豆瓣top250电影抓取(1)

waiting to write more

import json
import urllib.request
import urllib.parse


class DoubanMovies(object):
    movies = []

    def __init__(self, base_url):
        self.base_url = base_url

    def download(self, start=0):
        post_data = {
            "start": start,
        }
        post_data = urllib.parse.urlencode(post_data)
        post_data = post_data.encode("utf-8")
        print(post_data)
        request = urllib.request.Request(self.base_url, post_data)

        # download movies
        response = urllib.request.urlopen(request)
        return response.read().decode("utf-8")

    def parse(self, data):
        data = json.loads(data)
        for movie in data["subjects"]:
            movie_name = bytes(movie["title"], encoding="utf-8")
            movie_name = movie_name.decode("utf-8")
            self.movies.append(movie_name)


if __name__ == "__main__":
    pass
    movies_obj = DoubanMovies("https://api.douban.com/v2/movie/top250")
    for i in [i*10 for i in range(25) if i % 2 == 0]:
        json_data = movies_obj.download(start=i)
        movies_obj.parse(json_data)

    print(movies_obj.movies)

# store the data into the database