利用python爬虫实现爬取网易云音乐热歌榜

from urllib import request
from bs4 import BeautifulSoup
import re
import requests
import time


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"
      }
    self.baseurl = baseurl
    self.headers = head
    self.path = path


  def main(self):
    html = self.askurl()
    bs4 = self.analysis(html)
    name1 = self.matching(bs4)
    self.save(name1)


  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("textarea")
    bs4 = str(bs4)
    return bs4


  def matching(self, bs4):
  	rule0 = re.compile(r'"name":"(.*?)","tns":[],"alias":[]')
    name0 = re.findall(rule0, bs4)
    str = ""
    for i in name0:
      str = str + "," + i
    str = str.replace("\xa0", " ")
    rule1 = re.compile(r'jpg,(.*?),(.*?)","id":(\d*)')
    name1 = re.findall(rule1, str)
    return name1


  def save(self, name1):
    for j in name1:
      print("正在下载：" + j[1] + " - " + j[0] + "...")
      url = "http://music.163.com/song/media/outer/url?id=" + j[2]
      content = requests.get(url=url, headers=self.headers).content
      with open(self.path + j[1] + " - " + j[0] + ".mp3", "wb") as f:
        f.write(content)
      print(j[1] + " - " + j[0] + "下载完毕。\n")
      time.sleep(0.5)
    return


if __name__ == "__main__":
  baseurl = "https://music.163.com/discover/toplist?id=3778678" # 要爬取的热歌榜链接
  path = "D:/360下载/网易云热歌榜/" # 保存的文件目录
  demo0 = Music(baseurl, path)
  demo0.main()
  print("下载完毕")

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import re
import urllib.request
import urllib.error
import urllib.parse
import json



def get_all_hotSong(): #获取热歌榜所有歌曲名称和id
 url='http://music.163.com/discover/toplist?id=3778678' #网易云云音乐热歌榜url
 html=urllib.request.urlopen(url).read().decode('utf8') #打开url
 html=str(html) #转换成str
 pat1=r'<ul class="f-hide"><li><a href="/song\&#63;id=\d*&#63;" rel="external nofollow" rel="external nofollow" >.*</a></li></ul>' #进行第一次筛选的正则表达式
 result=re.compile(pat1).findall(html) #用正则表达式进行筛选
 result=result[0] #获取tuple的第一个元素

 pat2=r'<li><a href="/song\&#63;id=\d*&#63;" rel="external nofollow" rel="external nofollow" >(.*&#63;)</a></li>' #进行歌名筛选的正则表达式
 pat3=r'<li><a href="/song\&#63;id=(\d*&#63;)" rel="external nofollow" >.*&#63;</a></li>' #进行歌ID筛选的正则表达式
 hot_song_name=re.compile(pat2).findall(result) #获取所有热门歌曲名称
 hot_song_id=re.compile(pat3).findall(result) #获取所有热门歌曲对应的Id

 return hot_song_name,hot_song_id

def get_hotComments(hot_song_name,hot_song_id):
 url='http://music.163.com/weapi/v1/resource/comments/R_SO_4_' + hot_song_id + '&#63;csrf_token=' #歌评url
 header={ #请求头部
 'User-Agent':'Mozilla/5.0 (X11; Fedora; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}
 #post请求表单数据
 data={'params':'zC7fzWBKxxsm6TZ3PiRjd056g9iGHtbtc8vjTpBXshKIboaPnUyAXKze+KNi9QiEz/IieyRnZfNztp7yvTFyBXOlVQP/JdYNZw2+GRQDg7grOR2ZjroqoOU2z0TNhy+qDHKSV8ZXOnxUF93w3DA51ADDQHB0IngL+v6N8KthdVZeZBe0d3EsUFS8ZJltNRUJ','encSecKey':'4801507e42c326dfc6b50539395a4fe417594f7cf122cf3d061d1447372ba3aa804541a8ae3b3811c081eb0f2b71827850af59af411a10a1795f7a16a5189d163bc9f67b3d1907f5e6fac652f7ef66e5a1f12d6949be851fcf4f39a0c2379580a040dc53b306d5c807bf313cc0e8f39bf7d35de691c497cda1d436b808549acc'}
 postdata=urllib.parse.urlencode(data).encode('utf8') #进行编码
 request=urllib.request.Request(url,headers=header,data=postdata)
 reponse=urllib.request.urlopen(request).read().decode('utf8')
 json_dict=json.loads(reponse) #获取json
 hot_commit=json_dict['hotComments'] #获取json中的热门评论


 num=0
 fhandle=open('./song_comments','a') #写入文件
 fhandle.write(hot_song_name+':'+'\n')

 for item in hot_commit:
 num+=1
 fhandle.write(str(num)+'.'+item['content']+'\n')
 fhandle.write('\n==============================================\n\n')
 fhandle.close()




hot_song_name,hot_song_id=get_all_hotSong() #获取热歌榜所有歌曲名称和id

num=0
while num < len(hot_song_name): #保存所有热歌榜中的热评
 print('正在抓取第%d首歌曲热评...'%(num+1))
 get_hotComments(hot_song_name[num],hot_song_id[num])
 print('第%d首歌曲热评抓取成功'%(num+1))
 num+=1