This article mainly introduces the news aggregation of the python basic tutorial project in detail. It has a certain reference value. Interested friends can refer to the
"Python Basic Tutorial" book. The fourth exercise is news aggregation. A type of application that is rare nowadays, at least I have never used it, is also called Usenet. The main function of this program is to collect information from specified sources (here, Usenet newsgroups), and then save this information to specified destination files (two forms are used here: plain text and html files). The use of this program is somewhat similar to the current blog subscription tool or RSS subscriber.
First introduce the code, and then analyze it one by one:
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' % item.body
print >> out, '''