302重定向、下歌

重定向：

 

def redirect(url):

    r = requests.get(url,params={'chrome':'utf-8', 'q':'666'})   #allow_redirects=False

    print(r.url, r.status_code, r.history)

 

redirect('http://www.so.com/s')

redirect('http://www.haosou.com/s')

*********************分割线*********************

重定向的应用场景：请求状态码为302的网址，从而获取以文件后缀结尾的真实下载网址

 

Egの下载酷我音乐：

 

import requests,os

 

def downLoadKuwo(url):

    r = requests.get(url).text

    musicName = '：'.join(r.split('title>')[1].split('-酷我音乐')[0].split('-')[:2][::-1])

    musicID=url.split('?')[0].split('/')[-1]

    redirectResult=requests.get(f'http://antiserver.kuwo.cn/anti.s?format=aac|mp3\

&rid=MUSIC_{musicID}&type=convert_url&response=res')

    #urllib2获取经若干次重定向的最终网址用r.geturl()；而requests库默认重定向，无需再请求r.url

    musicName=r'E:\music\\'+musicName+'.'+redirectResult.url.split('.')[-1]

    if not os.path.isdir('E:\music'):os.makedirs('E:\music')

    if not os.path.isfile(musicName):

        with open(musicName,'wb') as f: #with语法和iter_content()都是迭代器，避免内存耗尽

            for chunk in redirectResult.iter_content(1024*1024):   #f.write(redirectResult.content)

                f.write(chunk)

 

downLoadKuwo('http://www.kuwo.cn/yinyue/97881')   #http://bd.kuwo.cn/yinyue/7746750

****************************************分割线****************************************

Egの下载α旗下某视频网的视频：

 

import re,requests

from fake_useragent import UserAgent

from urllib.parse import parse_qs

 

def 下载某网(url):

    res=requests.get(url,headers={'User-Agent':UserAgent().random}).text

    videoName=re.findall('title":"(.*?)"',res)[0]+'.mp4'

    vUrl=re.findall('url_encoded_fmt_stream_map":"(.*?)"',res)[0].replace(r'\u0026','&')

    vUrl=parse_qs(vUrl)['url'][0].replace(',',',')

    result=requests.get(vUrl)

    with open(videoName,'wb') as f:

        for chunk in result.iter_content(1024 * 1024):

            f.write(chunk)

 

url='https://www.某网.com/watch?v=5yAU52qfYuU'

下载某网(url)

****************************************分割线****************************************

Egの下载喜马拉雅FM的音乐：

 

import requests,re,os,json

from fake_useragent import UserAgent

 

h={'User-Agent': UserAgent().random}

noName=r'[\\/:*?"<>|]'

 

def getAnchors():

    anchors = []

    for x in range(1,3):    #下载两页的主播人数

        res=requests.get(f'http://www.ximalaya.com/dq/{x}/',headers=h).text

        anchors.extend(re.findall('href="(.+?)" hashlink title="(.+?)" class="discoverAlbum_title',res))

    return anchors

 

def getAlbums():

    for anchors in getAnchors():

        path=f'E:/xmly/{anchors[1]}'

        if not os.path.isdir(path): os.makedirs(path)

        os.chdir(path)

        res = requests.get(anchors[0], headers=h).text    #各主播的音频专辑只下1页

        rule='(\d+?)" track_title="(.+?)" track_.+?([0-9-]+?)<.+?title="(\d+?)次'

        musicsDetails=re.findall(rule,res,re.S)

        with open(f'{anchors[1]}.txt','w',encoding='utf8') as f:

            for x in musicsDetails:

                f.write(json.dumps(x,ensure_ascii=False)+'\n')

        for x in musicsDetails[:4]: #音频挺多，每页选取前4个下载

            js=f'http://www.ximalaya.com/tracks/{x[0]}.json'

            musicUrl=requests.get(js,headers=h).json()['play_path_32']

            fileName=re.sub(noName,' ',x[1]).strip()+'.m4a'

            with open(fileName,'wb') as music:

                music.write(requests.get(musicUrl,headers=h).content)

 

if __name__ == '__main__':

    getAlbums()