#coding:utf8
from test import html_downloader
from test import html_outputer
from test import html_parser
from test 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 #记录当前爬取得是第几个url
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/item/Python"
#root_url="http://baike.baidu.com/view/21087.htm"
obj_spider=SpiderMain()
obj_spider.craw(root_url)
下载器
#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()
解释器：
#coding:utf8
import re
import urlparse
from bs4 import BeautifulSoup
class HtmlParser(object):
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
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={}
#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管理器：
#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)
# 批量添加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 get_new_url(self):
new_url=self.new_urls.pop()
self.old.urls.add(new_url)
return new_url
def has_new_url(self):
return len(self.new_urls)!=0
输出器：
#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 output_html(self):
fout=open('output.html','w')
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>")
