Python爬虫爬取百度百科词条

在慕课网上的课程，我将他的代码在我电脑上进行了实现

慕课网相关链接：http://www.imooc.com/learn/563

GitHub代码：https://github.com/DongChengrong/imooc

目标：爬取百度百科上的1000条词条，将爬取的词条url地址输出，将词条的相关信息（url、标题、概述）写入一个叫output.htm的文件

 

首先打开eclipse，建立一个PyDev的项目，在该项目的src目录下新建一个叫做baike_spider的包，这个包下新建5个Python文件，分别是用于启动的spider_main.py、html下载器html_downloader.py、用于解析HTML文件的html_parser.py、用于url管理的url_manager.py、用于向output.html中写信息的html_outputer.py

 

下面我将分别给出五个文件的内容

 

spider_main.py

 

#coding:utf-8

from baike_spider import url_manager,html_downloader,html_outputer,html_parser

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 == 1000):
                    break;
                
                count = count + 1 
            except Exception,e:
                print e
                print "craw failed"
            
        self.outputer.output_html()

if __name__ == '__main__':
    root_url = 'https://baike.baidu.com/item/Python/407313'
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

html_downloader.py

 

 

#coding:utf-8
import urllib2

class HtmlDownloader():
    
    def download(self, url):
        if url is None:
            return None
        
        response = urllib2.urlopen(url)
        
        if response.getcode() != 200:
            return None
        
        return response.read()

html_parser.py

 

 

#coding:utf-8
import re
from bs4 import BeautifulSoup
import urlparse


class HtmlParser():
    
    def _get_new_urls(self,page_url,soup):
        
        new_urls = set()
        links = soup.find_all('a',href = re.compile(r"/item/"))
        for link in links:
            new_url = link['href']
            new_full_url = urlparse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
            
        return new_urls
    
    def _get_new_data(self,page_url,soup):
        
        res_data = {}
        res_data['url'] = page_url
        
        #

        title_node = soup.find('dd', class_ = "lemmaWgt-lemmaTitle-title").find("h1")
        res_data['title'] = title_node.get_text()
        #

        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

html_outputer.py

 

 

#coding:utf-8
import sys
from doctest import _SpoofOut
from idlelib.IOBinding import encoding

class HtmlOutputer():
    
    def __init__(self):
        self.datas = []   
    
    def collect_data(self,data):
        if data is None:
            return
        self.datas.append(data)
        
    def output_html(self):
        with open("output.html",'w') as fout:
            
            fout.write("")
            fout.write("")
            fout.write("")
            
            for data in self.datas:
                
                fout.write("")
                fout.write("" % data['title']).encode("utf-8"))
                fout.write(("" % data['summary']).encode('utf-8'))
                fout.write("")
            
            fout.write("
" % data['url'])
                fout.write(("%s
%s
")
            fout.write("")
            fout.write("")
        
            fout.close()

url_manager.py

 

 

#coding:utf-8

class UrlManager():
    
    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 add_new_urls(self,urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(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

 

 

好了，就这些，祝福同学们一起成功的爬取词条

 

附上我运行成功后生成的output.html截图