您好,登錄后才能下訂單哦!
本篇文章給大家分享的是有關利用python爬蟲實現爬取網易云音樂熱歌榜,小編覺得挺實用的,因此分享給大家學習,希望大家閱讀完這篇文章后可以有所收獲,話不多說,跟著小編一起來看看吧。
代碼實現:
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("正在下載:" + 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] + "下載完畢。\n") time.sleep(0.5) return if __name__ == "__main__": baseurl = "https://music.163.com/discover/toplist?id=3778678" # 要爬取的熱歌榜鏈接 path = "D:/360下載/網易云熱歌榜/" # 保存的文件目錄 demo0 = Music(baseurl, path) demo0.main() print("下載完畢")
內容擴展:
Python3實戰之爬蟲抓取網易云音樂的熱門評論
#!/usr/bin/env python3 # -*- coding: utf-8 -*- import re import urllib.request import urllib.error import urllib.parse import json def get_all_hotSong(): #獲取熱歌榜所有歌曲名稱和id url='http://music.163.com/discover/toplist?id=3778678' #網易云云音樂熱歌榜url html=urllib.request.urlopen(url).read().decode('utf8') #打開url html=str(html) #轉換成str pat1=r'<ul class="f-hide"><li><a href="/song\?id=\d*?" rel="external nofollow" rel="external nofollow" >.*</a></li></ul>' #進行第一次篩選的正則表達式 result=re.compile(pat1).findall(html) #用正則表達式進行篩選 result=result[0] #獲取tuple的第一個元素 pat2=r'<li><a href="/song\?id=\d*?" rel="external nofollow" rel="external nofollow" >(.*?)</a></li>' #進行歌名篩選的正則表達式 pat3=r'<li><a href="/song\?id=(\d*?)" rel="external nofollow" >.*?</a></li>' #進行歌ID篩選的正則表達式 hot_song_name=re.compile(pat2).findall(result) #獲取所有熱門歌曲名稱 hot_song_id=re.compile(pat3).findall(result) #獲取所有熱門歌曲對應的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 + '?csrf_token=' #歌評url header={ #請求頭部 '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請求表單數據 data={'params':'zC7fzWBKxxsm6TZ3PiRjd056g9iGHtbtc8vjTpBXshKIboaPnUyAXKze+KNi9QiEz/IieyRnZfNztp7yvTFyBXOlVQP/JdYNZw2+GRQDg7grOR2ZjroqoOU2z0TNhy+qDHKSV8ZXOnxUF93w3DA51ADDQHB0IngL+v6N8KthdVZeZBe0d3EsUFS8ZJltNRUJ','encSecKey':'4801507e42c326dfc6b50539395a4fe417594f7cf122cf3d061d1447372ba3aa804541a8ae3b3811c081eb0f2b71827850af59af411a10a1795f7a16a5189d163bc9f67b3d1907f5e6fac652f7ef66e5a1f12d6949be851fcf4f39a0c2379580a040dc53b306d5c807bf313cc0e8f39bf7d35de691c497cda1d436b808549acc'} postdata=urllib.parse.urlencode(data).encode('utf8') #進行編碼 request=urllib.request.Request(url,headers=header,data=postdata) reponse=urllib.request.urlopen(request).read().decode('utf8') json_dict=json.loads(reponse) #獲取json hot_commit=json_dict['hotComments'] #獲取json中的熱門評論 num=0 fhandle=open('./song_comments','a') #寫入文件 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() #獲取熱歌榜所有歌曲名稱和id num=0 while num < len(hot_song_name): #保存所有熱歌榜中的熱評 print('正在抓取第%d首歌曲熱評...'%(num+1)) get_hotComments(hot_song_name[num],hot_song_id[num]) print('第%d首歌曲熱評抓取成功'%(num+1)) num+=1
以上就是利用python爬蟲實現爬取網易云音樂熱歌榜,小編相信有部分知識點可能是我們日常工作會見到或用到的。希望你能通過這篇文章學到更多知識。更多詳情敬請關注億速云行業資訊頻道。
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。