import requests                     #用于请求网页获取网页数据

from bs4 import BeautifulSoup       #解析网页数据

import time                         #time库中的sleep()方法可以让程序暂停

import csv

'''

爬虫测试

酷狗top500数据

写入csv文件

'''

fp = open('D://kugou.csv','wt',newline='',encoding='utf-8')#创建csv

writer = csv.writer(fp)

writer.writerow(('rank','singer','song','time'))

#加入请求头

headers = {

    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'

}

#定义获取信息的函数

def get_info(url):

    wb_data = requests.get(url,headers=headers)#get方法加入请求头

    soup = BeautifulSoup(wb_data.text,'html.parser')#对返回结果进行解析

    #定位元素位置并通过selector方法获取

    ranks = soup.select('span.pc_temp_num')

    titles = soup.select('div.pc_temp_songlist > ul > li > a')

    times = soup.select('span.pc_temp_tips_r > span')

    for rank,title,time in zip(ranks,titles,times):

        data = {

            'rank':rank.get_text().strip(),

            'singer':title.get_text().split('-')[0],

            'song':title.get_text().split('-')[0],#通过split获取歌手和歌曲信息

            'time':time.get_text().strip()#get_text()获取文本内容

        }

        writer.writerow((rank.get_text().strip(),title.get_text().split('-')[0],title.get_text().split('-')[0],time.get_text().strip()))

        # 获取爬取信息并按字典格式打印

        #print(data)

#程序主入口

if __name__ == '__main__':

    urls = ['http://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(1,4)]#构造多页url

    for url in urls:

        get_info(url)#循环调用

        time.sleep(1)#每循环一次，睡眠1秒,防止网页浏览频率过快导致爬虫失败