Urllib+BeautifulSoup(抓取音频)

更多爬虫实例请见 https://blog.csdn.net/weixin_39777626/article/details/81564819

from bs4 import BeautifulSoup
from urllib.request import urlopen,urlretrieve,Request
import json

Url=[]
def getUrl(URL):
    try:
        headers = {
            'User-Agent': r'xxxxxxxxxxxxxxxx'
                          r'xxxxxxxxxxxxxxxxxxx',
            'Referer': r'http://www.ximalaya.com/99380456/album/12061818/',
            'Connection': 'keep-alive'
        }
        req = Request(URL, headers=headers)
        page = urlopen(req).read()
        bs4=BeautifulSoup(page,'lxml')
        pictures=bs4.find('div',class_='personal_container').find('div','personal_body').get('sound_ids')
        List=pictures.split(',')
        for i in List:
            i='http://www.ximalaya.com/tracks/'+i+'.json'
            Url.append(i)
        return Url
    except:
        return '...'

def getmusic(url):
    headers = {
            'User-Agent': r'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)'
                          r'Chrome/47.0.2526.108 Safari/537.36 2345Explorer/8.8.3.16721',
            'Referer': r'http://www.ximalaya.com/',
            'Connection': 'keep-alive'
        }
    req = Request(url, headers=headers)
    page = urlopen(req).read()
    page = page.decode('utf-8')
    a=json.loads(page)
    name=a.get('title')+'.m4a'
    music=a.get('play_path_64')
    urlretrieve(music,name)

for i in range(1,4):
    getUrl('http://www.ximalaya.com/15312621/album/381417?page=%d'%i)
    for url in Url:
        getmusic(url)

更多爬虫实例请见 https://blog.csdn.net/weixin_39777626/article/details/81564819