                        課程
                    
                        /后端開發(fā)
                        
                            /Python
                        
                        /Python開發(fā)簡(jiǎn)單爬蟲

第一行：craw 1 : None。第二行：craw field

主代碼:

#?coding:utf8
#encoding=utf-8**
import?url_manager,?html_downloader,?html_parser,?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_urls,?new_data?=?self.parser.parse(new_url,?html_cont)
????????????????self.urls.add_new_urls(new_urls)
????????????????self.outputer.collect_data(new_data)
????????????????if?count?==?1000:
????????????????????print?'done'
????????????????????break
????????????????count?=?count?+?1
????????????except:
????????????????print?'craw?field'

????????self.outputer.output_html()

if?__name__?==?"__main__":
????root_url?=?"https://baike.baidu.com/item/Python/407313?fr=aladdin"
????obj_spider?=?SpiderMain()
????obj_spider.craw(root_url)

管理器：

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,?new_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

解析器：

class?HtmlParser(object):

????def?_get_new_urls(self,?page_url,?soup):
????????new_urls?=?set()
????????#?/view/123.htm
????????links?=?soup.find_all('a',?herf=re.compile(r"/item/\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

????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"
????????summary_node?=?soup.find('div',?class_?="lemma-summary")
????????res_data['summary']?=?sumary_node.get_text()

????????return?res_data


????def?parse(self,?pew_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

輸出器：

class?Htmloutputer(object):
????def?__init__(self):
????????self.datas?=?[]

????def?collect_data(self,?new_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("<rd>%s</td>"?%?data['url'])
????????????fout.write("<rd>%s</td>"?%?data['title'].encode('uft-8'))
????????????fout.write("<rd>%s</td>"?%?data['summary'].encode('uft-8'))
????????????fout.write("</tr>")

????????fout.write("</table>")
????????fout.write("<body>")
????????fout.write("<html>")

下載器：

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()

輸出結(jié)果：

craw 1 : None
craw field

Process finished with exit code 0