先上代碼,然后再來逐一分析:
from nntplib import NNTP from time import strftime,time,localtime from email import message_from_string from urllib import urlopen import textwrap import re day = 24*60*60 def wrap(string,max=70): ''' ''' return ' '.join(textwrap.wrap(string)) + ' ' class NewsAgent: ''' ''' def init(self): self.sources = [] self.destinations = [] def addSource(self,source): self.sources.append(source) def addDestination(self,dest): self.destinations.append(dest) def distribute(self): items = [] for source in self.sources: items.extend(source.getItems()) for dest in self.destinations: dest.receiveItems(items) class NewsItem: def init(self,title,body): self.title = title self.body = body class NNTPSource: def init(self,servername,group,window): self.servername = servername self.group = group self.window = window def getItems(self): start = localtime(time() - self.window*day) date = strftime('%y%m%d',start) hour = strftime('%H%M%S',start) server = NNTP(self.servername) ids = server.newnews(self.group,date,hour)[1] for id in ids: lines = server.article(id)[3] message = message_from_string(' '.join(lines)) title = message['subject'] body = message.get_payload() if message.is_multipart(): body = body[0] yield NewsItem(title,body) server.quit() class SimpleWebSource: def init(self,url,titlePattern,bodyPattern): self.url = url self.titlePattern = re.compile(titlePattern) self.bodyPattern = re.compile(bodyPattern) def getItems(self): text = urlopen(self.url).read() titles = self.titlePattern.findall(text) bodies = self.bodyPattern.findall(text) for title.body in zip(titles,bodies): yield NewsItem(title,wrap(body)) class PlainDestination: def receiveItems(self,items): for item in items: print item.title print '-'*len(item.title) print item.body class HTMLDestination: def init(self,filename): self.filename = filename def receiveItems(self,items): out = open(self.filename,'w') print >> out,''' <html> <head> <title>Today's News</title> </head> <body> <h1>Today's News</hi> ''' print >> out, '<ul>' id = 0 for item in items: id += 1 print >> out, '<li><a href="#" rel="external nofollow" >%s</a></li>' % (id,item.title) print >> out, '</ul>' id = 0 for item in items: id += 1 print >> out, '<h2><a name="%i">%s</a></h2>' % (id,item.title) print >> out, '<pre>%s</pre>' % item.body print >> out, ''' </body> </html> ''' def runDefaultSetup(): agent = NewsAgent() bbc_url = 'http://news.bbc.co.uk/text_only.stm' bbc_title = r'(?s)a href="[^" rel="external nofollow" ]*">s*<b>s*(.*?)s*</b>' bbc_body = r'(?s)</a>s*<br/>s*(.*?)s*<' bbc = SimpleWebSource(bbc_url, bbc_title, bbc_body) agent.addSource(bbc) clpa_server = 'news2.neva.ru' clpa_group = 'alt.sex.telephone' clpa_window = 1 clpa = NNTPSource(clpa_server,clpa_group,clpa_window) agent.addSource(clpa) agent.addDestination(PlainDestination()) agent.addDestination(HTMLDestination('news.html')) agent.distribute() if name == 'main': runDefaultSetup()
這個程序,首先從整體上進行分析,重點部分在于NewsAgent,它的作用是存儲新聞來源,存儲目標地址,然后在分別調用來源服務器(NNTPSource以及SimpleWebSource)以及寫新聞的類(PlainDestination和HTMLDestination)。所以從這里也看的出,NNTPSource是專門用來獲取新聞服務器上的信息的,SimpleWebSource是獲取一個url上的數據的。而PlainDestination和HTMLDestination的作用很明顯,前者是用來輸出獲取到的內容到終端的,后者是寫數據到html文件中的。
有了這些分析,然后在來看主程序中的內容,主程序就是來給NewsAgent添加信息源和輸出目的地址的。
這確實是個簡單的程序,不過這個程序可是用到了分層了。
相信看了本文案例你已經掌握了方法,更多精彩請關注Gxl網其它相關文章!
推薦閱讀:
配置OpenCV3+Python3的方法
Python3+opencv的配置教程
聲明:本網頁內容旨在傳播知識,若有侵權等問題請及時與本網聯系,我們將在第一時間刪除處理。TEL:177 7030 7066 E-MAIL:11247931@qq.com