Python이 뉴스 수집 프로젝트를 만듭니다.
- php中世界最好的语言원래의
- 2018-04-09 13:44:302534검색
이번에는 뉴스 집계 프로젝트를 만들기 위해 Python을 가져오겠습니다. Python에서 뉴스 집계 프로젝트를 만들 때의 주의 사항은 무엇입니까?
코드부터 시작해 하나씩 분석해 보겠습니다.
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, '''