爬虫 爬取豆瓣高分电影信息

import re, requests
import json

class DoubanSpider:
    def __init__(self):
        self.url_temp = "https://movie.douban.com/j/search_subjects?type=movie&tag=%E8%B1%86%E7%93%A3%E9%AB%98%E5%88%86&sort=recommend&page_limit=20&page_start={}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"}

    def parse_url(self, url):  # 发送请求，获取响应
        print(url)
        response = requests.get(url, self.headers)
        return response.content.decode()

    def get_content_list(self, json_str):  # 提取数据
        dict_ret = json.loads(json_str)
        print(dict_ret)
        content_list = dict_ret["subjects"]  # 所有电影数据
        return content_list

    def save_content_list(self, content_list):  # 保存
        with open("douban.txt", 'a', encoding="utf-8") as f:
            for content in content_list:
                f.write(json.dumps(content, ensure_ascii=False))
                f.write("\n")  # 写入换行符
        print("保存成功")

    def run(self):  # 实现主要逻辑
        num = 0
        while True:
            # 1、构造start_url
            url = self.url_temp.format(num)
            # 2、发送请求，获取响应
            json_str = self.parse_url(url)
            # 3、提取数据
            content_list = self.get_content_list(json_str)
            # 4、保存
            self.save_content_list(content_list)
            # 5、判断是否有下一页
            if len(content_list) < 20:
                break
            # 6、构造下一个url地址
            num += 20


if __name__ == '__main__':
    douban = DoubanSpider()
    douban.run()