【技术流】2017年有哪些值得看的电影（豆瓣8.0以上）

# -*- coding: utf-8 -*-
import time
import requests
from bs4 import BeautifulSoup
import json
import time
import os
import multiprocessing

class movie_spider(object):
    #将电影的分类和对应的Tag建立了一个字典类型
    m_movie_class = {'Chinese':'%E5%8D%8E%E8%AF%AD','EuropeandAmerica':'%E6%AC%A7%E7%BE%8E','Korea':'%E9%9F%A9%E5%9B%BD',
              'Janpan':'%E6%97%A5%E6%9C%AC','Action':'%E5%8A%A8%E4%BD%9C','Comedy':'%E5%96%9C%E5%89%A7',
              'Love':'%E7%88%B1%E6%83%85','ScienceFiction':'%E7%A7%91%E5%B9%BB','Suspense':'%E6%82%AC%E7%96%91'}
    def __init__(self,movie_class_name,movie_class_content,iter_number = 100,local_path=''):
        self.movie_list = list() 
        self.movie_class_name = movie_class_name
        self.movie_class_content = movie_class_content
        self.iter_number = iter_number  #查询电影的个数
        self.local_path = local_path
    def get_movie_id(self):
        for start in range(0, self.iter_number, 20):
            url = 'https://movie.douban.com/j/search_subjects?type=movie&tag=' + str(
                self.movie_class_content) + '&sort=recommend&page_limit=20&page_start=' + str(start)
            time.sleep(0.5)
            source_code = requests.get(url)
            soup = BeautifulSoup(source_code.text, 'lxml')
            j = json.loads(soup.text)
            subjects = j['subjects']
            for item in subjects:
                self.get_movie_infor(item['id'])
    def get_movie_infor(self,id):
        url = 'https://movie.douban.com/j/subject_abstract?subject_id=' + str(id);
        source_code = requests.get(url)
        soup = BeautifulSoup(source_code.text, 'lxml')
        j = json.loads(soup.text)
        subjects = j['subject']
        self.get_movie_content(id, subjects)
    def get_movie_content(self,id,item):
        if (item['release_year'] == '2017'):
            movie = list()
            movie.append(id)
            movie.append(item['title'])
            movie.append(float(item['rate']))
            movie.append(item['actors'])
            movie.append(item['region'])
            movie.append(item['duration'])
            #movie.append(str(item['short_comment']['content']))  #评论暂时有问题
            self.movie_list.append(movie)
    def save_movie_content(self,movies, num =10, rate=8.0):
        folder_path = str(self.local_path)+'/'+'douban_'+str(self.movie_class_name)+'.txt'
        with open(folder_path, 'w', encoding='utf-8', errors='ignore') as f:
            n = 0
            while n < num:
                if (movies[n][2] >= rate):
                    f.write(str(n))
                    f.write('\t')
                    for item in movies[n]:
                        f.write(str(item))
                        f.write('\t')
                    f.write("\n")
                    n = n + 1
                else:
                    break
    def print_movie_content(self,movies):
        for movie in movies:
            print(str(movie) + ' ', end='')
            print(end='\n')
    def start(self,):
        print ("Process Start: "+str(self.movie_class_name))
        self.get_movie_id()
        init_movies = sorted(self.movie_list, key=lambda movie: movie[2], reverse=True)
        self.save_movie_content(init_movies,10,8.0)  #打印出10部超过8.0评分的电影，如果没有10部，只打印出来有的

def main():
    #使用的是多线程
    local_time = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
    os.mkdir(local_time)
    for movie_class_name in movie_spider.m_movie_class:
        ms = movie_spider(movie_class_name,movie_spider.m_movie_class[movie_class_name],300,local_time)  #300为查询电影的个数
        p = multiprocessing.Process(target=ms.start)
        p.start()

if __name__ == '__main__':
    main()