def _get_meta(self):
"""Fetch Gist metadata."""
# Use json data provided if available
if self._json:
_meta = self._json
setattr(self, 'id', _meta['repo'])
else:
# Fetch Gist metadata
_meta_url = GIST_JSON % self.id
_meta = json.load(urllib2.urlopen(_meta_url))['gists'][0]
for key, value in _meta.iteritems():
if key == 'files':
# Remap file key from API.
setattr(self, 'filenames', value)
# Store the {current_name: original_name} mapping.
setattr(self, '_renames', dict((fn, fn) for fn in value))
elif key == 'public':
# Attach booleans
setattr(self, key, value)
elif key == 'created_at':
# Attach datetime
setattr(self, key, dtime(value))
else:
# Attach properties to object
setattr(self, key, unicode(value))
return _meta
def _get_meta(self):
"""Fetch Gist metadata."""
# Use json data provided if available
if self._json:
_meta = self._json
setattr(self, "id", _meta["repo"])
else:
# Fetch Gist metadata
_meta_url = GIST_JSON % self.id
_meta = json.load(urllib2.urlopen(_meta_url))["gists"][0]
for key, value in _meta.iteritems():
if key == "files":
# Remap file key from API.
setattr(self, "filenames", value)
# Store the {current_name: original_name} mapping.
setattr(self, "_renames", dict((fn, fn) for fn in value))
elif key == "public":
# Attach booleans
setattr(self, key, value)
elif key == "created_at":
# Attach datetime
setattr(self, key, dtime(value))
else:
# Attach properties to object
setattr(self, key, unicode(value))
return _meta
def to_django(self):
art = DjangoArticle()
art.title = self.title
art.subtitle = self.subtitle
print self.published
art.published = dtime(self.published)
art.author = self.author
art.content = self.content
art.ourl = self.url
art.slug = self.slug
if len(self.content) > 1000:
art.save()
else:
print('%s had no usable content.' % (self.title if self.title else ''))
posts = []
try:
in_file = sys.argv[1]
except IndexError:
print 'Specify a file.'
parser = lxml.etree.XMLParser(recover=True) #recovers from bad characters.
tree = lxml.etree.parse(in_file, parser)
for post in tree.iterfind('//item'):
p = Post()
p.title = post.find('title').text
p.published = dtime(post.find('pubDate').text)
p.content = smart_str(
post.find('{http://purl.org/rss/1.0/modules/content/}encoded').text)
posts.append(p)
os.system('mkdir -p content')
os.chdir('content')
for post in posts:
#print '- %s' % post.title
#print post.__dict__
filename = post.published.strftime('%y%m%d-')
filename = filename + '_'.join(post.title.split()[:5]).lower()
for char in '?\':.#/':
filename = filename.replace(char, '')
