Python 是一种极具可读性和通用性的编程语言。Python 易于设置，并且是用相对直接的风格来编写，对错误会提供即时反馈，对初学者而言是个很好的选择。
Python 是一种多范式语言，也就是说，它支持多种编程风格，包括脚本和面向对象，这使得它适用于通用目的。
Python项目练习一：即时标记
这个项目分为四个模块：
分析器：负责读取文本，管理其他的类
规则：检测文本块的类型（标题，列表等），使用相对应的规则
过滤器：处理一些内嵌元素，比如
处理程序：为文本块添加标记
目的就是要将一段文本根据文本的格式转换成HTML
Python项目练习二：画幅好画
这是《python基础教程》中的第二个项目，关于python操作PDF
涉及到的知识点
1、urllib的使用
2、reportlab库的使用
这个例子着实很简单，不过我发现在python里面可以直接在数组［］里面写for循环，真是越用越方便。
下面是代码：
Python项目练习三：新闻聚合
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）。
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()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。
以上就是本次分享的所有内容，如果你觉得文章还不错，欢迎关注公众号：Python日志，资料源码领取加QQ群：676910747