一个简单的Python爬虫

最新推荐文章于 2020-04-30 11:26:09 发布

ThousandWind

最新推荐文章于 2020-04-30 11:26:09 发布

阅读量3.9k

点赞数 2

分类专栏： Python 文章标签： python 爬虫

本文链接：https://blog.csdn.net/ThousandWind/article/details/51104396

版权

Python 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

　　基于慕课网的教程实现了一个简单的爬虫，这个Python爬虫可以爬取百度百科上面与Python词条相关的词条的名子和摘要信息，并保存在名为output.html的文件里。
　　爬虫一共由五个部分组成，分别是spyder_main.py、html_downloader.py、html_outputer.py、html_parser.py和url_manager.py
　　spyder_main.py：主函数,主要用于实现模块间的调度
　　html_downloader.py：用来下载url
　　html_outputer.py：用来收集爬取的数据并输出成html
　　html_parser.py：用来解析url页面
　　url_manager.py：用于管理已经下载和还没有下载的url

　　具体代码如下：

spyder_main.py

import url_manager
import html_downloader
import html_outputer
import html_parser
class SpiderMain(object):    
    count = 1
    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 ==10:
                    break

                count = count + 1
            except:
                print 'craw failed'
        self.outputer.output_html()

if __name__ == '__main__':
    root_url = 'http://baike.baidu.com/link?url=iYGd6RePOS1xkyTpV0OoSrZ96YRjaPmaxxLgEH4yQFlepo11sn5g4E0oi6cu1hihq651LtUSr9ZVjIY4ePnPla'
    //root_url是百度百科python页面的链接
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

html_downloader.py

import urllib2
class HtmlDownloader(object):
    def download(self,url):
        if url is None:
            return None
        response = urllib2.urlopen(url)

        if response.getcode()!=200:
            return None

        return response.read()

html_outputer.py

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

    def collect_data(self,data):
        if data is None:
            return
        self.datas.append(data)
        return self.datas

    def output_html(self):
        fout = open('output.html','w')
        fout.write('<html>')
        fout.write('<meta charset="utf-8">')        
        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>')

html_parser.py

from bs4 import BeautifulSoup
import re
import urlparse

class HtmlParser(object):
    def _get_new_urls(self,page_url,soup):
        new_urls = set()
        #/view/123.html
        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)
        return new_urls
    def _get_new_data(self,page_url,soup):
        res_data = {}
        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

url_manager.py

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

ThousandWind

关注

2
点赞
踩
5

收藏

觉得还不错? 一键收藏
1
评论
一个简单的Python爬虫

基于慕课网的教程实现了一个简单的爬虫，这个Python爬虫可以爬取百度百科上面与Python词条相关的词条的名子和摘要信息，并保存在名为output.html的文件里。　　爬虫一共由五个部分组成，分别是spyder_main.py、html_downloader.py、html_outputer.py、html_parser.py和url_manager.py 　　spyder_main.py
复制链接

扫一扫