def track(func):
"""A syntactic-sugar decorator to automatically track yielded
references from an entry. See :class:`Translation` in
:mod:`acrylamid.views.entry` for an example."""
def dec(entry, item):
append(entry, item)
return item
return lambda entry, **kw: map(partial(dec, entry), func(entry, **kw))
def wordpress(xml):
"""WordPress to Acrylamid, inspired by the Astraeus project."""
if 'xmlns:wp' not in xml:
raise InputError('not a WP dump')
global USED_WORDPRESS
USED_WORDPRESS = True
def generate(item):
entry = {
'title': item.find('title').text,
'link': item.find('link').text,
'content': (item.find('%sencoded' % cons).text or '').replace('\n', '<br />\n'),
'description': item.find('%sencoded' % excerptns).text or '',
'date': datetime.strptime(item.find('%spost_date' % wpns).text,
"%Y-%m-%d %H:%M:%S"),
'author': item.find('%screator' % dcns).text,
'tags': [tag.text for tag in item.findall('category')]
}
# attachment, nav_menu_item, page, post
entry['type'] = item.find('%spost_type' % wpns).text
if entry['type'] == 'post':
entry['type'] = 'entry'
if item.find('%sstatus' % wpns).text != 'publish':
entry['draft'] = True
return entry
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
# wordpress name spaces
dcns = '{http://purl.org/dc/elements/1.1/}'
cons = '{http://purl.org/rss/1.0/modules/content/}'
defaults = {
'title': tree.find('channel/title').text,
'www_root': tree.find('channel/link').text
}
for version in range(1, 10):
wpns = '{http://wordpress.org/export/1.%i/}' % version
excerptns = '{http://wordpress.org/export/1.%i/excerpt/}' % version
if tree.find('channel/%swxr_version' % wpns) is None:
continue
entries = list(map(generate, tree.findall('channel/item')))
return defaults, [entry for entry in entries if entry['type'] in ('page', 'entry')]
def track(func):
"""A syntactic-sugar decorator to automatically track yielded
references from an entry. See :class:`Translation` in
:mod:`acrylamid.views.entry` for an example."""
def dec(entry, item):
append(entry, item)
return item
return lambda entry, **kw: map(partial(dec, entry), func(entry, **kw))
def atom(xml):
def parse_date_time(stamp):
ts = parsedate_tz(stamp)
ts = mktime_tz(ts)
return datetime.fromtimestamp(ts)
def generate(item):
entry = {}
try:
entry['title'] = item.find(ns + 'title').text
entry['date'] = item.find(ns + 'updated').text
entry['link'] = item.find(ns + 'link').text
entry['content'] = item.find(ns + 'content').text
except (AttributeError, TypeError):
raise AcrylamidException(
'invalid Atom feed: provide at least title, ' +
'link, content and updated!')
if item.find(ns + 'content').get('type', 'text') == 'html':
entry['content'] = unescape(entry['content'])
return {
'title': entry['title'],
'content': entry['content'],
'date': datetime.strptime(entry['date'], "%Y-%m-%dT%H:%M:%SZ"),
'link': entry['link'],
'tags': [x.get('term') for x in item.findall(ns + 'category')]
}
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
if not tree.tag.endswith('/2005/Atom}feed'):
raise InputError('no Atom feed')
ns = '{http://www.w3.org/2005/Atom}' # etree Y U have stupid namespace handling?
defaults = {}
defaults['sitename'] = tree.find(ns + 'title').text
defaults['author'] = tree.find(ns + 'author').find(ns + 'name').text
www_root = [
a for a in tree.findall(ns + 'link')
if a.attrib.get('rel', 'alternate') == 'alternate'
]
if www_root:
defaults['www_root'] = www_root[0].attrib.get('href')
return defaults, list(map(generate, tree.findall(ns + 'entry')))
def determine_version(self, bundle, env, hunk=None):
if not hunk and not has_placeholder(bundle.output):
hunks = [FileHunk(bundle.resolve_output(env)), ]
elif not hunk:
src = sum(map(env.resolver.resolve_source, bundle.contents), [])
hunks = [FileHunk(hunk) for hunk in src + bundle.resolve_depends(env)]
else:
hunks = [hunk, ]
hasher = self.hasher()
for hunk in hunks:
hasher.update(hunk.data())
return hasher.hexdigest()[:self.length]
def atom(xml):
def parse_date_time(stamp):
ts = parsedate_tz(stamp)
ts = mktime_tz(ts)
return datetime.fromtimestamp(ts)
def generate(item):
entry = {}
try:
entry['title'] = item.find(ns + 'title').text
entry['date'] = item.find(ns + 'updated').text
entry['link'] = item.find(ns + 'link').text
entry['content'] = item.find(ns + 'content').text
except (AttributeError, TypeError):
raise AcrylamidException('invalid Atom feed: provide at least title, '
+ 'link, content and updated!')
if item.find(ns + 'content').get('type', 'text') == 'html':
entry['content'] = unescape(entry['content'])
return {'title': entry['title'],
'content': entry['content'],
'date': datetime.strptime(entry['date'], "%Y-%m-%dT%H:%M:%SZ"),
'link': entry['link'],
'tags': [x.get('term') for x in item.findall(ns + 'category')]}
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
if not tree.tag.endswith('/2005/Atom}feed'):
raise InputError('no Atom feed')
ns = '{http://www.w3.org/2005/Atom}' # etree Y U have stupid namespace handling?
defaults = {}
defaults['sitename'] = tree.find(ns + 'title').text
defaults['author'] = tree.find(ns + 'author').find(ns + 'name').text
www_root = [a for a in tree.findall(ns + 'link')
if a.attrib.get('rel', 'alternate') == 'alternate']
if www_root:
defaults['www_root'] = www_root[0].attrib.get('href')
return defaults, list(map(generate, tree.findall(ns + 'entry')))
def wordpress(xml):
"""WordPress to Acrylamid, inspired by the Astraeus project."""
if 'xmlns:wp' not in xml:
raise InputError('not a WP dump')
global USED_WORDPRESS
USED_WORDPRESS = True
def generate(item):
entry = {
'title': item.find('title').text,
'link': item.find('link').text,
'content': (item.find('%sencoded' % cons).text or '').replace('\n', '<br />\n'),
'date': datetime.strptime(item.find('%spost_date' % wpns).text,
"%Y-%m-%d %H:%M:%S"),
'author': item.find('%screator' % dcns).text,
'tags': [tag.text for tag in item.findall('category')]
}
if item.find('%spost_type' % wpns).text == 'page':
entry['type'] = 'page'
if item.find('%sstatus' % wpns).text != 'publish':
entry['draft'] = True
return entry
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
# wordpress name spaces
dcns = '{http://purl.org/dc/elements/1.1/}'
cons = '{http://purl.org/rss/1.0/modules/content/}'
defaults = {
'title': tree.find('channel/title').text,
'www_root': tree.find('channel/link').text
}
for version in range(1, 10):
wpns = '{http://wordpress.org/export/1.%i/}' % version
return defaults, list(map(generate, tree.findall('channel/item')))
def determine_version(self, bundle, env, hunk=None):
if not hunk and not has_placeholder(bundle.output):
hunks = [
FileHunk(bundle.resolve_output(env)),
]
elif not hunk:
src = sum(map(env.resolver.resolve_source, bundle.contents), [])
hunks = [
FileHunk(hunk) for hunk in src + bundle.resolve_depends(env)
]
else:
hunks = [
hunk,
]
hasher = self.hasher()
for hunk in hunks:
hasher.update(hunk.data())
return hasher.hexdigest()[:self.length]
def rss(xml):
if 'xmlns:wp' in xml:
raise InputError('WordPress dump')
def parse_date_time(stamp):
ts = parsedate_tz(stamp)
ts = mktime_tz(ts)
return datetime.fromtimestamp(ts)
def generate(item):
entry = {}
for k, v in iteritems({'title': 'title', 'date': 'pubDate',
'link': 'link', 'content': 'description'}):
try:
entry[k] = item.find(v).text if k != 'content' \
else unescape(item.find(v).text)
except (AttributeError, TypeError):
pass
if any(filter(lambda k: k not in entry, ['title', 'date', 'link', 'content'])):
raise AcrylamidException('invalid RSS 2.0 feed: provide at least title, ' \
+ 'link, content and pubDate!')
return {'title': entry['title'],
'content': entry['content'],
'date': parse_date_time(entry['date']),
'link': entry['link'],
'tags': [cat.text for cat in item.findall('category')]}
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
if tree.tag != 'rss' or tree.attrib.get('version') != '2.0':
raise InputError('no RSS 2.0 feed')
defaults = {'author': None}
channel = tree.getchildren()[0]
for k, v in iteritems({'title': 'sitename', 'link': 'www_root',
'language': 'lang', 'author': 'author'}):
try:
defaults[v] = channel.find(k).text
except AttributeError:
pass
return defaults, list(map(generate, channel.findall('item')))
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
if tree.tag != 'rss' or tree.attrib.get('version') != '2.0':
raise InputError('no RSS 2.0 feed')
defaults = {'author': None}
channel = tree.getchildren()[0]
for k, v in iteritems({'title': 'sitename', 'link': 'www_root',
'language': 'lang', 'author': 'author'}):
try:
defaults[v] = channel.find(k).text
except AttributeError:
pass
return defaults, list(map(generate, channel.findall('item')))
def rss(xml):
if 'xmlns:wp' in xml:
raise InputError('WordPress dump')
def parse_date_time(stamp):
ts = parsedate_tz(stamp)
ts = mktime_tz(ts)
return datetime.fromtimestamp(ts)
def generate(item):
entry = {}
for k, v in iteritems({
'title': 'title',
'date': 'pubDate',
'link': 'link',
'content': 'description'
}):
try:
entry[k] = item.find(v).text if k != 'content' \
else unescape(item.find(v).text)
except (AttributeError, TypeError):
pass
if any(
filter(lambda k: k not in entry,
['title', 'date', 'link', 'content'])):
raise AcrylamidException('invalid RSS 2.0 feed: provide at least title, ' \
+ 'link, content and pubDate!')
return {
'title': entry['title'],
'content': entry['content'],
'date': parse_date_time(entry['date']),
'link': entry['link'],
'tags': [cat.text for cat in item.findall('category')]
}
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
if tree.tag != 'rss' or tree.attrib.get('version') != '2.0':
raise InputError('no RSS 2.0 feed')
defaults = {'author': None}
channel = tree.getchildren()[0]
for k, v in iteritems({
'title': 'sitename',
'link': 'www_root',
'language': 'lang',
'author': 'author'
}):
try:
defaults[v] = channel.find(k).text
except AttributeError:
pass
return defaults, list(map(generate, channel.findall('item')))
try:
tree = ElementTree.fromstring(xml.encode('utf-8'))
except ElementTree.ParseError:
raise InputError('no well-formed XML')
if tree.tag != 'rss' or tree.attrib.get('version') != '2.0':
raise InputError('no RSS 2.0 feed')
defaults = {'author': None}
channel = tree.getchildren()[0]
for k, v in iteritems({
'title': 'sitename',
'link': 'www_root',
'language': 'lang',
'author': 'author'
}):
try:
defaults[v] = channel.find(k).text
except AttributeError:
pass
return defaults, list(map(generate, channel.findall('item')))
