主要5部分：主函數，url管理器，網頁下載器，網頁輸出器，網頁解析器
（用了set，但是下面的代碼並沒有突出set的優勢。後續可改進）
主要入口函數， spider_main:
import url_manager, html_downloader, html_outputer, html_parserclass 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)#根節點入隊 while self.urls.has_new_url():#類似廣度優先搜尋 try: new_url = self.urls.get_new_url()#從隊列中得到一個新的url print 'craw %d : %s' % (count, new_url)#哪個url正在被爬取 html_cont = self.downloader.download(new_url)#把這個網頁爬下來 new_urls, new_data = self.parser.parse(new_url, html_cont)#解析內部的url和資料 self.urls.add_new_urls(new_urls)#將又爬到的url添加到隊列中 self.outputer.collect_data(new_data)#收集資料 self.outputer.output_html()#列印資料 if count == 10: break count += 1 except Exception as e: print e print 'craw failed'if __name__ == "__main__": root_url = "http://baike.baidu.com/view/21087.htm" #根節點 obj_spider = SpiderMain() obj_spider.craw(root_url)
class UrlManager(object): def __init__(self): self.new_urls = set() self.old_urls = set() def get_new_url(self): new_url = self.new_urls.pop() self.old_urls.add(new_url) return new_url def add_new_url(self, url):#添加新的url到隊列中 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):#大量新增 if urls is None or len(urls) == 0:#沒爬到或者爬到了空串 return for url in urls: self.add_new_url(url) def has_new_url(self):#判斷隊列是否為空白 return len(self.new_urls) != 0
import urllib2class HtmlDownloader(object): def download(self, url): if url is None: return None response = urllib2.urlopen(url)#開啟url，並擷取傳回值 if response.getcode() != 200: return None return response.read()#返回網頁的全部內容
網頁解析器：
import reimport urlparsefrom bs4 import BeautifulSoupclass HtmlParser(object): def _get_new_urls(self, page_url, soup):#從一堆文字中擷取url（正則匹配） new_urls = set() links = soup.find_all('a', href = re.compile(r"/view/\d+\.htm"))#擷取a標籤中，href為指定格式的標籤全部內容 for link in links: new_url = link['href']#取其中的href new_full_url = urlparse.urljoin(page_url, new_url)#拼接成完整連結 new_urls.add(new_full_url) return new_urls def _get_new_data(self, page_url, soup):#從一堆文字中擷取資料 res_data = {}#索引值對組合，title索引值對，summary索引值對 #url res_data['url'] = page_url #<dd class="lemmaWgt-lemmaTitle-title"> title_node = soup.find('dd', class_ = "lemmaWgt-lemmaTitle-title").find('h1') res_data['title'] = title_node.get_text() #print res_data['title'] #<div class="lemma-summary" label-module="lemmaSummary"> summary_node = soup.find('div', class_ = "lemma-summary") res_data['summary'] = summary_node.get_text() #print res_data['summary'] 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
網頁輸出器：
class HtmlOutputer(object): def __init__(self): self.datas = [] def collect_data(self, data):#將資料（索引值對們）組成列表 if data is None: return self.datas.append(data) def output_html(self): fout = open("F:\\output.html", 'w') fout.write("<html>") fout.write("<body>") fout.write("<table>") for data in self.datas: print data['title'] 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()
Start building with 50+ products and up to 12 months usage for Elastic Compute Service
1 on 1 presale consultation
24/7 Technical Support 6 Free Tickets per Quarter Faster Response
Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.
A comprehensive suite of global cloud computing services to power your business
Payment Methods We Support
