python实现百度百科词条的爬虫

照着慕课网上的《Python开发简单爬虫》课程跟着敲完代码，做了个爬虫。

照着敲完代码后，自己又调试了足足2个小时，爬虫才正常运行。

看着别人敲代码又快又不出错，自己敲代码一会没有引用包，一会打错字，真是知易行难啊。

代码量不大，就直接贴文章后面了。

慕课网视频网址：  http://www.imooc.com/learn/563

一共六段代码：

spider_main.py url_manager.py html_downloader.py html_parser.py html_outputer.py spider_main.py

我这边出问题最多的是html_parse.py， 不知道大家会怎么样呢？

# -*- coding: utf-8 -*-
from baike_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 == 50:
                    break
                
                count = count + 1
            except:
                print("craw failed, exit")
           
        self.outputer.output_html()


if __name__ == '__main__':
    pass
    root_url = "http://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)
    

url_manager.py

# -*- coding: utf-8 -*-

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 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

html_downloader.py

# !/usr/bin/env python
# -*- coding: utf-8 -*-
import urllib2

class HtmlDownloader(object):
    
    
    def download(self, url):
        if url is None:
            return None
        user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
        headers = {'User-Agent': user_agent}
        request = urllib2.Request(url, '', headers)
        response = urllib2.urlopen(request)
        #print(response.read())
        
        if response.getcode() != 200:
            return None
        
        return response.read()

html_parser.py

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

class HtmlParser(object):
    
    
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
        for link in links:
            new_url = link['href']
            new_full_url = urlparse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
        
        #print(new_urls)            
        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 -*-

class HtmlOutputer(object):
    def __init__(self):
        self.datas = []
    
    
    def collect_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>")
        
        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()

 

转载于:https://my.oschina.net/hongyu201/blog/791005