python爬虫 爬取酷狗音乐排行榜

#coding=utf-8

观察url,直接生成列表式爬取

import time
import requests
from lxml import etree

headers = {
    'User-Agent': 'Mozilla/5.0 (Android 6.0; Nexus 5 Build/MRA58N)\
     AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Mobile Safari/537.36'}


def get_info(url):
    '''
    get源码,encode,解析,xpath,保存
    '''
    response = requests.get(url, headers=headers)
    response = response.text.encode('utf-8')
    selector = etree.HTML(response)
    soup = selector.xpath('//*[@class="pc_temp_songlist "]/ul//li/a/text()')

    with open('aa.txt','a') as f:
        for i in soup:
            f.write(i.encode('utf-8') + '\n')


if __name__ == '__main__':
    urls = ['http://www.kugou.com/yy/rank/home/{}-8888.html?from=rank'.format(str(i)) for i in range(1, 24)]
    for url in urls:
        print(url)
        get_info(url)