在以上兩篇文章中已經介紹到了 Python 爬蟲和 MongoDB ， 那么下面我就將爬蟲爬下來的數據存到 MongoDB 中去，首先來介紹一下我們將要爬取的網站, readfree 網站，這個網站非常的好，我們只需要每天簽到就可以免費下載三本書，良心網站，下面我就將該網站上的每日推薦書籍爬下來。

利用上面幾篇文章介紹的方法，我們很容易的就可以在網頁的源代碼中尋找到書籍的姓名和書籍作者的信息。

找到之后我們復制 XPath ，然后進行提取即可。源代碼如下所示

# coding=utf-8

import re
import requests
from lxml import etree
import pymongo
import sys

reload(sys)
sys.setdefaultencoding('utf-8')

def getpages(url, total):
  nowpage = int(re.search('(d+)', url, re.S).group(1))
  urls = []

  for i in range(nowpage, total + 1):
    link = re.sub('(d+)', '%s' % i, url, re.S)
    urls.append(link)

  return urls

def spider(url):
  html = requests.get(url)

  selector = etree.HTML(html.text)

  book_name = selector.xpath('//*[@id="container"]/ul/li//div/div[2]/a/text()')
  book_author = selector.xpath('//*[@id="container"]/ul/li//div/div[2]/div/a/text()')

  saveinfo(book_name, book_author)

def saveinfo(book_name, book_author):
  connection = pymongo.MongoClient()
  BookDB = connection.BookDB
  BookTable = BookDB.books

  length = len(book_name)

  for i in range(0, length):
    books = {}
    books['name'] = str(book_name[i]).replace('n','')
    books['author'] = str(book_author[i]).replace('n','')
    BookTable.insert_one(books)

if __name__ == '__main__':
  url = 'http://readfree.me/shuffle/?page=1'
  urls = getpages(url,3)

  for each in urls:
    spider(each)