python基础教程项目四之新闻聚合

时间:2022-09-10 23:44:11

python基础教程》书中的第四个练习,新闻聚合。现在很少见的一类应用,至少我从来没有用过,又叫做Usenet。这个程序的主要功能是用来从指定的来源(这里是Usenet新闻组)收集信息,然后讲这些信息保存到指定的目的文件中(这里使用了两种形式:纯文本和html文件)。这个程序的用处有些类似于现在的博客订阅工具或者叫RSS订阅器。

先上代码,然后再来逐一分析:

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
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>%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()

这个程序,首先从整体上进行分析,重点部分在于NewsAgent,它的作用是存储新闻来源,存储目标地址,然后在分别调用来源服务器(NNTPSource以及SimpleWebSource)以及写新闻的类(PlainDestination和HTMLDestination)。所以从这里也看的出,NNTPSource是专门用来获取新闻服务器上的信息的,SimpleWebSource是获取一个url上的数据的。而PlainDestination和HTMLDestination的作用很明显,前者是用来输出获取到的内容到终端的,后者是写数据到html文件中的。

有了这些分析,然后在来看主程序中的内容,主程序就是来给NewsAgent添加信息源和输出目的地址的。

这确实是个简单的程序,不过这个程序可是用到了分层了。

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持服务器之家。

原文链接:https://www.the5fire.com/python-pro4-newsagent.html