Python爬蟲實踐--爬取網易雲音樂

import os

import re

import json

import requests

from lxml import etree

def download_songs(url=None):

     if url is None:

         url = '

     url = url.replace('/#', '').replace('https', 'http')  # 對字串進行去空格和轉協議處理

     # 網易雲音樂外鏈 url 介面：

     out_link = '

     # 請求頭

     headers = {

         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36',

         'Referer': '

         'Host': 'music.163.com'

     }

     # 請求頁面的原始碼

     res = requests.get(url=url, headers=headers).text

     tree = etree.HTML(res)

     # 音樂列表

     song_list = tree.xpath('//ul[@class="f-hide"]/li/a')

     # 如果是歌手頁面

     artist_name_tree = tree.xpath('//h2[@id="artist-name"]/text()')

     artist_name = str(artist_name_tree[0]) if artist_name_tree else None

     # 如果是歌單頁面：

     #song_list_tree = tree.xpath('//*[@id="m-playlist"]/div[1]/div/div/div[2]/div[2]/div/div[1]/table/tbody')

     song_list_name_tree = tree.xpath('//h2[contains(@class,"f-ff2")]/text()')

     song_list_name = str(song_list_name_tree[0]) if song_list_name_tree else None

     # 設定音樂下載的資料夾為歌手名字或歌單名

     folder = './' + artist_name if artist_name else './' + song_list_name

     if not os.path.exists(folder):

         os.mkdir(folder)

     for i, s in enumerate(song_list):

         href = str(s.xpath('./@href')[0])

         song_id = href.split('=')[-1]

         src = out_link + song_id  # 拼接獲取音樂真實的 src 資源值

         title = str(s.xpath('./text()')[0])  # 音樂的名字

         filename =外匯跟單gendan5.com title + '.mp3'

         filepath = folder + '/' + filename

         print(' 開始下載第 {} 首音樂： {}\n'.format(i + 1, filename))

         try:  # 下載音樂

             # 下載歌詞

             #download_lyric(title, song_id)

             data = requests.get(src).content  # 音樂的二進位制資料

             with open(filepath, 'wb') as f:

                 f.write(data)

         except Exception as e:

             print(e)

     print('{} 首全部歌曲已經下載完畢！ '.format(len(song_list)))

def download_lyric(song_name, song_id):

     url = '{}&lv=-1&kv=-1&tv=-1'.format(song_id)

     # 請求頭

     headers = {

         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36',

         'Referer': '

         'Host': 'music.163.com'

         # 'Origin': '

     }

     # 請求頁面的原始碼

     res = requests.get(url=url, headers=headers).text

     json_obj = json.loads(res)

     lyric = json_obj['lrc']['lyric']

     reg = re.compile(r'\[.*\]')

     lrc_text = re.sub(reg, '', lyric).strip()

     print(song_name, lrc_text)

if __name__ == '__main__':

     #music_list = ' # 歌曲清單

     music_list = ' # 歌手排行榜

     # music_list = ' 全部 &limit=435&offset=435&s= 梁靜茹 ' # 搜尋列表

     download_songs(music_list)