Use Click Package to Write Beautiful Command Application with Python

click is a Python package for creating beautiful command line interfaces in a composable way with as little amount of code as necessary. It’s the “Command Line Interface Creation Kit”. It’s highly configurable but comes with good defaults out of the box.

Install

pip install click 

Hello world Sample

import click

@click.command()
@click.option('--count', default=1, help='number of greetings')
@click.option('--name', prompt='Your name',
              help='the person to greet', required=True)
def hello(count, name):
    for x in range(count):
        print('Hello %s!' % name)

if __name__ == '__main__':
    hello()

You can find quickstart and full docs here.

Bind livestatus unix socket to TCP socket use Python and twisted

from twisted.internet import protocol, reactor
import socket,os

socket_path = "/var/lib/nagios3/rw/live"

class Echo(protocol.Protocol):
    def dataReceived(self, data):
 s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)

 s.connect(socket_path)

 s.send(data)
 s.shutdown(socket.SHUT_WR)
 answer = s.recv(100000000)
        self.transport.write(answer)

class EchoFactory(protocol.Factory):
    def buildProtocol(self, addr):
        return Echo()

reactor.listenTCP(6557, EchoFactory())
reactor.run()


Postfix bounces email handler by python script

#!/usr/bin/python
# -*- coding: utf-8 -*-
# export PYTHONIOENCODING=utf-8
import MySQLdb
import string
import email
from cStringIO import StringIO
from email import message_from_string
from flufl.bounce import scan_message
import re, sys, os

class DB:
conn = None

def connect(self):
self.conn = MySQLdb.connect(host='10.0.0.1', user='xx_rw', passwd='123456', db='xxx', use_unicode=True, charset="utf8")

def query(self, sql, string):
try:
cursor = self.conn.cursor()
cursor.execute(sql,string)
except (AttributeError, MySQLdb.OperationalError):
self.connect()
cursor = self.conn.cursor()
cursor.execute(sql,string)
return cursor


def main():
db = DB()
sender=sys.argv[2]
recipient=sys.argv[1]
email_input = sys.stdin.readlines()
parser = email.FeedParser.FeedParser()
msg = None
for msg_line in email_input:
msg = parser.feed(msg_line)
msg = parser.close()

#filter_recipient = scan_message(message_from_string(string.join(message, ' ')))
filter_recipient = scan_message(msg)
if (len(filter_recipient)>0):
db.query("""INSERT INTO email_bounces (`sender`, `recipient`) VALUES(%s, %s)""", (filter_recipient, recipient))

if __name__ == "__main__":
main()

Python and Linux Command

import commands
out = commands.getoutput("ls")
print out


在App Engine上使用bottle框架

application: my-bottle-app\
version: 1
runtime: python
api_version: 1

handlers:
- url: /styles
static_dir: styles

- url: /.*
script: main.py

from framework import bottle
from framework.bottle import route, template, request, error, debug
from google.appengine.ext.webapp.util import run_wsgi_app

@route('/')
def DisplayForm():
message = 'Hello World'
output = template('templates/home', data = message)
return output

def main():
debug(True)
run_wsgi_app(bottle.default_app())

@error(403)
def Error403(code):
return 'Get your codes right dude, you caused some error!'

@error(404)
def Error404(code):
return 'Stop cowboy, what are you trying to find?'

if __name__=="__main__":
main()

Python类例子

[cc lang="python"]class Message:
def __init__(self, aString):
self.text = aString
def printIt(self):
print self.text

m1 = Message("Hello world")
m2 = Message("So long, it was short but sweet")

note = [m1, m2] # put the objects in a list
for msg in note:
msg.printIt() # print each message in turn
[/cc]

详细指南

极速 Twisted Web 60秒(6): 定制返回代码

[cc lang="python"]from twisted.web.server import Site
from twisted.web.resource import Resource
from twisted.internet import reactor

class PaymentRequired(Resource):
def render_GET(self, request):
request.setResponseCode(402)
return "Please swipe your credit card."

root = Resource()
root.putChild("buy", PaymentRequired())
factory = Site(root)
reactor.listenTCP(8880, factory)
reactor.run() [/cc]

极速 Twisted Web 60秒(5): 错误句柄

[cc lang="python"]
from twisted.web.server import Site
from twisted.web.resource import Resource
from twisted.internet import reactor
from twisted.web.error import NoResource

from calendar import calendar

class YearPage(Resource):
def __init__(self, year):
Resource.__init__(self)
self.year = year

def render_GET(self, request):
return "

%s

" % (calendar(self.year),)

class Calendar(Resource):
def getChild(self, name, request):
try:
year = int(name)
except ValueError:
return NoResource()
else:
return YearPage(year)

root = Calendar()
factory = Site(root)
reactor.listenTCP(8880, factory)
reactor.run()
[/cc]

极速 Twisted Web 60秒(4): 动态URL处理

[cc lang="python"]
from twisted.web.server import Site
from twisted.web.resource import Resource
from twisted.internet import reactor

from calendar import calendar

class YearPage(Resource):
def __init__(self, year):
Resource.__init__(self)
self.year = year

def render_GET(self, request):
return "

%s

" % (calendar(self.year),)

class Calendar(Resource):
def getChild(self, name, request):
return YearPage(int(name))

root = Calendar()
factory = Site(root)
reactor.listenTCP(8880, factory)
reactor.run()
[/cc]

极速 Twisted Web 60秒(3): 静态URL处理

[cc lang="python"]
from twisted.web.server import Site
from twisted.web.resource import Resource
from twisted.internet import reactor
from twisted.web.static import File

root = Resource()
root.putChild("foo", File("/tmp"))
root.putChild("bar", File("/lost+found"))
root.putChild("baz", File("/opt"))

factory = Site(root)
reactor.listenTCP(8880, factory)
reactor.run()
[/cc]

极速 Twisted Web 60秒(2): 生成动态页面

[cc lang="python"]
from twisted.internet import reactor
from twisted.web.server import Site
from twisted.web.resource import Resource
import time

class ClockPage(Resource):
isLeaf = True
def render_GET(self, request):
return "%s" % (time.ctime(),)

resource = ClockPage()
factory = Site(resource)
reactor.listenTCP(8880, factory)
reactor.run()
[/cc]

极速 Twisted Web 60秒(1): 访问静态目录文件

[cc lang='python' ]
from twisted.web.server import Site
from twisted.web.static import File
from twisted.internet import reactor

resource = File('/tmp')
factory = Site(resource)
reactor.listenTCP(8888, factory)
reactor.run()
[/cc]

使用python的lxml库解析html

[cc lang="python"]import urllib2
import lxml.html as H

def getjarinfo(url):
c=urllib2.urlopen(url)

f=c.read()
doc = H.document_fromstring(f)
tables=doc.xpath("//table[@id='download']")
pinpais=doc.xpath("//td[@id='music']")
jixings=doc.xpath("//div[@id='game']")
jars = doc.xpath("//table[@id='download']//tr[2]/td[1]/a[1]")
for j in range(len(pinpais)):
print jars[j].get('href')
print pinpais[j].text_content()
print jixings[j].text_content()
e=doc.xpath(u"//div[text()='%s']" % u"游戏")
describe=e[0].getnext().text_content()
#r = doc.xpath("//table[@id='download']//tr[2]/td[1]/a[1]")[0]
#jarurl=r.get('href')

if __name__ == '__main__':
url='http://google.com/'
getjarinfo(url)
[/cc]

pyCurl获取网页问题

终于解决了这个问题，原来是我的代码中构造HTTP header的时候多了可以接受gzip压缩，支持gzip压缩的网页就下载了也不能用BeautifulSoup分析了，原来1ting.com现在支持gzip压缩了，还换了一个nProxy，多半是把ngnix的代码改了配置重新编译了~ 真是很~~


# Use Pycurl
def buildHeaders(browser, referer=""):
"""
Build HTTP Headers, So we can download wma files.
Arguments:
- `browser`: Which browser will use
- `referer`: Referer url
"""
if referer != "":
buildHeaders = ['User-Agent: ' + browser, 'Accept: text/html, application/xml;q=0.9, audio/x-ms-wma, application/xhtml+xml, image/png, gzip, x-gzip, image/jpeg, image/gif, image/x-xbitmap, */*;q=0.1', 'Accept-Language: en-us', 'Accept-Encoding: deflate, identity, *;q=0', 'Accept-Charset: iso-8859-1, utf-8, utf-16, *;q=0.1', 'Cookie: PIN=G39J3kmH2AU0SBieDgavAg==', 'Referer:' + referer]
else:
buildHeaders = ['User-agent: ' + browser, 'Accept: text/html, application/xml;q=0.9, audio/x-ms-wma, application/xhtml+xml, image/png, gzip, x-gzip, image/jpeg, image/gif, image/x-xbitmap, */*;q=0.1', 'Accept-Language: en-us', 'Accept-Encoding: deflate, identity, *;q=0', 'Accept-Charset: iso-8859-1, utf-8, utf-16, *;q=0.1', 'Cookie: PIN=G39J3kmH2AU0SBieDgavAg==']
return buildHeaders



Proxy and Port Mapping With Python

Use python to do tiny proxy server by example.

Python 八荣八耻

以动手实践为荣 , 以只看不练为耻;
以打印日志为荣 , 以单步跟踪为耻;
以空格缩进为荣 , 以制表缩进为耻;
以单元测试为荣 , 以人工测试为耻;

以模块复用为荣 , 以复制粘贴为耻;
以多态应用为荣 , 以分支判断为耻;
以Pythonic为荣 , 以冗余拖沓为耻;
以总结分享为荣 , 以跪求其解为耻;

每日至少抽一刻钟,解答邮件列表中初学者的问题，
每周至少抽两小时,整理新学知识将体验发表/分享出去，
通过Blog/Wiki/MaiList/个人网站……
每旬至少抽四个小时, 来翻译自个儿喜爱的自由软件的文档，
每月至少抽八小时, 快乐的编程，推进自个儿的项目，
每年至少参加一次, 自由软件的活动，传播自由软件思想，
发展一名“自由人”……

只要我们每个人都坚持下去……
10年！就足以改变中国软件的整体风貌！

PycURL example

Here's a little sample of Python code demonstrating the use of PycURL, the Python interface to libcURL. It does the same thing as my cURL example. Refer to this page for a detailed list of libcurl options.


import pycurl, StringIO
# Constants
DOWNLOADED_FILE = r'C:\temp\downloaded_file.txt'
USER_AGENT = 'Mozilla/4.0 (compatible; MSIE 6.0)'
LOGIN_URL = 'http://interesting.website.com/LogIn.asp'
LOGIN_POST_DATA = 'FormField=URL%20Encoded%20Value'
DOWNLOAD_URL = 'http://interesting.website.com/do_it.asp?do=0&something=0&interesting=0'
DOWNLOAD_REFERER = 'http://interesting.website.com/referer.asp'
FILE_MODE = 'wb'

# Set up objects
dev_null = StringIO.StringIO()
slurpp = pycurl.Curl()

# Request login page
slurpp.setopt(pycurl.USERAGENT, USER_AGENT)
slurpp.setopt(pycurl.FOLLOWLOCATION, 1)
#slurpp.setopt(pycurl.AUTOREFERER, 1) # not yet implemented in pycURL
slurpp.setopt(pycurl.WRITEFUNCTION, dev_null.write)
slurpp.setopt(pycurl.COOKIEFILE, '')
slurpp.setopt(pycurl.URL, LOGIN_URL)
slurpp.perform()

# Log in to site
slurpp.setopt(pycurl.POSTFIELDS, LOGIN_POST_DATA)
slurpp.setopt(pycurl.POST, 1)
slurpp.perform()

# Download relevant data
slurpp.setopt(pycurl.HTTPGET, 1)
slurpp.setopt(pycurl.URL, DOWNLOAD_URL)
slurpp.setopt(pycurl.REFERER, DOWNLOAD_REFERER)
outfile = file(DOWNLOADED_FILE, FILE_MODE)
slurpp.setopt(pycurl.WRITEFUNCTION, outfile.write)
slurpp.perform()

# Clean up and close out
outfile.close()
dev_null.close()
slurpp.close()


Python HTML 分析

在google上找了下，说 Beautiful Soup 还不错。顺便转一篇关于Python的资源文章。

Python基本安装：

• http://www.python.org/ 官方标准Python开发包和支持环境，同时也是Python的官方网站；


• http://www.activestate.com/ 集成多个有用插件的强大非官方版本，特别是针对Windows环境有不少改进；

Python文档：

• http://www.python.org/doc/current/lib/lib.html Python库参考手册。


• http://www.byteofpython.info/ 可以代替Tutorial使用，有中文译版的入门书籍。


• http://diveintopython.org/ 一本比较全面易懂的入门书，中文版翻译最近进步为很及时的5.4了。


• http://www.python.org/peps/pep-0008.html 建议采用的Python编码风格。


• http://doc.zoomquiet.org/ 包括Python内容的一个挺全面的文档集。

几个Python爬虫库

• 几个爬虫的库http://pypi.python.org/pypi?:action=browse&c=334


• 一个不错的小库，这个站点也是一个不错的入门级别的站点。例子代码很好。http://www.example-code.com/python/spider_begin.asp


• curl python 模块，获得HTML页面 http://pycurl.sourceforge.net/


• http://www.sqlite.com.cn/MySqlite/11/443.Html

python和web蜘蛛

这个视乎是很古老的话题了，很多项目是用C++或者java来开发，但是python却会成为我的首选，因为她可以更快，更方便在现在实现。

相关资料

• Python HTML Parser Performance