爬取豆瓣电影，把电影名称和详情url保存到json中

# -*-coding:utf-8-*-
import requests
import json

class Douban(object):
    def __init__(self):
        self.url = "https://m.douban.com/rexxar/api/v2/subject_collection/movie_showing/items?&start=0&count=100"
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.79 Safari/537.36'
        }

    def get_data(self):
        response = requests.get(self.url, headers=self.headers)
        # print(response.content.decode())
        return response.content.decode('UTF-8')

    def parse_data(self, data):
        # print(type(data))
        # str转化为dict
        dict_data = json.loads(data)
        # 使用key获取值  movie_li是一个元素为字典的列表
        movie_list = dict_data['subject_collection_items']
        # 把提取的内容放到新的元素为字典（key电影名称，）的列表中
        data_list = []
        for movie_info in movie_list:
            temp_dict = {}
            temp_dict['title'] = movie_info['title']
            temp_dict['url'] = movie_info['url']
            data_list.append(temp_dict)
            print(temp_dict['title'])
        # chardet.detect(data_list[0]['title'])
        return data_list


    def save_data(self, data_list):
        with open('douban_movie.json','w') as f:
            for data_info in data_list:
                str_data = json.dumps(data_info, ensure_ascii=False) + ',\n'
                f.write(str_data)

    def run(self):
        # 发起请求
        data = self.get_data()
        # 解析数据
        data_list = self.parse_data(data)
        # 保存数据
        self.save_data(data_list)
        # print(data)


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