Python爬虫爬取博客园并保存

Python爬虫爬取安科开发并保存       

爬取安科开发指定用户的文章修饰后全部保存到本地

首先定义爬取的模块文件：

1. crawlers_main.py 执行入口
2. url_manager.py url管理器
3. download_manager.py 下载模块
4. parser_manager.py html解析器（解析html需要利用的内容)
5. output_manager.py 输出html网页全部内容文件（包括css,png,js等）

crawlers_main.py 执行入口

# coding:utf8
 from com.crawlers import download_manager
 from com.crawlers import output_manager
 from com.crawlers import parser_manager
 from com.crawlers import url_manager
 
 
 class SpiderMain(object):
     def __init__(self):
         self.urls = url_manager.UrlManager()
         self.downloader = download_manager.DownloadManager()
         self.parser = parser_manager.ParserManager()
         self.output = output_manager.OutputManager()
 
     def craw(self, root_url):
         html_root = self.downloader.download(root_url)
         new_urls = self.parser.parseUrls(root_url,html_root)
         self.urls.add_new_urls(new_urls)
         count = 1
         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_data = self.parser.parse(new_url, html_cont)
                 self.output.collect_data(new_data)
                 if count == 1000:
                     break
                 count += 1
             except:
                 print('craw failed')
 
         self.output.output_html()
 
 
 if __name__ == "__main__":
     root_url = "http://www.cnblogs.com/zhuyuliang/"
     obj_spider = SpiderMain()
     obj_spider.craw(root_url)

url_manager.py url管理器

1 # coding:utf8
 2 class UrlManager(object):
 3 
 4     def __init__(self):
 5         self.new_urls = set()
 6         self.old_urls = set()
 7 
 8     def add_new_url(self, url):
 9         if url is None:
10             return
11         if url not in self.new_urls and url not in self.old_urls:
12             self.new_urls.add(url)
13 
14     def add_new_urls(self, urls):
15         if urls is None or len(urls) == 0:
16             return
17         for url in urls:
18             self.add_new_url(url)
19 
20     def has_new_url(self):
21         return len(self.new_urls) != 0
22 
23     def get_new_url(self):
24         new_url = self.new_urls.pop()
25         self.old_urls.add(new_url)
26         return new_url

download_manager.py 下载模块

# coding:utf8
 import urllib2
 
 
 class DownloadManager(object):
 
     def download(self, url):
         if url is None:
             return None
         response = urllib2.urlopen(url)
         if response.code != 200:
             return None
         return response.read()

parser_manager.py html解析器（解析html需要利用的内容)

# coding:utf8
 import re
 from HTMLParser import HTMLParser
 
 from bs4 import BeautifulSoup
 import urlparse
 
 import sys
 reload(sys)
 sys.setdefaultencoding('utf-8')
 
 class ParserManager(HTMLParser):
 
     def __init__(self):
         HTMLParser.__init__(self)
         self.links = []
 
     def handle_starttag(self, tag, attrs):
         # print "Encountered the beginning of a %s tag" % tag
         if tag == 'img' or tag == "script":
             for (variable, value) in attrs:
                 if variable == "src" or variable == "href":
                     self.links.append(value)
         if tag == "link":
             dic = dict(attrs)
             if dic['rel'] == "stylesheet":
                 self.links.append(dic['href'])
 
     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_data = self._get_new_data(page_url,soup)
             return new_data
 
     def _get_new_urls(self, page_url, soup):
         new_urls = set()
         #href="http://www.cnblogs.com/zhuyuliang/p/5218635.html"
         links = soup.find_all('a',href=re.compile(r'http://www.cnblogs.com/zhuyuliang/p/...'))
         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 = {}
         res_data['url'] = page_url
 
         #<a id="cb_post_title_url" class="postTitle2" href="http://www.cnblogs.com/zhuyuliang/p/5218635.html">Android开发代码规范</a>
         title_node = soup.find('a',class_='postTitle2')
         res_data['title'] = title_node.get_text()
 
         #div id='topics'
         summary_node = soup.find('div',class_="post")
         res_data['summary'] = summary_node
 
         new_tag = soup.new_tag("body")
         new_tag.string = summary_node.encode('utf-8')
         soup.body.replace_with(new_tag)
         res_data['template'] = soup
 
         return res_data
 
     def parseUrls(self,root_url,html_cont):
         soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
         new_urls = self._get_new_urls(root_url, soup)
         return new_urls

output_manager.py 输出html网页全部内容文件（包括css,png,js等）

# -*- coding:utf-8 -*-
 # !/bin/sh
 import os
 import urllib
 from com.crawlers.parser_manager import ParserManager
 
 
 class OutputManager(object):
 
     def __init__(self):
         self.datas = []
 
     def collect_data(self, data):
         if data is None:
             return
         self.datas.append(data)
 
 
     def output_html(self):
         for data in self.datas:
             fout = open('output/%s.txt'%data['title'].encode('utf-8'), 'w')
             fout.write("%s" % data['summary'].encode('utf-8'))
             fout.close()
             url = data['url'].encode('utf-8')
             pagename = data['title'].encode('utf-8')
             # html_code = urllib.urlopen(url).read()
             hp = ParserManager()
             html_code = data['template'].encode('utf-8')
             html_code = hp.unescape(html_code)
             hp.feed(html_code)
             hp.close()
             durl = url.rsplit('/',1)[0]
             self.download(pagename,html_code,durl,hp.links)
 
 
     def download(self,pagename,html_code,durl,links):
         if not os.path.exists('output/'+pagename+'_files'):
             os.mkdir('output/'+pagename+'_files')
             upurl = durl.rsplit('/',1)[0]
             for link in links:
                 fname = link.split('/')[-1]
                 fname = fname.split('?')[0]
                 localpath = '%s%s' % ('output/'+pagename+'_files/',fname)
                 replacelocalpath = '%s%s' % (pagename + '_files/', fname)
                 # if link[0:3] == '../':
                 #         downlink = "http:" + link
                 # else:
                 #         downlink = link
                 try:
                     urllib.urlretrieve("http://www.cnblogs.com" + link,localpath)
                 except Exception,error:
                     print 'download error:', error
                 else:
                     print 'download '+fname
                     html_code = html_code.replace(link,replacelocalpath)
                 open('output/'+pagename+'.html','w').write(html_code)
         return True

最后输出：

>结束