# 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
import requests,os #下载酷我音乐
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=‘E:\music\\‘+musicName+‘.‘+redirectResult.url.split(‘.‘)[-1]
if not os.path.isdir(‘E:\music‘):os.mkdir(‘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): #f.write(redirectResult.content)
f.write(chunk)
downLoadKuwo(‘http://www.kuwo.cn/yinyue/97881‘) #http://bd.kuwo.cn/yinyue/7746750
****************************************分割线****************************************
下载喜马拉雅FM的音乐：
import requests,re,os,json
headers={‘User-Agent‘: ‘Mozilla/5.0 Chrome/59‘}
def getAnchors():
anchors = []
for x in range(1,3): #下载两页的主播人数
res=requests.get(‘http://www.ximalaya.com/dq/%s/‘ %x,headers=headers).text
anchors.extend(re.findall(‘href="(.+?)" hashlink title="(.+?)" class="discoverAlbum_title‘,res))
return anchors
def getAlbums():
for anchors in getAnchors():
path=‘E:\scrapyDownload\%s‘ %anchors[1]
if not os.path.exists(path): os.mkdir(path)
os.chdir(path)
res = requests.get(anchors[0], headers=headers).text #主播的音频数只下1页
rule=‘(\d+?)" track_title="(.+?)" track_.+?([0-9-]+?)<.+?title="(\d+?)次‘
musicsDetails=re.findall(rule,res,re.S)
with open(‘%s.txt‘ %anchors[1],‘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=‘http://www.ximalaya.com/tracks/%s.json‘ %x[0]
musicUrl=requests.get(js,headers=headers).json()[‘play_path_32‘]
with open(x[1].replace(‘?‘,‘‘)+‘.m4a‘,‘wb‘) as music: #Win系统的文件名不能有?
music.write(requests.get(musicUrl,headers=headers).content)
if __name__ == ‘__main__‘:
getAlbums()