Python简易爬虫--抓取任意数目百度百科内容

使用Python语言,编写简单的爬虫程序,在百度百科页面上爬取跟词条“Python”有关的1000个页面(页面数目可以自己任意设定)。
这个简易的爬虫项目可以分为5个模块:
首先,需要有一个程序入口spider_main,同时作为爬虫的总控程序(调度程序),
改程序需要进行初始化:
self.urls = url_manager.UrlManger()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = html_outputer.HtmlOutputer()

可以看出,这里需要url管理器,html下载器,html解析器,html分析结果输出器。其中,就程序语句

        self.urls = url_manager.UrlManger()

而言,url_manager为模块名称(module),UrlManger为模块中的类(class)。
Beautiful Soup提供一些简单的、python式的函数用来处理导航、搜索、修改分析树等功能。它是一个工具箱,通过解析文档为用户提供需要抓取的数据,因为简单,所以不需要多少代码就可以写出一个完整的应用程序。 Beautiful Soup自动将输入文档转换为Unicode编码,输出文档转换为utf-8编码。你不需要考虑编码方式,除非文档没有指定一个编码方式,这时,Beautiful Soup就不能自动识别编码方式了。然后,你仅仅需要说明一下原始编码方式就可以了。 Beautiful Soup已成为和lxml、html6lib一样出色的python解释器,为用户灵活地提供不同的解析策略或强劲的速度。

为了进行演示,程序中抓取1000个页面的内容并进行初步分析。同学们如果感兴趣,可以进行任意页面的内容抓取分析。程序具有通用性,进行简单的修改可以对于任意网页进行内容自由抓取。

下面,我们来展示五个模块的相应代码:

  • 程序入口:spider_main
#coding:utf-8
from baike_spider import html_downloader, url_manager, html_parser,\
    html_outputer


class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.UrlManger()
        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/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)
  • url管理器:url_manager
#coding:utf-8
class UrlManger(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下载器:html_downloader
#coding:utf-8
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解析器:html_parser
#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)
        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   
  • html输出器:html_outputer
#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>")

        count = 1
        for data in self.datas :     

            fout.write("<tr>")
            fout.write("<td>%d</td>" % count)
            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>")
            count = count + 1

        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")
        fout.close()

你可能感兴趣的:(python)