import requests
from bs4 import BeautifulSoup
from time import sleep
import pymongo
#連接數(shù)據(jù)庫
client = pymongo.MongoClient(‘localhost',27017)
mydb = client[‘yourdb']
#創(chuàng)建數(shù)據(jù)庫
musicTop = mydb[‘musicTop']

#使用header是用于偽裝為瀏覽器，讓爬蟲更穩(wěn)定
Headers = {
‘User-Agent': ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'
}
#定義獲取信息的函數(shù)
def get_info(url):
wd_data = requests.get(url,headers=Headers)
soup = BeautifulSoup(wd_data.text,‘lxml')
#獲取排名情況
ranks = soup.select(‘span.pc_temp_num')
#獲取標題
titles = soup.select(‘div.pc_temp_songlist > ul > li > a')
#獲取時間
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(),
‘song':title.get_text(),
‘time':time.get_text().strip()
}
musicTop.insert_one(data) #存入數(shù)據(jù)庫中
if name == ‘main':
urls = [‘http://www.kugou.com/yy/rank/home/{}-8888.html'.format(number) for number in range(1,24)]
for url in urls:
get_info(url)
sleep(2)