为什么运行之后是这样的?
craw 1 : http://baike.baidu.com/view/21087.htm
craw failed
craw 1 : http://baike.baidu.com/view/21087.htm
craw failed
2016-05-14
import re
import urlparse
from bs4 import BeautifulSoup
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={}
#url
res_data['url']=page_url
#<dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
title_node=soup.find('dd',class_="lemmaWgt-lemmaTitle-title")
res_data['title']=title_node.get_text()
#<div class="lemma-summary" >
summary_node=soup.find('div',class_="lemma-summary")
res_data['summary']=title_summary.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
代码就是按照视频敲的,不知道哪错了
举报