爬虫----python2.7

用python2.7爬取网易云音乐

想根据歌手爬取 ··但是网易云的那个官网··有一块歌手的链接没找到url在哪写的··  截取的包也看了  但是 还是没找到 可能是学艺不精吧  

所以我就选择了一个笨办法  

#-*-encoding:utf-8-*-
import sys
import urllib2
import bs4
import requests
import json
import urllib
reload(sys)
sys.setdefaultencoding('utf-8')

def url_demo():
    url = 'http://music.163.com/artist/album?id='
    urls =[]
    i = range(4000,4010)
    for n in i:
        nurl = url+str(n)
        urls.append(nurl)
    return urls
'''
歌曲专辑
'''
def find_gequ():
    urls = url_demo()
    songs_url = []
    for url in urls:
        try:
            html = get_html(url)
            soup = bs4.BeautifulSoup(html,'html.parser')
            text_urls=[]
            for i in soup.select('div.g-wrap6 > ul > li > p > a'):
                text_urls.append('http://music.163.com'+i['href'])

        except:
            urls.remove(url)
        if len(text_urls) != 0:
            songs_url.append(text_urls)
    return songs_url

'''
每个歌单的内容
'''
def get_gequ():
    urls =  find_gequ()
    for i in urls:
        song = []
        for url in i:
            html = get_html(url)
            soup = bs4.BeautifulSoup(html,'html.parser')
            text = soup.select('textarea')[0].get_text()
            content = json.loads(text)
            for n in content:
                song .append([n['name'],n['artists'][0]['name']])
        print i
        print '正在写入'+url+'-'*20
        write_xml(content[0]['artists'][0]['name'],i,song)

def write_xml(name,url,content):
    w_name = name+'.xml'
    f = open('E:\demo\\'+w_name,'wb')
    f.write('<doc>\n')
    f.write('\t<url>')
    for i in url:
        f.write(i+' , ')
    f.write('\t</url>\n')
    for i in content:
        f.write('\t\t<song_name>%s</song_name>\n'%i[0])
        f.write('\t\t<songer_name>%s</songer_name>\n'%i[1])
    f.write('</doc>\n')

def get_html(url):
    html = urllib2.urlopen(url).read().decode('utf-8')
    return html


if __name__ == '__main__':
    get_gequ()

感觉比第一次写的时候 可阅读性强了一丢丢 吧  ~QwQ   自我感觉还好  用bs4 爬取的

当然 我是要拿到歌单而已 不是歌曲