说明：支持中文 # coding=gbk
创建项目：File->New->Project->PyDev->PyDev Project
新建项目名称：任意。新建package名称:wangyepachong
创建5个Module文件：
在项目中用到的所有模块，都需要在eclipse中添加：windows->preferences->PyDev->Interpreters->Python Interpreter 找到Forced Builtins 中添加需要导入的模块：
比如：bs4 urllib2 re 等
html_dowanloader.py
html_outputer.py
html_parser.py
spider_main.py
url_manager.py
第一个文件：spider_main.py
# coding=gbk
‘‘‘
简单爬虫架构
URL管理器
网页下载器，urllib2
网页解析器：BeautifulSoup
这只是最简单的爬虫！！！
--后期，需要登录的，验证码，Ajax,服务器防爬虫，多线程，分布式
‘‘‘
import __main__
from wangyepachong import url_manager
from wangyepachong import html_downloader
from wangyepachong import html_parser
from wangyepachong import 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.collectdata(new_data)
if count == 1000:
break
count = count + 1
except:
print ‘craw faild‘
self.outputer.output_html()
if __main__ =="__main__":
root_url = "http://baike.baidu.com/view/21087.htm"
obj_spider = SpiderMain()
obj_spider.craw(root_url)
第二个文件：html_dowanloader.py
# coding=gbk
import urllib2
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()
第三个文件：html_parser.py
# coding=gbk
from bs4 import BeautifulSoup
import re
import urlparse
class HtmlParser(object):
def parse(self,page_url,html_cont):
if page_url is None or html_cont is None:
return
soup = BeautifulSoup(html_cont,‘html.parser‘,form_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
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"))
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):
#创建一个字典，用于存放数据
res_data ={}
#
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()
summary_node = soup.find(‘div‘,class_="lemma-summary")
res_data[‘summary‘] = summary_node.get_text()
return res_data
第四个文件：url_manager.py
# coding=gbk
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
第五个文件：html_outputer.py
# coding=gbk
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>")
问题1：编写完成后有条语句报错，但是后期自己就没有问题了
title_node = soup.find(‘dd‘,class_="lemmaWgt-lemmaTitle-title").find("h1")
问题2：目前代码没有报错，但是不能运行，可能因为逻辑没有完全分析清楚，后期再修改细节，使该项目可以运行