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) if count == 100: break count = count + 1 except: print 'craw failed' self.outputer.out_html() if __name__=="__main__": root_url = "http://baike.baidu.com/link?url=Ak2ZeZ5dQxpl3iq7SFtqYNsp6L-QSKgg7tWodHFgJ0lViVE59bpDoX054BZza0R-vgS6gih9QygDM0GMLbz97_" obj_spider = SpiderMain() obj_spider.craw(root_url) print "finish!!!!" 3.创建url管理器模块： #coding:utf8 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 == 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_url4.创建url下载器模块： #coding:utf8 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() 5.创建url解析器模块： #coding:utf8 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('/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 = {} #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 def parse(self,page_url,html_data): if page_url is None or html_data is None: return soup = BeautifulSoup(html_data,'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 6.创建url打印输出模块： #coding:utf8 class HtmlOutputer(object): def __init__(self): self.datas = [] def collect_data(self,data): if data is None: return self.datas.append(data) def out_html(self): fout = open('output.html','w') fout.write("<html>") fout.write(r'<head><meta charset="utf-8"></head>') 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()