虾米音乐下载

#encoding:utf8

import requests
import re
from bs4 import BeautifulSoup
from lxml import etree

class xiaMi:
    def __init__(self):
        self.root_url = "http://www.xiami.com/search?key="
        self.head = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.3831.602 Safari/537.36"}

    def get_html(self,url):
        if url == "":
            return
        html = requests.get(url,headers=self.head)
        if html.status_code != 200:
            return
        else:
            return html.text

    def related_songs(self,response):
        songs = []
        for tr in BeautifulSoup(response,"lxml").find_all("tr"):
            xpath = etree.HTML(str(tr))
            try:
                song_name = xpath.xpath('//*[@class="song_name"]/a/text()')[0]#歌曲名
                song_artist = xpath.xpath('//*[@class="song_artist"]/a/text()')[0]#歌手
                song_album = "".join(xpath.xpath('//*[@class="song_album"]/a/text() | //*[@class="song_album"]/a/b/text()'))#专辑
                sid = re.match(r'\w+\(\'(\d+)\',\'\d+\'\)',xpath.xpath('//*[@class="song_act"]/div/a[@class="song_digg"]/@onclick')[0]).group(1)
                songs.append({"song_name":song_name,"song_artist":song_artist.strip(),"song_album":song_album,"sid":sid})
            except:
                pass
        if songs == []:
            return False
        return songs

    def parse_url(self,song_id):
        url = "http://www.xiami.com/widget/xml-single/uid/0/sid/"+song_id
        sid = re.compile('CDATA\[(.*?)\]', re.S).findall(requests.get(url,headers=self.head).text)[4]
        num_loc = sid.find('h')#获取当前h的下标  改下标为1
        rows = int(sid[0:num_loc])#获取第一个数字
        strlen = len(sid) - num_loc#用该字符串减去h出现的下标得到的长度
        cols = int(strlen / rows)#用长度除以第一位数字得到的串数
        right_rows = strlen % rows#用长度除以第一位数字得到的余数
        new_s = sid[num_loc:]#获取h以后的所有元素
        output = ''
        for i in range(len(new_s)):
            x = i % rows
            y = int(i / rows)
            p = 0
            if x <= right_rows:
                p = x * (cols + 1) + y
            else:
                p = right_rows * (cols + 1) + (x - right_rows) * cols + y
            output += new_s[int(p)]
        return requests.utils.unquote(output).replace('^', '0')

    def get_download_link(self,name,url):
        print("开始下载%s"%name)
        musice = requests.get(url,headers=self.head).content
        with open("music/%s.mp3"%name,"wb") as f:
            f.write(musice)
        print("%s下载完成"%name)

    def dio(self):
        while True:
            select = input("搜索歌曲,退出q:")
            if select.lower() == "q":
                exit(0)
            else:
                html = self.get_html(self.root_url+select)
                songs = self.related_songs(html)
                if songs == False:
                    print("输入的歌名有误!")
                    continue
                for i in range(len(songs)):
                    print("%d  %s\t%s\t%s"%(i+1,songs[i]["song_name"],songs[i]["song_artist"],songs[i]["song_album"]))
                sid = int(input("请选择:"))-1
                print("您选择的是\t《%s》\t的\t《%s》"%(songs[sid]["song_artist"],songs[sid]["song_name"]))
                download_url = self.parse_url(songs[sid]["sid"])
                self.get_download_link(songs[sid]["song_name"],download_url)



if __name__ == '__main__':
    wode = xiaMi()
    wode.dio()