_info(r_list)

    # 打印页面
    # def save_info(self, r_list):
    #     one_film_dict = {}
    #     for rt in r_list:
    #         one_film_dict['name'] = rt[0].strip()
    #         one_film_dict['stars'] = rt[1].strip()
    #         one_film_dict['time'] = rt[2].strip()
    #         print(one_film_dict)

    # 保存页面
    def save_info(self, r_list):
        film_list = []
        with open('./maoyan.csv', 'a', encoding='utf-8', newline='') as f:
            # 方法一：一条一条写入csv
            # for rt in r_list:
            #     writer = csv.writer(f)
            #     writer.writerow([rt[0].strip(), rt[1].strip(), rt[2].strip()])
            # 方法二：一次性写入csv,减少IO
            writer = csv.writer(f)
            for rt in r_list:
                # 把处理过的数据定义成元组
                t = (rt[0].strip(), rt[1].strip(), rt[2].strip())
                film_list.append(t)
            writer.writerows(film_list)

    # 主函数
    def main(self):
        if os.path.exists('./maoyan.csv'):
            os.remove('./maoyan.csv')
        with open('./maoyan.csv', 'a', encoding='utf-8', newline='') as f:
            writer = csv.writer(f)
            writer.writerow(['电影名称', '主演', '上映时间'])
        i = 1
        for offset in range(0, 91, 10):
            url = self.url.format(offset)
            self.get_page(url)
            print('第{}页成功下载'.format(i))
            i += 1
            # time.sleep(random.randint(1, 4))


if __name__ == '__main__':
    start = time.time()
    spider = MaoyanSpider()
    spider.main()
    end = time.time()
    print('程序执行时间为: %.2f' % (end - start))

转载于:https://www.cnblogs.com/yuxiangyang/p/11212544.html