Python爬取百度百科1000个页面

###爬虫架构动态工作流程

• 调度器去问url管理器有没有待爬取的url，返回是或否给调度器，如果是的话，调度器从url管理器中取出一个待爬取的url，url管理器将这个url返回给调度器。
• 现在调度器得到了这个url，调度器将url传送给下载器下载内容，下载好之后将url内容返回给调度器。
• 调度器将url的内容传送给解析器进行网页解析。解析之后返回有价值的数据和新的url列表。
• 一方面调度器将价值数据传送给应用进行数据收集，另一方面将新的url列表补充到url管理器。
• 如果url管理器还有新的待爬url，就将其循环。
• 等到url管理器没有待爬的url，将其价值数据发到应用上。

#!/usr/bin/python
# coding=utf-8

#from baike_spider import url_manager,html_downloader,html_parser,html_outputer
import url_manager,html_downloader,html_parser,html_outputer

class SpiderMain(object):
    """docstring for SpiderMain"""
    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)
        #如果管理器中有url, 下载，解析，把解析出的url放入 管理器，有用内容放入 收集器
        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.parser(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:
                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)

#!/usr/bin/python
# coding=utf-8

class UrlManager(object):
    """docstring for 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):
        #pop, 从set中拿一个并移除
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

#!/usr/bin/python
# coding=utf-8

import urllib2

class HtmlDownloader(object):
    """docstring for HtmlDownloader"""
    def __init__(self):
        pass

    def download(self, url):
        if url is None:
            return None

        response = urllib2.urlopen(url)
        #print response.getcode()

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

        return response.read()

#!/usr/bin/python
# coding=utf-8

from bs4 import BeautifulSoup
import re
import urlparse

class HtmlParser(object):
    """docstring for HtmlParser"""
    def __init__(self):
        pass

    def parser(self, page_url, html_cont):
        #print page_url
        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

    def _get_new_urls(self, page_url, soup):
        # /view/数字.htm
        # such as /view/123.htm
        new_urls = set()
        links = soup.find_all('a', href = re.compile(r"/view/\d+\.htm"))
        for link in links:
            new_url = link['href']
            #print new_url
            #安装page_url 的格式，把new_url补全
            new_full_url = urlparse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
            #print new_full_url
        return new_urls

    def _get_new_data(self, page_url, soup):
        res_data = {}   #字典

        # 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" label-module="lemmaSummary">
        summary_node = soup.find('div', class_= "lemma-summary")
        res_data['summary'] = summary_node.get_text()

        return res_data

#!/usr/bin/python
# coding=utf-8

class HtmlOutputer(object):
    """docstring for HtmlOutputer"""
    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>")

        # python 默认 ascii
        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()