python做出新闻聚合项目-Python教程-PHP中文网

python做出新闻聚合项目

php中世界最好的语言

发布： 2018-04-09 13:44:30

原创

2686人浏览过

这次给大家带来python做出新闻聚合项目，python做出新闻聚合项目的注意事项有哪些，下面就是实战案例，一起来看一下。

先上代码，然后再来逐一分析：

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 '\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 = 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('\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.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 class="brush:php;toolbar:false;">%s

登录后复制

' % item.body print >> out, '''

以上就是python做出新闻聚合项目的详细内容，更多请关注php中文网其它相关文章！