《python基礎(chǔ)教程》書中的第四個練習(xí)，新聞聚合。現(xiàn)在很少見的一類應(yīng)用，至少我從來沒有用過，又叫做Usenet。這個程序的主要功能是用來從指定的來源（這里是Usenet新聞組）收集信息，然后講這些信息保存到指定的目的文件中（這里使用了兩種形式：純文本和html文件）。這個程序的用處有些類似于現(xiàn)在的博客訂閱工具或者叫RSS訂閱器。
先上代碼，然后再來逐一分析：
from nntplib import NNTPfrom time import strftime,time,localtimefrom email import message_from_stringfrom urllib import urlopenimport textwrapimport reday = 24*60*60def wrap(string,max=70): ''' ''' return '/n'.join(textwrap.wrap(string)) + '/n'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 = bodyclass 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('/n'.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.bodyclass 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()
新聞熱點(diǎn)
疑難解答
