只输出了两条内容，但去掉try并没有报错。。。要哭了，请各位大神帮忙看看！
（1）spider_main
#coding:utf8
import sys
reload(sys)
sys.setdefaultencoding('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)
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 has_new_url(self):
return len(self.new_urls) != 0
def get_new_url(self):
#pop方法会抽取并移除一个url
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
（2）html_downloader
#coding:utf8
import urllib2
import sys
reload(sys)
sys.setdefaultencoding('utf8')
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()
（3）html_parser
#coding:utf8
from bs4 import BeautifulSoup
import re
import urlparse
import sys
reload(sys)
sys.setdefaultencoding('utf8')
class HtmlParser(object):
def _get_new_urls(self, page_url, soup):
new_urls = set()
#/item/%E6%95%99%E5%AD%A6 https://baike.baidu.com/item/%E6%95%99%E5%AD%A6
links = soup.find_all('a', href = re.compile(r"/item/."))
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):
#将数据提出用res_data
res_data = {}
#把url放进最终数据中
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
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
（4）html_outputer
#coding:utf8
import sys
reload(sys)
sys.setdefaultencoding('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>")
#Python默认编码是ascii，所以如需输出utf-8需做处理.encode('utf-8')
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()
（5）url_manager
#coding:utf8
import sys
reload(sys)
sys.setdefaultencoding('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)
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 has_new_url(self):
return len(self.new_urls) != 0
def get_new_url(self):
#pop方法会抽取并移除一个url
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
