MythTV  master
traileraddicts_api.py
Go to the documentation of this file.
1 #!/usr/bin/env python
2 # -*- coding: UTF-8 -*-
3 # ----------------------
4 # Name: traileraddicts_api - XPath and XSLT functions for the TrailerAddicts.com grabber
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__ ="traileraddicts_api - XPath and XSLT functions for the TrailerAddicts.com grabber"
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 = ['traileraddictsLinkGenerationMovie', 'traileraddictsLinkGenerationClip', 'traileraddictsCheckIfDBItem']
95  self.TextTail = etree.XPath("string()")
96  self.persistence = {}
97  # end __init__()
98 
99 
104 
105  def traileraddictsLinkGenerationMovie(self, context, *args):
106  '''Generate a link for the TrailerAddicts.com site.
107  Call example: 'mnvXpath:traileraddictsLinkGenerationMovie(position(), link)'
108  return the url link
109  '''
110  webURL = args[1].strip()
111 
112  # If this is for the download element then just return what was found for the "link" element
113  if self.persistence.has_key('traileraddictsLinkGenerationMovie'):
114  if args[0] == self.persistence['traileraddictsLinkGenerationMovie']['position']:
115  return self.persistence['traileraddictsLinkGenerationMovie']['link']
116  else:
117  self.persistence['traileraddictsLinkGenerationMovie'] = {}
118  self.persistence['traileraddictsLinkGenerationMovie']['embedRSS'] = etree.parse(u'http://www.traileraddict.com/embedrss', common.parsers['xml'].copy())
119  self.persistence['traileraddictsLinkGenerationMovie']['matchlink'] = etree.XPath('//link[string()=$link]/..', namespaces=common.namespaces)
120  self.persistence['traileraddictsLinkGenerationMovie']['description'] = etree.XPath('normalize-space(description)', namespaces=common.namespaces)
121  self.persistence['traileraddictsLinkGenerationMovie']['embedded'] = etree.XPath('//embed/@src', namespaces=common.namespaces)
122 
123  self.persistence['traileraddictsLinkGenerationMovie']['position'] = args[0]
124 
125  matchLink = self.persistence['traileraddictsLinkGenerationMovie']['matchlink'](self.persistence['traileraddictsLinkGenerationMovie']['embedRSS'], link=webURL)[0]
126  self.persistence['traileraddictsLinkGenerationMovie']['link'] = self.persistence['traileraddictsLinkGenerationMovie']['embedded'](common.getHtmlData(u'dummy',(self.persistence['traileraddictsLinkGenerationMovie']['description'](matchLink))))[0]
127 
128  return self.persistence['traileraddictsLinkGenerationMovie']['link']
129  # end traileraddictsLinkGenerationMovie()
130 
131 
132  def traileraddictsLinkGenerationClip(self, context, *args):
133  '''Generate a link for the TrailerAddicts.com site.
134  Call example: 'mnvXpath:traileraddictsLinkGenerationClip(position(), link)'
135  return the url link
136  '''
137  webURL = args[1].strip()
138  # If this is for the download element then just return what was found for the "link" element
139  if self.persistence.has_key('traileraddictsLinkGenerationClip'):
140  if args[0] == self.persistence['traileraddictsLinkGenerationClip']['position']:
141  return self.persistence['traileraddictsLinkGenerationClip']['link']
142  else:
143  self.persistence['traileraddictsLinkGenerationClip'] = {}
144  self.persistence['traileraddictsLinkGenerationClip']['embedded'] = etree.XPath('//embed[@allowfullscreen="true"]/@src', namespaces=common.namespaces)
145 
146  self.persistence['traileraddictsLinkGenerationClip']['position'] = args[0]
147 
148  tmpHTML = etree.parse(webURL, etree.HTMLParser())
149  self.persistence['traileraddictsLinkGenerationClip']['link'] = self.persistence['traileraddictsLinkGenerationClip']['embedded'](tmpHTML)[0]
150  return self.persistence['traileraddictsLinkGenerationClip']['link']
151  # end traileraddictsLinkGenerationClip()
152 
153  def traileraddictsCheckIfDBItem(self, context, *arg):
154  '''Use a unique key value pairing to find out if the 'internetcontentarticles' table already
155  has a matching item. This is done to save accessing the Internet when not required.
156  Call example: 'mnvXpath:traileraddictsCheckIfDBItem(.)'
157  return True if a match was found
158  return False if a match was not found
159  '''
160  return common.checkIfDBItem('dummy', {'feedtitle': 'Movie Trailers', 'title': arg[0], 'author': arg[1], 'description': arg[2]})
161  # end traileraddictsCheckIfDBItem()
162 
163 
168 
169 
174 
175 
176 
long long copy(QFile &dst, QFile &src, uint block_size)
Copies src file to dst file.
def traileraddictsLinkGenerationMovie(self, context, *args)
Start of XPath extension functions.