Python实践7：类、函数定义及批量下载资料

import os
from urllib import request
from bs4 import BeautifulSoup
import re
import requests
import time
 
def getFileSize(filePath):
    fsize = os.path.getsize(filePath)
    fsize = fsize/float(1024 * 1024)  
    return round(fsize,2)  # MB 两位小数

class Music(object):
    def __init__(self, baseurl, path):
        head = {
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"
            }
        baseurl = baseurl.replace("#/", "")
        self.baseurl = baseurl
        self.headers = head
        self.path = path
 
 
    def main(self):
        html = self.askurl()
        bs4 = self.analysis(html)
        id = self.matching(bs4)
        self.save(id)
 
 
    def askurl(self):
        req = request.Request(url=self.baseurl, headers=self.headers)
        response = request.urlopen(req)
        html = response.read().decode("utf-8")
        return html
 
 
    def analysis(self, html):
        soup = BeautifulSoup(html, "html.parser")
        bs4 = soup.find_all("li")
        bs4 = str(bs4)
        return bs4
 
 
    def matching(self, bs4):
        rule = re.compile(r'href="/song\?id=(\d*?)"', re.S)
        id = re.findall(rule, bs4)
        return id
 
 
    def save(self, id):
        count = 0
        for i in id:
            url = "https://music.163.com/song?id=" + i
            req = request.Request(url=url, headers=self.headers)
            response = request.urlopen(req)
            html = response.read().decode("utf-8")
            soup = BeautifulSoup(html, "html.parser")
            bs4 = soup.find_all("title")
            bs4 = str(bs4)
            rule = re.compile(r'<title>(.*?) - (.*?) - 单曲 - 网易云音乐</title>', re.S)
            name_list = re.findall(rule, bs4)
            name = name_list[0]
            songname = str(name[0]).replace(r"/", "-")
            songname = songname.replace(r"|", "-")
            songname = songname.replace(r"？", "-")
            songname = songname.replace(r"?", "-")
            singername = name[1].replace(r"/", "-")

            count += 1

            print( str(count) + "...正在下载..." + songname + "...by " + singername + "...")
            saveurl = "http://music.163.com/song/media/outer/url?id=" + i
            content = requests.get(url=saveurl, headers=self.headers).content
            
            filename = self.path + singername +'_' + str(count) + '_' + songname  +  ".mp3"
            
            
            if not os.path.exists(filename):
                f = open(filename, "wb")
                f.write(content)
                print( '  '+ filename + "......下载完毕")
                f.close()
                filesize = getFileSize(filename)
                if  filesize < 1.0:  #对于需要会员需要下载的歌曲，下载后只有几十kb，无法播放
                    newFilename = filename+'_'+str(filesize)+'MB_可能无效.mp3'
                    if not os.path.exists(newFilename):
                        os.rename(filename,newFilename)
                        print( '  '+ "该文件太小，可能无效，已经备注......")
            else:
                print('  该文件已经存在，不用下载...')
        return
 

 
if __name__ == "__main__":
    artisturl = r'https://music.163.com/#/artist?id=14400'  # 歌手主页的网址
    path1 = r"F:\python_code\歌曲\_"     # 本地路径
    artist_demo = Music(artisturl,path1)
    artist_demo.main()
    print("\n全部下载完毕...\n")