Homework05~~~~~作业

今天的作业很难，我真的不会！！！！

import json
import requests
import multiprocessing

def text(path):
    song_play_url_list = []
    song_name_list = []
    with open(path,mode='r') as f:
        res = f.readlines()[0].strip('\n').split('}')
        for json_ in res[:-1]:
            _json = json_ + '}'
            _json = json.loads(_json)
            song_play_url = _json['song_play_url']
            if song_play_url is not None:
                song_play_url_list.append(song_play_url)
                song_name = _json['song_name']  
                song_name_list.append(song_name)
        return song_play_url_list , song_name_list 

song_url,song_name = text('C:/Users/admin/Desktop/yinyue/top_500.txt')

def download(song_url,song_name):
    i = -1
    for path_ in song_url:
        i += 1
        response = requests.get(path_)
        mp3_ = response.content
        with open('D:/music/'+song_name[i]+'.mp3',mode='wb') as f:
            f.write(mp3_)

#download(song_url,song_name)
if __name__ == "__main__":
    x = int(len(song_url)/2)
    #创建进程
    p1 = multiprocessing.Process(target=download,args=(song_url[0:x],song_name[0:x]))
    p2 = multiprocessing.Process(target=download,args=(song_url[x:],song_name[x:]))
    #启动进程
    p1.start()
    p2.start()
    p1.join()
    p2.join()
    print("Over")

结果显示：

2.想办法把 https://www.17k.com/list/3015690.html 页面中章节详情的内容URL给拿到
2.1 做进程划分,爬取章节页面详情存储到本地,一个章节一个html文件.
2.2 html = response.text
2.3 如果你的请求返回出来的是乱码,设置response.encoding=‘utf-8’/‘gbk’…
2.4 你把文章的内容给拿出来存到本地.