-*- coding: utf-8 -*-
"""
Spyder Editor
This is a temporary script file.
"""
import urllib2
from bs4 import BeautifulSoup
import re
import urlparse
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):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
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'/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):
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").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
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()
爬虫总调度程序
class SpiderMain(object):
# 构造函数初始化url管理器、HTML下载器、HTML解析器、输出四个对象
def init(self):
# url管理器
self.urls = UrlManager()
# url下载器
self.downloader = HtmlDownloader()
# url解析器
self.parser = HtmlParser()
# 最终的输出
self.outputer = HtmlOutputer()
# 爬虫调度程序
def craw(self, root_url):
count = 1
# 添加入口URL
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
try:
# 取出新的URL
new_url = self.urls.get_new_url()
# 下载该url对应的页面
print("craw %d : %s" % (count, new_url))
html_cont = self.downloader.download(new_url)
# 解析该url对应的页面，得到新的链接和内容
new_urls, new_data = self.parser.parse(new_url, html_cont)
# 将新url添加到url管理器中
self.urls.add_new_urls(new_urls)
# 将解析到的内容收集起来
self.outputer.collect_data(new_data)
if count == 1000: # 爬取1000个页面即可
break
count = count + 1
except:
print("craw fail")
# 最终输出爬取目标的内容
self.outputer.output_html()
主函数启动爬虫
if name=="__main__":
# root_url = "http://baike.baidu.com/item/Python/407313?fr=aladdin"
root_url = "http://baike.baidu.com/item/Python/407313?fr=aladdin"
obj_Spider = SpiderMain()
obj_Spider.craw(root_url)
提示runfile('C:/Users/sun/.spyder/temp.py', wdir='C:/Users/sun/.spyder') craw 1 : http://baike.baidu.com/item/Python/407313?fr=aladdin craw fail
