爬虫

import requests
from bs4 import BeautifulSoup
newsary=[]
for i in range(25):
    res=requests.get('http://r.qidian.com/yuepiao?chn=-1&page='+str(i))
#print(res)
    soup=BeautifulSoup(res.text,'html.parser')
#print(soup)
#for news in soup.select('.rank-view-list h4'): 

    for news in soup.select('.rank-view-list li'): 
    #print(news)
    #print(news.select('a')[1].text,news.select('a')[2].text,news.select('a')[3].text,news.select('p')[1].text,news.select('p')[2].text,news.select('a')[0]['href'])
        newsary.append({'title':news.select('a')[1].text,'name':news.select('a')[2].text,'style':news.select('a')[3].text,'describe':news.select('p')[1].text,'lastest':news.select('p')[2].text,'url':news.select('a')[0]['href']})


# print newsary

import pandas
newsdf=pandas.DataFrame(newsary)
newsdf

newsdf.to_excel('qidian_rank1.xlsx')