求帮助~~~捉急啊
我用的phtyon 3.5，自己改了一些地方，但结果出来是空白页，而且不循环，只抓到一个空白页运行结果如图：
spider_main:
import url_manager,html_downloader,html_parser,html_outputer
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)
url_manager:
class UrlManager(object):
def __init__(self):#需要维护两个列表-带爬取得url列表，爬取过的url列表
self.new_urls=set()
self.old_urls=set()
def add_new_url(self,url):#向url管理器中添加一个新的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):#向url管理器中添加批量url
if url is None or len(urls)==0:
return
for url in urls:#通过循环一个一个添加
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):#从url管理器中获取一个新的带爬取得url
new_url=self.new_urls.pop()#pop方法会从列表中获取url并会移除
self.old_urls.add(new_url)#将此url添加进old_url
return new_url
html_downloader:
import urllib
class HtmlDownloader(object):
def download(self,url):
if url is None:
return None
response=urllib.urlopen(url)#请求url内容
if response.getcode()!=200:
return None
return response.read()#返回下载好的内容
html_outputer:
class HtmlOutputer(object):
def __init__(self):#初始化构造函数，维护收集的数据存入数组
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')#输出html文件
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()
html_parser:
from bs4 import BeautifulSoup
import re
import urllib.parse
class HtmlParser(object):
def _get_new_urls(self,page_url,soup):
new_urls=set()
#/view/123.htm
links=soup.find_all('a',href=re.compile(r"/view/\d+\.htm"))#获取链接
for link in links:
new_url=link['href']#不完整的链接
new_full_url=urllib.parse.urljoin(page_url,new_url)#自动将两个不完整的链接拼成完整链接
new_url.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').find("h1")
res_data['title']=title_node.get_text()
#<div class="lemma-summary" label-module="lemmaSummary">
summary_node=soup.find('div')
res_data['summary']=summary_node.get_text()#提取数据
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
