本文为大家分享了python爬取酷狗音乐排行榜的具体代码,供大家参考,具体内容如下
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
|
#coding=utf-8
from pymongo import MongoClient
import time
import requests
from lxml import etree
client = MongoClient() #连接mongo
hello = client.hello #连接数据库
user = hello.song #连接表
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()' )
#保存到本地
# with open('aa.txt','a') as f:
# for i in soup:
# f.write(i.encode('utf-8') + '\n')
#存入数据库
for i in soup:
user.insert({ 'song' : i})
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)
|
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持服务器之家。
原文链接:https://blog.csdn.net/qq_18525247/article/details/80238425