count = count + 1 为什么会报错？？？
#coding=utf-8
import urllib2
import re
import urlparse
from bs4 import BeautifulSoup
class SpiderMain(object):
def __init__(self): #初始化对象
self.urls = url_manager.UrlManager() #管理器
self.downloader = html_downloader.HtmlDownloader() #下载器
self.parser = html_parser.HtmlParser() #解析器
self.outputer = html_outputer.HtmlOutputer() #输出器
def craw(self,root_url): #如果有待爬取的url
count = 1 #记录当前爬取的是第几个url
self.urls.add_new_url(root_url) #取一个出来
while self.urls.has_new_url(): #循环遍历
try:
new_url = self.urls.get_new_url() #得到链接
print 'craw %d : %s'%(count,new_url)
html_cont = self.downloader.download(new_url) #下载对应的页面
new_urls,new_data = self.parser.parse(new_url,html_cont)#解析
self.urls.add_new_urls(new_urls) #将新的url补充进url管理器
self.outputer.collect_data(new_data) #进行数据的升级并输出
if count == 1000:
break
count = count + 1
except:
print 'craw failed'
self.outputer.output_html()
class UrlManager(object):
def __init__(self):
self.new_urls = set()
self.old_urls = set()
def add_new_url(self,url): #向管理器添加新的url
if url is None: #如果url等于空
return #不进行添加
if url not in self.new_urls and url not in self.old_urls:
#这个url既不在待爬取的urls里也不再爬取过的url里表里
self.new_urls.add(url) #添加到待爬取的列表里
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: #若列表为空
return #不进行添加
for url in urls:
self.add_new_url(url) #进行单个添加
def has_new_url(self): #判断管理器中有新的待爬取的url
return len(self.new_urls) != 0 #如果urls长度不为0的话说明有待爬取url
def get_new_url(self): #从管理器中获取新的待爬取的url
new_url = self.new_urls.pop() #获取一个url
#pop:会从列表中获取一个url并且会移除这个url
self.old_urls.add(new_url) #将这个url添加进oldurl
return new_url #将这个url返回
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()
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
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>")
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()
if __name__=="__main__":
root_url = "http://baike.baidu.com/view/21087.htm" #入口url
obj_spider = SpiderMain()
obj_spider.craw(root_url) #启动爬虫
