python爬取網(wǎng)易云音樂(lè)熱歌榜實(shí)例代碼
首先找到要下載的歌曲排行榜的鏈接,這里用的是:
https://music.163.com/discover/toplist?id=3778678
然后更改你要保存的目錄,目錄要先建立好文件夾,例如我的是保存在D盤-360下載-網(wǎng)易云熱歌榜文件夾內(nèi),就可以完成下載。
如果文件夾沒(méi)有提前建好,會(huì)報(bào)錯(cuò)[Errno 2] No such file or directory。
代碼實(shí)現(xiàn):
from urllib import requestfrom bs4 import BeautifulSoupimport reimport requestsimport timeclass 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? - ' + j[0] + '.mp3', 'wb') as f:f.write(content) print(j[1] + ' - ' + j[0] + '下載完畢。n') time.sleep(0.5) returnif __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(wǎng)易云熱歌榜/' # 保存的文件目錄 demo0 = Music(baseurl, path) demo0.main() print('下載完畢')
內(nèi)容擴(kuò)展:
Python3實(shí)戰(zhàn)之爬蟲抓取網(wǎng)易云音樂(lè)的熱門評(píng)論
#!/usr/bin/env python3# -*- coding: utf-8 -*-import reimport urllib.requestimport urllib.errorimport urllib.parseimport jsondef 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(wǎng)易云云音樂(lè)熱歌榜url html=urllib.request.urlopen(url).read().decode(’utf8’) #打開url html=str(html) #轉(zhuǎn)換成str pat1=r’<ul class='f-hide'><li><a href='http://www.lshqa.cn/song?id=d*?' rel='external nofollow' rel='external nofollow' >.*</a></li></ul>’ #進(jìn)行第一次篩選的正則表達(dá)式 result=re.compile(pat1).findall(html) #用正則表達(dá)式進(jìn)行篩選 result=result[0] #獲取tuple的第一個(gè)元素 pat2=r’<li><a href='http://www.lshqa.cn/song?id=d*?' rel='external nofollow' rel='external nofollow' >(.*?)</a></li>’ #進(jìn)行歌名篩選的正則表達(dá)式 pat3=r’<li><a href='http://www.lshqa.cn/song?id=(d*?)' rel='external nofollow' >.*?</a></li>’ #進(jìn)行歌ID篩選的正則表達(dá)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(duì)應(yīng)的Id return hot_song_name,hot_song_iddef 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(píng)url header={ #請(qǐng)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(qǐng)求表單數(shù)據(jù) data={’params’:’zC7fzWBKxxsm6TZ3PiRjd056g9iGHtbtc8vjTpBXshKIboaPnUyAXKze+KNi9QiEz/IieyRnZfNztp7yvTFyBXOlVQP/JdYNZw2+GRQDg7grOR2ZjroqoOU2z0TNhy+qDHKSV8ZXOnxUF93w3DA51ADDQHB0IngL+v6N8KthdVZeZBe0d3EsUFS8ZJltNRUJ’,’encSecKey’:’4801507e42c326dfc6b50539395a4fe417594f7cf122cf3d061d1447372ba3aa804541a8ae3b3811c081eb0f2b71827850af59af411a10a1795f7a16a5189d163bc9f67b3d1907f5e6fac652f7ef66e5a1f12d6949be851fcf4f39a0c2379580a040dc53b306d5c807bf313cc0e8f39bf7d35de691c497cda1d436b808549acc’} postdata=urllib.parse.urlencode(data).encode(’utf8’) #進(jìn)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(píng)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==============================================nn’) fhandle.close()hot_song_name,hot_song_id=get_all_hotSong() #獲取熱歌榜所有歌曲名稱和idnum=0while num < len(hot_song_name): #保存所有熱歌榜中的熱評(píng) print(’正在抓取第%d首歌曲熱評(píng)...’%(num+1)) get_hotComments(hot_song_name[num],hot_song_id[num]) print(’第%d首歌曲熱評(píng)抓取成功’%(num+1)) num+=1
以上就是python爬取網(wǎng)易云音樂(lè)熱歌榜實(shí)例代碼的詳細(xì)內(nèi)容,更多關(guān)于python爬取網(wǎng)易云音樂(lè)熱歌榜的資料請(qǐng)關(guān)注好吧啦網(wǎng)其它相關(guān)文章!
相關(guān)文章:
1. Springboot整合camunda+mysql的集成流程分析2. jsp網(wǎng)頁(yè)實(shí)現(xiàn)貪吃蛇小游戲3. ASP動(dòng)態(tài)網(wǎng)頁(yè)制作技術(shù)經(jīng)驗(yàn)分享4. python中復(fù)數(shù)的共軛復(fù)數(shù)知識(shí)點(diǎn)總結(jié)5. PHP中file_get_contents設(shè)置header請(qǐng)求頭,curl傳輸選項(xiàng)參數(shù)詳解說(shuō)明6. 愛因斯坦謎題的java解答方法7. idea自定義快捷鍵的方法步驟8. idea重置默認(rèn)配置的方法步驟9. html清除浮動(dòng)的6種方法示例10. HTML DOM setInterval和clearInterval方法案例詳解
