MythTV  master
nasa_api.py
Go to the documentation of this file.
1 #!/usr/bin/env python
2 # -*- coding: UTF-8 -*-
3 # ----------------------
4 # Name: nasa_api - XPath and XSLT functions for the NASA RSS/HTML items
5 # Python Script
6 # Author: R.D. Vaughan
7 # Purpose: This python script is intended to perform a variety of utility functions
8 # for the conversion of data to the MNV standard RSS output format.
9 # See this link for the specifications:
10 # http://www.mythtv.org/wiki/MythNetvision_Grabber_Script_Format
11 #
12 # License:Creative Commons GNU GPL v2
13 # (http://creativecommons.org/licenses/GPL/2.0/)
14 #-------------------------------------
15 __title__ ="nasa_api - XPath and XSLT functions for the NASA RSS/HTML"
16 __author__="R.D. Vaughan"
17 __purpose__='''
18 This python script is intended to perform a variety of utility functions
19 for the conversion of data to the MNV standard RSS output format.
20 See this link for the specifications:
21 http://www.mythtv.org/wiki/MythNetvision_Grabber_Script_Format
22 '''
23 
24 __version__="v0.1.0"
25 # 0.1.0 Initial development
26 
27 
28 # Specify the class names that have XPath extention functions
29 __xpathClassList__ = ['xpathFunctions', ]
30 
31 # Specify the XSLT extention class names. Each class is a stand lone extention function
32 #__xsltExtentionList__ = ['xsltExtExample', ]
33 __xsltExtentionList__ = []
34 
35 import os, sys, re, time, datetime, shutil, urllib, string
36 from copy import deepcopy
37 
38 
39 class OutStreamEncoder(object):
40  """Wraps a stream with an encoder"""
41  def __init__(self, outstream, encoding=None):
42  self.out = outstream
43  if not encoding:
44  self.encoding = sys.getfilesystemencoding()
45  else:
46  self.encoding = encoding
47 
48  def write(self, obj):
49  """Wraps the output stream, encoding Unicode strings with the specified encoding"""
50  if isinstance(obj, unicode):
51  try:
52  self.out.write(obj.encode(self.encoding))
53  except IOError:
54  pass
55  else:
56  try:
57  self.out.write(obj)
58  except IOError:
59  pass
60 
61  def __getattr__(self, attr):
62  """Delegate everything but write to the stream"""
63  return getattr(self.out, attr)
64 sys.stdout = OutStreamEncoder(sys.stdout, 'utf8')
65 sys.stderr = OutStreamEncoder(sys.stderr, 'utf8')
66 
67 try:
68  from StringIO import StringIO
69  from lxml import etree
70 except Exception, e:
71  sys.stderr.write(u'\n! Error - Importing the "lxml" and "StringIO" python libraries failed on error(%s)\n' % e)
72  sys.exit(1)
73 
74 # Check that the lxml library is current enough
75 # From the lxml documents it states: (http://codespeak.net/lxml/installation.html)
76 # "If you want to use XPath, do not use libxml2 2.6.27. We recommend libxml2 2.7.2 or later"
77 # Testing was performed with the Ubuntu 9.10 "python-lxml" version "2.1.5-1ubuntu2" repository package
78 version = ''
79 for digit in etree.LIBXML_VERSION:
80  version+=str(digit)+'.'
81 version = version[:-1]
82 if version < '2.7.2':
83  sys.stderr.write(u'''
84 ! Error - The installed version of the "lxml" python library "libxml" version is too old.
85  At least "libxml" version 2.7.2 must be installed. Your version is (%s).
86 ''' % version)
87  sys.exit(1)
88 
89 
90 class xpathFunctions(object):
91  """Functions specific extending XPath
92  """
93  def __init__(self):
94  self.functList = ['nasaTitleEp', ]
95  # Show 1
96  self.regexPattern = re.compile(u'''Show\\ (?P<seasno>[0-9]+).*$''', re.UNICODE)
97  # end __init__()
98 
99 
104 
105  def nasaTitleEp(self, context, *arg):
106  '''Parse the guid element and extract an episode number
107  Call example: 'mnvXpath:nasaTitleEp(string(title))'
108  return the a massaged title element and an episode element
109  '''
110  stripArray = ['HST SM4:', 'NASA 360:', 'NASA 360', 'NASA EDGE:', 'NASA EDGE', 'NE Live@', 'NE@', 'NASA Mission Update:', "NASA TV's This Week @NASA," ]
111  title = arg[0]
112  for stripText in stripArray:
113  title = title.replace(stripText, u'')
114  title = title.strip()
115  episodeNumber = None
116  if title.startswith('Show'):
117  match = self.regexPattern.match(title)
118  if match:
119  episodeNumber = match.groups()
120  episodeNumber = int(episodeNumber[0])
121  title = title[title.find(':')+1:].strip()
122 
123  mythtvNamespace = "http://www.mythtv.org/wiki/MythNetvision_Grabber_Script_Format"
124  mythtv = "{%s}" % mythtvNamespace
125  NSMAP = {'mythtv' : mythtvNamespace}
126  elementTmp = etree.Element(mythtv + "mythtv", nsmap=NSMAP)
127  if not episodeNumber == None:
128  etree.SubElement(elementTmp, "title").text = u"EP%02d: %s" % (episodeNumber, title)
129  etree.SubElement(elementTmp, mythtv + "episode").text = u"%s" % episodeNumber
130  else:
131  etree.SubElement(elementTmp, "title").text = title
132  return elementTmp
133  # end nasaTitleEp()
134 
135 
140 
141 
146 
147 
def nasaTitleEp(self, context, *arg)
Start of XPath extension functions.
Definition: nasa_api.py:105
def __init__(self, outstream, encoding=None)
Definition: nasa_api.py:41