def parse_post(self, entry):
# parse the dates first.
updated = parse_iso8601(entry.findtext(atom.updated))
published = entry.findtext(atom.published)
if published is not None:
published = parse_iso8601(published)
else:
published = updated
# figure out tags and categories by invoking the
# callbacks on the extensions first. If no extension
# was able to figure out what to do with it, we treat it
# as category.
tags, categories = self.parse_categories(entry)
link = entry.find(atom.link)
if link is not None:
link = link.attrib.get('href')
post_parser = _pickle(entry.findall(textpress.data)[0].text).get('parser', 'html')
if post_parser not in get_application().parsers:
post_parser = 'html'
post = Post(
entry.findtext(textpress.slug), # slug
_get_text_content(entry.findall(atom.title)), # title
link, # link
published, # pub_date
self.parse_author(entry), # author
# XXX: the Post is prefixing the intro before the actual
# content. This is the default Zine behavior and makes sense
# for Zine. However nearly every blog works differently and
# treats summary completely different from content. We should
# think about that.
_get_html_content(entry.findall(atom.summary)), # intro
_get_html_content(entry.findall(atom.content)), # body
tags, # tags
categories, # categories
parser=post_parser,
updated=updated,
uid=entry.findtext(atom.id)
)
post.element = entry
content_type = entry.findtext(textpress.content_type)
if content_type not in ('page', 'entry'):
post.content_type = 'entry'
# now parse the comments for the post
self.parse_comments(post)
for extension in self.extensions:
extension.postprocess_post(post)
return post
def parse_post(self, entry):
# parse the dates first.
updated = parse_iso8601(entry.findtext(atom.updated))
published = entry.findtext(atom.published)
if published is not None:
published = parse_iso8601(published)
else:
published = updated
# figure out tags and categories by invoking the
# callbacks on the extensions first. If no extension
# was able to figure out what to do with it, we treat it
# as category.
tags, categories = self.parse_categories(entry)
link = entry.find(atom.link)
if link is not None:
link = link.attrib.get('href')
post = Post(
None,
_get_text_content(entry.findall(atom.title)),
link,
published,
self.parse_author(entry),
# XXX: the Post is prefixing the intro before the actual
# content. This is the default Zine behavior and makes sense
# for Zine. However nearly every blog works differently and
# treats summary completely different from content. We should
# think about that.
None,
_get_html_content(entry.findall(atom.content)),
tags,
categories,
parser='html',
updated=updated,
uid=entry.findtext(atom.id)
)
post.element = entry
# now parse the comments for the post
self.parse_comments(post)
for extension in self.extensions:
try:
extension.postprocess_post(post)
except SkipItem:
return None
return post
def parse_post(self, entry):
# parse the dates first.
updated = parse_iso8601(entry.findtext(atom.updated))
published = entry.findtext(atom.published)
if published is not None:
published = parse_iso8601(published)
else:
published = updated
# figure out tags and categories by invoking the
# callbacks on the extensions first. If no extension
# was able to figure out what to do with it, we treat it
# as category.
tags, categories = self.parse_categories(entry)
link = entry.find(atom.link)
if link is not None:
link = link.attrib.get('href')
post = Post(
None,
_get_text_content(entry.findall(atom.title)),
link,
published,
self.parse_author(entry),
# XXX: the Post is prefixing the intro before the actual
# content. This is the default Zine behavior and makes sense
# for Zine. However nearly every blog works differently and
# treats summary completely different from content. We should
# think about that.
None,
_get_html_content(entry.findall(atom.content)),
tags,
categories,
parser='html',
updated=updated,
uid=entry.findtext(atom.id))
post.element = entry
# now parse the comments for the post
self.parse_comments(post)
for extension in self.extensions:
try:
extension.postprocess_post(post)
except SkipItem:
return None
return post
def parse_comments(self, post):
comments = {}
unresolved_parents = {}
for element in post.element.findall(zine.comment):
author = element.find(zine.author)
dependency = author.attrib.get('dependency')
if dependency is not None:
author = self._get_author(dependency)
email = www = None
else:
email = author.findtext(zine.email)
www = author.findtext(zine.uri)
author = author.findtext(zine.name)
body = _get_html_content(element.findall(zine.content))
comment = Comment(author, body, email, www, None,
parse_iso8601(element.findtext(zine.published)),
element.findtext(zine.submitter_ip), 'html',
_to_bool(element.findtext(zine.is_pingback)),
int(element.findtext(zine.status)),
element.findtext(zine.blocked_msg),
_parser_data(element.findtext(zine.parser_data)))
comments[int(element.attrib['id'])] = comment
parent = element.findtext(zine.parent)
if parent:
unresolved_parents[comment] = int(parent)
for comment, parent_id in unresolved_parents.iteritems():
comment.parent = comments[parent_id]
return comments.values()
def parse_comments(self, post):
comments = {}
unresolved_parents = {}
for element in post.element.findall(zine.comment):
author = element.find(zine.author)
dependency = author.attrib.get('dependency')
if dependency is not None:
author = self._get_author(dependency)
email = www = None
else:
email = author.findtext(zine.email)
www = author.findtext(zine.uri)
author = author.findtext(zine.name)
body = _get_html_content(element.findall(zine.content))
comment = Comment(author, body, email, www, None,
parse_iso8601(element.findtext(zine.published)),
element.findtext(zine.submitter_ip), 'html',
_to_bool(element.findtext(zine.is_pingback)),
int(element.findtext(zine.status)),
element.findtext(zine.blocked_msg),
_parser_data(element.findtext(zine.parser_data)))
comments[int(element.attrib['id'])] = comment
parent = element.findtext(zine.parent)
if parent:
unresolved_parents[comment] = int(parent)
for comment, parent_id in unresolved_parents.iteritems():
comment.parent = comments[parent_id]
return comments.values()
def __init__(self, timestamp, level, location, module, message=None):
self.timestamp = parse_iso8601(timestamp)
self.level = gettext(level)
self.internal_level = level
self.location = location
self.module = module
self.lines = []
if message is not None:
self.lines.append(message)
def __init__(self, timestamp, level, location, module, message=None):
self.timestamp = parse_iso8601(timestamp)
self.level = gettext(level)
self.internal_level = level
self.location = location
self.module = module
self.lines = []
if message is not None:
self.lines.append(message)
def parse_comments(self, post):
comments = {}
unresolved_parents = {}
for element in post.element.findall(textpress.comment):
author = element.find(textpress.author)
dependency = author.attrib.get('dependency')
if dependency is not None:
author = self._get_author(author)
email = www = None
else:
email = author.findtext(textpress.email)
www = author.findtext(textpress.uri)
author = author.findtext(textpress.name)
body = element.findall(textpress.data)
if body:
pickled = _pickle(body[0].text)
body = pickled.get('raw_body', u'')
comment_parser = pickled.get('parser', 'html')
if comment_parser not in get_application().parsers:
comment_parser = 'html'
comment = Comment(
author, body, email, www, None,
parse_iso8601(element.findtext(textpress.published)),
element.findtext(textpress.submitter_ip), comment_parser,
_to_bool(element.findtext(textpress.is_pingback)),
int(element.findtext(textpress.status)),
element.findtext(textpress.blocked_msg),
_parser_data(element.findtext(textpress.parser_data))
)
comments[int(element.findtext(textpress.id))] = comment
parent = element.findtext(textpress.parent)
if parent is not None or '':
unresolved_parents[comment] = int(parent)
for comment, parent_id in unresolved_parents.iteritems():
comment.parent = comments[parent_id]
return comments.values()
