简单爬取Library genesis 免费文献下载网

Library genesis 免费文献下载网（列表简单）

import requests.
import pandas as p
from bs4 import BeautifulSoup as bs

def spider(url):
    req=requests.get(url)
    req.encoding='utf-8'
    return bs (req.text,'html.parser')

def pandaWork(lis1,lis2,lis3):
    data=p.DataFrame({'ID':lis1,'作者':lis2,'书名':lis3})
    w=p.ExcelWriter('Lg图书馆.xlsx')
    data.to_excel(w,'Lg图书馆')
    w.save()

lis1=[]
lis2=[]
lis3=[]

for i in range(5):
    url='http://gen.lib.rus.ec/search.php?&req=the+critique+of+pure+reason&phrase=1&view=simple&column=def&sort=def&sortmode=ASC&page=%d'%(i+1)
    pbj=spider(url)
    for i in pbj.find_all('tr',valign="top",bgcolor="#C6DEFF"):
        lis1.append(i.find_all('td')[0].text)
        lis2.append(i.find_all('td')[1].find('a').text)
        lis3.append(i.find_all('td')[2].find('a').text)
pandaWork(lis1,lis2,lis3)