python开发爬虫实例代码

1.创建baike_spider包

2.创建调度模块：

#coding:utf8

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)
                new_cont = self.downloader.download(new_url)
                new_urls,new_data = self.parser.parse(new_url,new_cont)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)