python实现爬虫数据存到 MongoDB

在以上两篇文章中已经介绍到了 Python 爬虫和 MongoDB ， 那么下面我就将爬虫爬下来的数据存到 MongoDB 中去，首先来介绍一下我们将要爬取的网站, readfree 网站，这个网站非常的好，我们只需要每天签到就可以免费下载三本书，良心网站，下面我就将该网站上的每日推荐书籍爬下来。

利用上面几篇文章介绍的方法，我们很容易的就可以在网页的源代码中寻找到书籍的姓名和书籍作者的信息。

找到之后我们复制 XPath ，然后进行提取即可。源代码如下所示

# 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)