# coding:utf8
from taigong import url_manager,html_downloader, html_parser, html_outputer
class SpiderMain(object):
#在构造函数中对象进行初始化
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = html_outputer.HtmlOutputer()
#爬虫的总调度程序
def craw(self,root_url):
count = 1 #记录当前爬取的时第几个url
self.urls.add_new_url(root_url)#将入口url添加进url管理器中
while self.urls.has_new_urls():#当存在可爬取的url时
try:
new_url = self.urls.get_new_url()#获取有待爬取的url
print 'craw %d:%s'%(count,new_url)
#启动下载器
html_cont = self.downloader.doanload(new_url)#下载好的页面存储下来
#调用解析器解析
new_urls,new_data = self.parser.parse(new_url,html_cont)
self.urls.add_new_urls(new_urls)
#收集数据
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://jwc.tit.edu.cn/"
obj_spider = SpiderMain()
obj_spider.craw(root_url) #启动爬虫
# coding:utf8
class UrlManager(object):#需要两个列表，待爬取的url和已经爬取过得url
def __init__(self):
self.new_urls = set()
self.old_urls = set()
def add_new_url(self,url):#向管理器中添加新的url
if url is None:
return
if url not in self.new_urls and url not in self.old_urls:#如果这个url既不在待爬取中也不在爬取过的
self.new_urls.add(url) #将其添加在待爬取中
def add_new_urls(self,urls):#向管理器中添加批量的url
if urls is None or len(urls) == 0:
return
for url in urls:
self.add_new_url(url)
def has_new_url(self):#判断管理器中是否有新的待爬取的url
return len(self.new_urls) != 0
def get_new_url(self):#获取新的待爬取的url
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
# coding:utf8
'''
Created on 2016年5月8日
@author: de
'''
import urllib2
class HtmlDownloader(object):
def doanload(self,url):
if url is None:
return None
response = urllib2.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
# coding:utf8
'''
Created on 2016年5月8日
@author: de
'''
from bs4 import BeautifulSoup
import re
import urlparse
class HtmlParser(object):
def _get_new_urls(self, page_url, soup):
new_urls = set()#将结果new_full_url存到新的列表里
#获取到所有的连接/info/view/content/123.htm
links = soup.find_all('a',href=re.compile(r"/view/\d+\.htm"))
for link in links:
new_url = link['href']
#将不完整的新的url按照page_url的格式拼接成相对应的完整的url
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):#解析数据
res_data = {}#存放数据
#url
res_data['url'] = page_url
#<td class="titlestyle1129870260_54099" align="center">
#关于组织2016年院级教学改革研究项目立项答辩的通知
#</td>
title_node = soup.find('td',class_="titlestyle1129870260_54099").find("tr")
res_data['title'] = title_node.get_text()
#<div id="vsb_content">
summary_node = soup.find('div',class_="vsb_content")
res_data['summary'] = summary_node.get_text()
return res_data
def parse(self,page_url,html_cont):#参数是新的url列表和数据
#首先进行参数判断
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
# coding:utf8
class HtmlOutputer(object):
#需要一个列表维护收集的数据
def __init__(self):
self.datas = []
def collect_data(self,data):
if data is None:
return
self.datas.append(data)
def output_html(self):
#建立文件的输出对象
fout = open('output.html','w')#w表示写模式
fout.write("<HTML>")
fout.write("<BODY>")
fout.write("<TABLE>")
#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()怪盗饭团