Python：的web爬虫实现及原理(BeautifulSoup工具)

　　最近一直在学习python，学习完了基本语法就练习了一个爬虫demo，下面总结下。

　　

　　主要逻辑是　

　　1）初始化url管理器，也就是将rooturl加入到url管理器中

　　2）在url管理器中得到新的new_url

　　3）根据新new_url得到它的内容html_cont　　(工具 urllib.request.urlopen(url))

　　4）解析这个新页面的内容html_cont并得到新的子url，并保存解析内容结果  （利用BeautifulSoup工具）

　　5）将新得到的子url保存到url管理器

　　6）迭代2-5步骤，知道输出某个阈值的数量即可停止

　　7）输出爬去的结果

　　注意编码问题，一致为UTF-8　--　　　.decode('UTF-8')

　　

BeautifulSoup工具的安装方式：进入Python3.xScript下 输入指令 pip install beautifulsoup4

主页面spider_main.py:

　　

'''
Created on 2016-3-30

@author: rongyu
'''
from bike_spider import url_manager, html_downloader, html_parser, html_outputer

  
class SpiderMain(object):
    
    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 = count + 1
            except:
                print('craw failed')

        self.outputer.output_html()
    
    

#主程序入口

if __name__=="__main__":
    root_url = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)　　　　#根据url开始爬取

url管理器页面UrlManager.py

'''
Created on 2016-3-30

@author: rongyu
'''



class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    
    def add_new_url(self,url):
        if url is None:
            return 
        if url not in self.new_urls and url not in self.old_urls:
            self.new_urls.add(url)

    
    def has_new_url(self):
        return len(self.new_urls) != 0

    
    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url
    
    def add_new_urls(self,urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(url)
    
    
    
    
    
    
    
    

下载器页面 HtmlDownloader.py

import urllib.request


class HtmlDownloader(object):
    
    
    def download(self,url):
        if url is None:
            return None
        
        response = urllib.request.urlopen(url)
        
        return response.read().decode('UTF-8')
    
    

解析器页面HtmlParser.py

from bs4 import BeautifulSoup
import re
import urllib.parse





class HtmlParser(object):
    
    
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        #/view/234.htm
        links = soup.find_all('a',href=re.compile(r"/view/d+.htm"))
        for link in links:
            new_url = link['href']
            new_full_url = urllib.parse.urljoin(page_url,new_url)
            new_urls.add(new_full_url)
        return new_urls
    
    def _get_new_data(self, page_url, soup):
        res_data = {}
        
        #url
        res_data['url'] = page_url
        
        #<dd class="lemmaWgt-lemmaTitle-title"> <h1>Python</h1>
        title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find("h1")
        res_data['title'] = title_node.get_text()
        
        #<div class="lemma-summary" label-module="lemmaSummary">
        summary_node = soup.find('div',class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()
        
        return res_data
    
    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
    

输出器的代码HtmlOutputer.py

class HtmlOutputer(object):
    def __init__(self):
        self.datas = []
    
    def collect_data(self,data):
        if data is None:
            #print("collect_data -data is none!")
            return
        
        self.datas.append(data)
        #print(self.datas)
    
    def output_html(self):
        fout = open('output.html','w')
        
        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")
        for data in self.datas:
           fout.write("<tr>")
           fout.write("<td>%s</td>"%data['url'].encode('UTF-8'))
           fout.write("<td>%s</td>"%data['title'].encode('UTF-8'))
           fout.write("<td>%s</td>"%data['summary'].encode('UTF-8'))
           fout.write("</tr>")
        fout.write("</table>")        
        fout.write("</body>")
        fout.write("</html>")
    
    
    
    

实验结果：

控制台输出