Python 爬取百度词条Python Demo

Python  爬取百度Python词条

1.main.py(运行)

# -*- coding: utf-8 -*- 
from baiKe_spider import url_manager, html_downloader, html_parser,html_outputer
 
#初始化需要的对象
class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.UrlManager()             #url管理器
        self.downloader =  html_downloader.HtmlDownloader()   #下载器         
        self.parser = html_parser.HtmlParser()              #html解析器
        self.outputer = html_outputer.HtmlOutputer()            #html输出器        
    #爬出的调度程序
    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()        #获取新的url
                print 'craw %d:%s' % (count,new_url)
                html_cont =  self.downloader.dowmload(new_url)                      #启动下载器下载页面
                new_urls,new_data = self.parser.parse(new_url,html_cont)           #解析器
                self.urls.add_new_urls(new_urls)
                self.outputer.cllect_data(new_data)
                #获取1000个之后跳出循环
                if count == 1000:
                    break
                count = count+1
            except:
                print 'craw failed'
        self.outputer.output_html()


if __name__ == "__main__":
    root_url = "https://baike.baidu.com/item/Python"      #入口的url(根据要爬取的地址)
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)                             #启动爬虫

2.url_manager.py(URL管理器)

# -*- coding: utf-8 -*- 
class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    
    #向管理器里添加一个新url
    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)
    
    #向管理器里批量添加多个新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)
    
    #判断管理器中是否有新的待爬取的url
    def has_new_url(self):
        return len(self.new_urls)  != 0


    #获取一个待爬去的url
    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url
3.html_parser.py(html解析器)

# -*- coding: utf-8 -*- 
import urlparse
from bs4 import BeautifulSoup
import re
import urllib
class HtmlParser(object):  
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        #/item/*
        links = soup.find_all('a',href = re.compile(r"^/item/"))#根据网站的格式变化
        for link in links:
            new_url = link['href']  
            
#             new_url.split("/")        
            new_full_url = urlparse.urljoin(page_url, new_url)
#             new_url1 = urllib.unquote(so).decode('gbk').encode('utf-8')
            new_urls.add(new_full_url)
        return new_urls        
   
    def _get_new_data(self, page_url, soup):
        #声明一个字典
        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">
        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

4.html_outputer.py(html输出器)

# -*- coding: utf-8 -*- 
class HtmlOutputer(object):
    def __init__(self):
        self.datas = []    
    def cllect_data(self,data):
        if data is None:
            return
        self.datas.append(data)
    
    def output_html(self):
        fout = open('output.html','w')
        fout.write("<html>")
        fout.write("<body>")
        fout.write("table")
        #ascil  默认编码 
        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>"%data['url'])
            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>")
        fout.close()

5.html_downloader.py(html下载器)

# -*- coding: utf-8 -*- 
import urllib2
class HtmlDownloader(object):
    
    
    def dowmload(self,url):
        if url is None:
            return None
        response = urllib2.urlopen(url)
        if response.getcode() != 200:
            return None
        return response.read()