spider_main.py程序代码如下：
#coding:utf8
import urllib2
import urllib.request
from bs4 import BeautifulSoup # 很好用的解析器
import re # 很容易遗漏，即使漏掉程序也不报错，很隐蔽
from baike_spider import url_manager,html_downloader,html_parser,html_outputer
class SpiderMain(object):
def __init__(self):#初始化各个对象
self.urls=url_manager.UrlManager()
self.downloader=html_downloader.HtmlDownloader()
self.parser=html_parser.HtmlParser()#解析器
self.outputer=html_outputer.HtmlOutputer()
def craw(self,root_url):#爬虫的调用程序
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==100:
break
count += 1
except:
print ('crawl failed')
self.outputer.output_html()
if __name__=="__main__": # 初始化程序
root_url="http://baike.baidu.com/view/21087.htm"
obj_spider=SpiderMain()
obj_spider.craw(root_url)
url_manager.py代码如下：
#coding:utf8
import urllib2
import urllib.request
from bs4 import BeautifulSoup # 很好用的解析器
import re # 很容易遗漏，即使漏掉程序也不报错，很隐蔽
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)
# 判断是否还有没有爬取的url，返回bool值
def has_new_url(self):
return len(self.new_urls)!=0
def get_new_url(self):
new_url=self.new_urls.pop()# pop用的极好，不仅取得了数据，而且将元素从set()中删除
self.old_urls.add(new_url)
return new_url
