파이썬 소스 한글 인코딩 지정(펌)

PYTHON ERROR

   

파이썬 소스에 한글 문자열이 있으면 다음과 같은 "SyntaxError: Non-ASCII character..."라는 에러가 납니다:

   

File "D:\Z\0.py", line 4

SyntaxError: Non-ASCII character '\x8c' in file D:\Z\0.py on line 4, but no encoding declared; see http://www.python.org/peps/pep-0263.html for details

   

파이썬은 영문 인코딩이 기본이기에, 한글을 표현하기 위해서는 한글 인코딩을 지정해 주어야 합니다.

# -*- coding: 949 -*-

   

위와 같은 행을, 파이썬 소스의 반드시 "1번째 줄" 또는 "2번째 줄"에 위치시켜야 합니다. 3번째 줄부터는 안됩니다.

   

또한

coding:

이곳의 콜론(:)기호를

   

coding :

이렇게 띄어쓰면 안됩니다.

   

파이썬 소스 한글 인코딩 지정 예제

   

파일명: 0.py

#!/usr/bin/python

# -*- coding: 949 -*-

   

   

print "Hello World! 똠방각하"

   

# 이 줄은 주석문(코멘트; Comment)입니다.

   

   

# -*- coding: cp949 -*-

또는

# -*- coding: ms949 -*-

라고 해도 됩니다.

   

   

그러나

# -*- coding: euc-kr -*-

이라고 하면, "똠방각하"의 "똠"자 등이 표현되지 않습니다.

   

"똠"자를 처리하지 못하고 이런 에러가 납니다: SyntaxError: 'euc_kr' codec can't decode bytes in position 20-21: illegal multibyte sequence

   

즉 확장완성형이 아닌 그냥 완성형으로 지정됩니다.

   

  디렉토리의 파일목록 얻기

glob모듈의 glob함수 사용: 와일드카드문자 ?(임의의문자 1개와 매칭),* 를 지원한다.

• import glob
  glob.glob('./[0-9].*')

     

   파일의 추가정보 알아내기

  isfile(path)- path가 일반 파일이면 True 리턴

  isdir(path)- path가 디렉토리이면 True 리턴

  islink(path), ismount(path), exist(path)

  파일크기, 접근시간

     

   경로명 다루기

• import os
  p = os.path.abspath('LogMergeServer.py') #상대경로를 절대경로로
  p
  '/hanmail/wap_log/LogMergeServer.py'
  os.path.split(p) #(디렉토리와 파일을 분리)
  ('/hanmail/wap_log', 'LogMergeServer.py')
•    

     

     

   URL다루기

  urlparse함수는 아래와 같이 분리하여 튜플을 리턴

  (addressing, scheme, network location, path, parameter, query, fragment, identifier)

  ex)

• import urlparse
  a='http://3355.daum.net/daum/search/top/TotalList?q=스파이더맨3&skey='
  x=urlparse.urlparse(a)
  x
• ('http', '3355.daum.net', '/daum/search/top/TotalList', '', 'q=\xbd\xba\xc6\xc4\xc0\xcc\xb4\xf5\xb8\xc73&skey=', '')
• urlparse.urlunparse(x)
  'http://3355.daum.net/daum/search/top/TotalList?q=\xbd\xba\xc6\xc4\xc0\xcc\xb4\xf5\xb8\xc73&skey='
• urlparse.urljoin(a, 'SearchTop')
•  'http://3355.daum.net/'

     

  Python regex

     text = '''128.134.98.74 - - [03/Jul/2007:17:03:01 +0900] "GET /daum/search/top/TotalList?q=\xc4\xab\xb5\xe5\xb2\xa4&access=KTF_SEARCH HTTP/1.1" 200 10949 "-" "Mozilla/1.22 (compatible;KUN/2.1.1; EV-K100; CellPhone)" "-" "8201096336669" "-"'''

      text = urllib.unquote(text)

      url = text.split("\"")[1].split(" ")[1]

      url = url.decode()

       

      pattern = r'^/\w+/\w+/(\w+)/\w.*q=([^&\xA1-\xFE]+).+?'

      p = re.compile(pattern)

      #p = re.compile(r'^/\w+/\w+/(\w+)/\w.*q=([^(\xa1-\xfe0-9a-zA-Z]+).+?')

      m = p.match(url)

      print url

      print '------------------------------------------------------'

     

      print m.group(0)

      print m.group(1)

      q = m.group(2)

      print q

     

     

     

  # -*- coding: euc-kr -*-

  import urllib

  import re

  import time

     

  class parseLog:

      def __init__(self):

          self.today = time.strftime('%y%m%d')

          self.infile = open(self.today + '.search_log', 'r')

          self.outfile = open(self.today + '.search_map', 'a')

           

      def extractUrl(self):

          self.urls=[]

          for line in self.infile:

              line = urllib.unquote(line)

              self.urls.append(line.split("\"")[1].split(" ")[1].decode())   

      def parseUrl(self):

          self.collMap = []

          for url in self.urls:

              #print url

              p = re.compile(r'^/\w+/\w+/(\w+)/\w.*q=([^&\xA1-\xFE]+).+?')

              m = p.match(url)

              collection = m.group(1)

              keyword = m.group(2)

              #print collection, keyword

              self.collMap.append((collection, keyword))

           

               

               

       

               

  if __name__== "__main__":

      p = parseLog()

      p.extractUrl()

      p.parseUrl()

      print p.collMap

     

     

     

•   # # -*- coding: euc-kr -*-
  import urllib
  import re
  import time
  from array import *
  class CollectionInfo:
      cafe = 0
      know = 0
      blog = 0
      news = 0
      image = 0
      web = 0
      keyword = ''
      def setKeyword(self, keyword):
          self.keyword = keyword
      def addCafe(self):
          self.cafe = self.cafe+1
      def addKnow(self):
          self.know = self.know+1
      def addBlog(self):
          self.blog = self.blog+1
      def addNews(self):
          self.news = self.news+1
      def addImage(self):
          self.image = self.image + 1
      def addWeb(self):
          self.web = self.web + 1
      def printColl(self):
          print 'cafe:',self.cafe,'/','blog:',self.blog,'/','know:',self.know,'/', 'news:',self.news,'/', 'image:',self.image,'/', 'web:',self.web   
  
         
  class ParseLog:
      def __init__(self):
          self.today = time.strftime('%y%m%d')
          self.infile = open(self.today + '.search_log', 'r')
          self.outfile = open(self.today + '.search_map', 'a')
          self.coldic = {}
        
      def extractUrl(self):
          self.urls=[]
          for line in self.infile:
              line.decode()
              line = urllib.unquote(line)
  
              self.urls.append(line.split("\"")[1].split(" ")[1])  
      '''/daum/search/blog/BlogList?q=%C7%CF%B5%CE%B8%AE%B3%E0&skey='''    
      def extractKeyword(self, url):
          if url.find('?q=') > 0:
              index = url.find('?q=')
          if url.find('&q=') > 0:
              index = url.find('&q=')
         
          q = url[index+3:]
         
          if q.find('&') > -1:
              q = q[:q.find('&')]
          return q
      def setCollectionInfo(self, collection, keyword):
          col=CollectionInfo()
          if 'cafe' == collection:
              col.addCafe()
          elif 'blog' == collection:
              col.addBlog()
          elif 'know' == collection:
              col.addKnow()
          elif 'news' == collection:
              col.addNews()
          elif 'image' == collection:
              col.addImage()
          elif 'web' == collection:
              col.addWeb()
         
          return col
  
      def setKeywordStat(self, collection, keyword, isFirst = False):   
          if(isFirst):
              self.coldic[keyword] = self.setCollectionInfo(collection,keyword)
          else:           
              if keyword in self.coldic:
                  if 'cafe' == collection:
                      self.coldic[keyword].addCafe()
                  elif 'blog' == collection:
                      self.coldic[keyword].addBlog()
                  elif 'know' == collection:
                      self.coldic[keyword].addKnow()
                  elif 'news' == collection:
                      self.coldic[keyword].addNews()
                  elif 'image' == collection:
                      self.coldic[keyword].addImage()
                  elif 'web' == collection:
                      self.coldic[keyword].addWeb()
              else:
                  self.coldic[keyword] = self.setCollectionInfo(collection,keyword)
      def parseUrl(self):
          self.collMap = []
          colPattern = re.compile(r'^/.*(cafe|know|blog|image|dr|news)/.*')
          i=0
          for url in self.urls:
              colMat = colPattern.search(url)
              collection = colMat.group(1)
              keyword = self.extractKeyword(url)
              if keyword is not '':   
                  keyword = keyword.replace('+','')#공백제거
                  print url
                  print keyword
                  if i == 0:
                      self.setKeywordStat(collection, keyword, True)
                  else:
                      self.setKeywordStat(collection, keyword)               
                  i=i+1
                  #setKeywordStat(collection,keyword,i)
                  self.collMap.append((collection, keyword))
              
  if __name__== "__main__":
      p = ParseLog()
      p.extractUrl()
      p.parseUrl()
      print '======================================'
      for keyword in p.coldic.keys():
          print keyword, p.coldic[keyword].printColl()
     

     

  Pasted from <http://joyungki.springnote.com/pages/227536>