#python爬取音乐网站

音乐网站"/>

#python爬取音乐网站

今天学习了网上一段爬取音乐的代码，自己也作了些微改动是它能顺便爬取歌词，并整理了些知识点（对刚接触几天的自己确实是知识点）完整代码如下：

#!/usr/bin/python
# _*_ coding: utf-8 _*_
from bs4 import BeautifulSoup
import re
import requests
import json
import urllib2,urllib
import osminimumsize = 1
def getlist(url):r = requests.get(url)content = r.contentcontent = content.decode('utf-8')#print contentsoup = BeautifulSoup(content,'lxml')#mm = soup.find_all('span',class_='song-title')[0]mm=soup.find_all('span',class_='song-title')mms = mmi = 0for m in  mm:mm[i] = m.contents[0]#获取span后第一个标签i+=1return mmurl = ""
list = getlist(url)for value in list:url = ''payload = {'word': value.get_text(), 'version': '2', 'from': '0'}#根据百度音乐API编写print "Song Name: " + value.get_text()#value.get_text()获取a标签内的内容r = requests.get(url, params=payload)contents = r.text#print contentsd = json.loads(contents, encoding="utf-8")#print dif('data' not in d):print "do not have flac\n"continueif('song' not in d["data"]):print "do not have flac\n"continuesongid = d["data"]["song"][0]["songid"]#print "Song ID: " + songidurl = ''payload = {'songIds': songid, 'type': 'mp3'}r = requests.get(url, params=payload)contents = r.textd = json.loads(contents, encoding="utf-8")#print dif d is not None and 'data' not in d or d['data'] == '':continuesonglink = d["data"]["songList"][0]["songLink"]lrcLink =d["data"]["songList"][0]["lrcLink"]print "lrc:"+lrcLinkif(len(songlink) < 10):print "do not have flac\n"continue#print "Song Source: " + songlink + "\n"songdir = "mm"#存放文件夹名称songdir_lrc = 'lrc'if not os.path.exists(songdir):#判断是否存在该文件夹os.makedirs(songdir)if not os.path.exists(songdir_lrc):#判断是否存在该文件夹os.makedirs(songdir_lrc)songname = d["data"]["songList"][0]["songName"]artistName = d["data"]["songList"][0]["artistName"]filename = "./" + songdir + "/" + songname + "-" + artistName + ".mp3"filename_lrc ="./"+songdir+"/"+songdir_lrc+"/"+ songname + "-" + artistName + ".lrc"f = urllib2.urlopen(songlink)headers = requests.head(songlink).headers#print headerssize = int(headers['Content-Length']) / (1024 ** 2)#print size#歌曲大小if not os.path.isfile(filename) or os.path.getsize(filename) < minimumsize:print "%s is downloading now ......\n" % songnamewith open(filename, "wb") as code:code.write(f.read())else:print "%s is already downloaded. Finding next song...\n\n" % songnameif  len(lrcLink) <8:print '歌词不存在'continuef_lrc = urllib2.urlopen(lrcLink)if not os.path.isfile(filename_lrc) :print "%s .lrc is downloading now ......\n" % songnamewith open(filename_lrc, "wb") as code:code.write(f_lrc.read())else:print "%s .lrc is already downloaded. Finding next song...\n\n" % songname
print "\n+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++\n"
print "finish!"
# print list

百度音乐api搜索方式：
1.搜索建议
请求地址（GET）：
参数：
format : ‘json’ （照写就可以）
word : ” （搜索关键词，支持拼音、拼音简写）
version : 2（照写）
from : 0（照写）
作用：
获取歌曲id（通过id获取歌曲信息）
获取歌曲名称
获取歌手名称
获取歌手图片（小图）
2请求地址（POST）：
参数：
songIds : ”（要获取的歌曲信息的歌曲编号。可以多个，以逗号分隔）
hq:0
type:m4a,mp3
rate:
pt:0
flag:-1
s2p:-1
prerate:-1
bwt:-1
dur:-1
bat:-1
bp:-1
pos:-1
auto:-1
获取歌曲的lrc歌词地址（歌词地址为相对路径，请加上）

知识点：
(1):requests爬取网页
r = requests.get(url)
content = r.content或contents = r.text
content获得网页内容
(2):获取标签内的无特殊标记的标签

   soup = BeautifulSoup(content,'lxml')mm=soup.find_all('span',class_='song-title')i = 0for m in  mm:mm[i] = m.contents[0]#获取span后第一个标签i+=1return mm

mm里是上图的内容，mm是ResultSet，for取出后用m.contents[]取span标签后的html标签
(3)json.loads
重要函数：
编码：把一个Python对象编码转换成Json字符串 json.dumps()
解码：把Json格式字符串解码转换成Python对象 json.loads()

另外python解析json的例子

#!/usr/bin/python
import json
#Function:Analyze json script
#Json is a script can descript data structure as xml, 
#for detail, please refer to ".html".
#Note:
#1.Also, if you write json script from python,
#you should use dump instead of load. pleaser refer to "help(json)".json file:
The file content of temp.json is:
{"name":"00_sample_case1","description":"an example."
}
f = file("temp.json");
s = json.load(f)
print s
f.close
json string:
s = json.loads('{"name":"test", "type":{"name":"seq", "parameter":["1", "2"]}}')
print s
print s.keys()
print s["name"]
print s["type"]["name"]
print s["type"]["parameter"][1]

(4)读写文件的模式

(5)with语句

 with open(filename_lrc, "wb") as code:code.write(f_lrc.read())

相当于

try:code = open(filename_lrc,'wb')
except:print 'fail to open'exit(-1)
try:code.write(f_lrc.read())
except:finally:f.close()

多个项时:

with open("filename.txt") as fn1, open('filename.txt') as fn2:do something with fn1,fn2

如：

with nested(open('file1'), open('file2'), open('file3')) as (f1,f2,f3):for i in f1:j = f2.readline()k = f3.readline()print(i,j,k)

with open('file1') as f1, open('file2') as f2, open('file3') as f3:for i in f1:j = f2.readline()k = f3.readline()print(i,j,k)

相关链接：
.html
.html
/