treecutter/directory.py

   1 #!/usr/bin/python
   2 import os
   3 import fnmatch
   4 from lxml import etree
   5 import treecutter.constants as const
   6
   7 class Directory():
   8     """Class containing the state of the directory with articles"""
   9     def __init__(self):
  10         self._cwd = '.'
  11         self._tree = []
  12
  13     def scan(self):
  14         for dirname, dirnames, filenames in os.walk(self._cwd):
  15             for filename in filenames:
  16                 if fnmatch.fnmatch(filename, '*.xml'):
  17                     file_ = os.path.join(dirname,filename)
  18                     doc = etree.parse(file_)
  19                     title = doc.xpath(u'/db:article/db:info/db:title',namespaces=const.XPATH)
  20                     menu  = doc.xpath(u'/db:article/db:info/db:titleabbrev',namespaces=const.XPATH)
  21                     if title and menu:
  22                         base = file_.split('.')[1]
  23                         link = base.replace('index','')
  24                         self._tree.append(link)
  25
  26     def set(self):
  27         return set(self._tree)