Python 编程常见问题

Python 编程常见问题

经常使用Python编程，把经常遇到问题在这里记录一下，省得到网上查找，因此这篇文章会持续更新，需要的可以Mark一下。进入正题：

1.Python常用的文件头声明

#!/usr/bin/python
#-*- coding: UTF-8 -*-
#
# @filename:
# @author:
# @since: 2013-
# @version: 0.0.1
#
# Usage:
###############################################################################
import os
import sys
import shutil
import fileinput

# utf8
import codecs

2.Python命令参数解析（长参数和短参数）

###############################################################
# command line for this app:
#   $ python app.py -s 5555 -p 5556
# or
#   $ python app.py --sink-port 5555 --publish-port 5556
###############################################################

import os
import optparse

pid = os.getpid()

# parse our options
# see usage for optparse.OptionParser():
#   http://docs.python.org/2/library/optparse.html
#
parser = optparse.OptionParser()

parser.add_option("-s", "--sink-port",
    action="store",
    dest="sink_port",
    help="Specifies sink port on that service is listening")

parser.add_option("-p", "--publish-port",
    action="store",
    dest="publish_port",
    help="Specifies publish port service publish to")

# parse args and get options
(options, args) = parser.parse_args()

sink_port = options.sink_port
pub_port = options.publish_port

print ("[Process:%d] is listening on (tcp://*:%s) and publish to (tcp://*:%s) ..." %
    (pid, sink_port, pub_port))

3.Python获取外部中断命令(Ctrl+C)结束本程序

import time
import os
import signal

is_exit = False
pid = os.getpid()

def sigint_handler(signum, frame):
    global is_exit
    is_exit = True
    print "[Process:%d] Receive a signal %d, is_exit = %d" % (pid, signum, is_exit)

signal.signal(signal.SIGINT, sigint_handler)
signal.signal(signal.SIGTERM, sigint_handler)

while not is_exit:
	# sleep 1 second
	time.sleep(1)
	print "."

print "[Process:%d] exit!" % (pid)

4.Python UTF-8文件操作

一个好的习惯就是永远使用UTF-8编码作一切事情，包括Python文件本身。下面使用UTF-8编码打开文件并写入数据：

#!/usr/bin/python
#-*- coding: UTF-8 -*-
# !!!请确保本Python文件以UTF-8保存!!!

# utf8
import codecs

def openFileUtf8(fname):
  fd = codecs.open(fname, "w", encoding = "UTF-8")
  return fd

def closeFile(fd):
  fd.close()

def writeUtf8(fd, str):
  fd.write(unicode(str, "UTF-8"))

def writelnUtf8(fd, str):
  fd.write(unicode(str, "UTF-8") + '\r\n')

fw = openFileUtf8("/path/to/yourfile.txt")
writeUtf8(fw, "我爱你，中国")
closeFile(fw)

5.Python UTF-8中文字符串操作

下面演示如何获取UTF8字符串长度（有效文字个数）和截断：

#!/usr/bin/python
#-*- coding: UTF-8 -*-
# !!!请确保本Python文件以UTF-8保存!!!
# 对于中文UTF-8编码的字符串，如何得到长度并截断其中的字符呢？
# 思路就是:
#   首先把UTF-8字符串转成UTF-16(Unicode)字符串，
#   然后判断UTF-16长度，截断UTF-16字符串，再转回UTF-8:

import codecs

utf8str = "我爱你love，中国"
print "utf8:", utf8str

utf16str = utf8str.decode('utf-8')
print "utf16 len (==10):", len(utf16str)

# 截取前3个字符
utf16str = utf16str[0:7]

# 截取到的字符转回UTF-8
utf8substr = utf16str.encode('utf-8')

print "utf8 substr:", utf8substr

print "上面全部过程写成一句话: utf8substr = utf8str.decode('utf-8')[0:7].encode('utf-8') "
utf8substr = utf8str.decode('utf-8')[0:7].encode('utf-8')
print "utf8 substr:", utf8substr

运行截图：

6. MySQL - Python

1) 在Ubuntu上使用Python操作MySQL, 首先是安装：

$ wget http://sourceforge.net/projects/mysql-python/files/mysql-python/1.2.3/MySQL-python-1.2.3.tar.gz
$ tar -zxvf MySQL-python-1.2.3.tar.gz
$ cd MySQL-python-1.2.3
$ sudo python setup.py install

错误解决办法：

错误：
Traceback (most recent call last):
  File "setup.py", line 5, in
    from setuptools import setup, Extension
ImportError: No module named setuptools

解决：
$ sudo apt-get install python-setuptools

错误：
sh: mysql_config: not found
...

EnvironmentError: mysql_config not found

解决：
$ sudo apt-get install libmysqlclient-dev

错误：
...

error: command 'gcc' failed with exit status 1

解决：
$ sudo apt-get install python-dev

2) 在RHEL6.x上使用Python操作MySQL：

# cd MySQL-python-1.2.3
# python ez_setup.py -U setuptools
# yum install -y python-devel
# python setup.py build
# python setup.py install
# python
>>> import MySQLdb

8. UTF-8 文件操作

UTF-8的网站出现了中文乱码的问题，怀疑是缺少UTF-8 BOM头导致的。所以给所有HTML和JS文件添加了BOM头，问题解决。

def removeBomHeader(file):
    BOM = b'\xef\xbb\xbf'
    f = open(file, 'rb')
    if f.read(3) == BOM:
        fbody = f.read()
        f.close()
        with open(file, 'wb') as f:
            f.write(fbody)
    f.close()

def addBOMHeader(file):
    BOM = b'\xef\xbb\xbf'
    f = open(file, 'rb')
    if f.read(3) != BOM:
        f.close()
        f = open(file, 'rb')
        fbody = f.read()
        f.close()
        with open(file, 'wb') as f:
            f.write(BOM)
            f.write(fbody)
    f.close()

打开终端，设置为utf-8显示模式：

python

import codec

>>> s= u'\u7f8e\u9cf3'
>>> s= u'\u7f8e\u9cf3'
>>> s
u'\u7f8e\u9cf3'
>>> print s
美鳳
>>> u16 = u'\u7f8e\u9cf3'
>>> print u16
美鳳
>>> u8=u16.encode('utf-8')
>>> print u8
美鳳
>>> u8
'\xe7\xbe\x8e\xe9\xb3\xb3'
>>> type(u16)
<type 'unicode'>
>>> type(u8)
<type 'str'>
>>>

（未完待续...）