简介
爬虫是一段自动抓取互联网信息的程序。它的价值是互联网数据为我所有。利用爬取到的数据,可以做很多的事情如:可以进行数据统计,对比;可以利用爬取的数据做某一方面的app;也可以利用爬取的数据做一个新闻阅读器等等。
爬虫架构
1)URL管理器
2)网页下载器
3)网页分析器
4)爬虫调用器
5)价值数据使用
爬虫实现
1)调度器实现
# coding:utf-8 import url_manager import html_downloader import html_parser import html_outputer import url_manager 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) 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 == 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)
2)URL管理器实现
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 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
3)URL下载器实现
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()
4)URL解析器实现
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 title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find("h1") res_data['title'] = title_node.get_text() 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
5)价值数据输出显示
# 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("<meta charset=\"UTF-8\">") 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()
执行
本爬虫为爬取百度百科与Python关键字相关的1000个静态网页,对网页中的数据,主要提取关键词和摘要信息,并将爬取的信息以HTML文件的方式存储,之后利用浏览器打开即可实现访问。