python简单爬虫

 1 #! -*- coding:utf-8 -*-
 2 
 3 import requests
 4 import pyquery
 5 from pyquery import PyQuery as pq
 6 
 7 # 爬取酷我音乐排行榜
 8 headers = {
 9     ‘User-Agent‘: ‘Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0‘}  # 设置User-Agent头，绕过反爬虫机制
10 url = "http://www.kuwo.cn/bang/index"  # 爬取的地址
11 html = requests.get(url, headers=headers)  # 获取网页内容
12 a = pq(html.text)
13 b = a(‘.name‘).find(‘a‘)
14 for c in b.items():
15     print(c.html())
16 print("爬取完成！")
17 
18 
19