Python+MongoDB 爬取百度词条

本文是根据慕课网的内容的学习与总结：http://www.imooc.com/learn/563

程序采用的开发环境如下：
MongoDB版本：mongodb-3.4.1
Python版本：2.7
集成IDE：Pycharm
思维导图：ImindMap 9
先看一下数据库中的已经爬取（132条）的内容（词条链接，简介，标题）：

1、设计思路：
爬虫的一般步骤：确定要爬取的内容，分析网页结构，下载网页，解析网页，保存数据
本程序：主要分为以下几个模块
（1）URL管理器、（2）网页下载器、（3）网页解析器、（4）保存数据

2、编码：
（1）URL管理器：有两个set集合，set1保存尚未被下载解析的url，set2保存已被下载解析的url。每次从set1中取出url，进行下载解析，同时将新解析出来的url存入set1。

注：用set是避免爬虫的重复爬取
url_manager.py

#coding:utf-8'''date: 2017-8-12description:Url管理类'''class UrlManager(object):    def __init__(self):        self.new_urls = set()        self.old_urls = set()    # 添加新的URL    def add_new_url(self, new_url):        if new_url is None:            return        if new_url not in self.new_urls and new_url not in self.old_urls:            self.new_urls.add(new_url)    # 添加多个Url    def add_new_urls(self, new_urls):        if new_urls is None or len(new_urls) == 0:            return        for url in new_urls:            self.add_new_url(url)    # 判断新Url集合是否为空    def has_new_url(self):        return len(self.new_urls) != 0    # 获取URL    def get_new_url(self):        new_url = self.new_urls.pop()        self.old_urls.add(new_url)        return  new_url

（2）.网页下载器：
这个比较简单，从URL管理器读取新的URL，进行下载即可，采用python2.7的内置库：urllib2
html_downloader.py

#coding:utf-8'''date:2017-8-12description: 网页下载器'''import urllib2class HtmlDownLoader(object):    def download(self, new_url):        if new_url is None:            return None        response = urllib2.urlopen(new_url)        if response.getcode() != 200:            return None        return response.read()

（3）Url解析器：采用第三方库beautifulsoup4，
html_parser.py

#coding:utf-8'''date:2017-8-12description: 网页解析类。采用BeautifulSoup进行解析'''import urlparsefrom bs4 import BeautifulSoupimport reclass HtmlParser(object):    # 爬取本词条网页的所有相关连接URL    def get_new_urls(self, page_url, soup):        new_urls = set()        links = soup.find_all('a',href=re.compile(r'/item/.+[0-9]'))        for link in links:            new_url = link['href']            new_full_url = urlparse.urljoin(page_url,new_url)            new_urls.add(new_full_url)            # print link        return new_urls    # 根据标签获取要爬取的数据    def get_new_data(self, page_url, soup):        res_data = {}        #url        res_data['url'] = page_url        # class ="lemmaWgt-lemmaTitle-title" >        title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find('h1')        res_data['title'] = title_node.get_text()        # class ="lemma-summary" label-module="lemmaSummary" >        summary_node = soup.find('div',class_="lemma-summary")        res_data['summary'] = summary_node.get_text()        return res_data    # 解析网页    def parse(self, page_url, html_cont):        if page_url is None or html_cont is None:            return        soup = BeautifulSoup(html_cont,'html.parser', from_encoding='utf-8')        new_urls = self.get_new_urls(page_url,soup)        new_data = self.get_new_data(page_url,soup)        return new_urls,new_data

（4）存入数据库：数据库采用MongoDB，编码时需要安装pymongo
html_outputer.py

#coding:utf-8'''date: 2017-8-12description:Url管理类'''import  pymongoclass HtmlOutputer(object):    # 获取MongoDB的数据库连接    def getConnect(self):        connection = pymongo.MongoClient()        BaiduItem = connection.BaiduItem        BaiduItemConnection = BaiduItem.bitems        return BaiduItemConnection    def collect_data(self, data):        if data is None:            return        self.getConnect().insert_one(data)

（5）程序入口：spider_main.py

#coding:utf-8'''date: 2017-8-12description:Url管理类'''import html_downloader,html_parser,html_outputer,url_managerclass SpiderMain(object):    #初始化构造器    def __init__(self):        self.urls = url_manager.UrlManager()        self.downloader = html_downloader.HtmlDownLoader()        self.parser = html_parser.HtmlParser()        self.outputer = html_outputer.HtmlOutputer()    def craw(self, root_url):        count = 1        self.urls.add_new_url(root_url)        while self.urls.has_new_url():            try:                new_url = self.urls.get_new_url()                print 'craw %d : %s' % (count, new_url)                html_cont = self.downloader.download(new_url)                new_urls, new_data = self.parser.parse(new_url, html_cont)                self.urls.add_new_urls(new_urls)                self.outputer.collect_data(new_data)                if count == 100:                    break                count += 1            except:                print 'crawed failed'        # self.outputer.saveInfo()if __name__ == '__main__':    root_url = "https://baike.baidu.com/view/21087.html"    obj_spider = SpiderMain()    obj_spider.craw(root_url)