def parse_html_lxml(html):
'parses a logfile with lxml'
messages = []
doc = lxml.html.document_fromstring(html, parser = lxmlparser())
for div in doc.xpath('//html/body/div'):
try:
message_type = div.attrib.get('class', '')
if not 'message' in message_type:
continue
message_type = message_type.replace('message', '').strip()
if not message_type in ('incoming', 'outgoing'):
continue
buddyname = div.find_class('buddy')[0].text
timestamp = div.attrib.get('timestamp')
if timestamp is not None:
timestamp = parse_timestamp(timestamp)
message = render_contents(div.find_class('msgcontent')[0])
auto = boolify(div.attrib.get('auto', 'false'))
except Exception:
print_exc()
else:
messages.append(Message(buddy = S(name=buddyname),
timestamp = timestamp,
message = message,
type = message_type,
auto = auto,
has_autotext = auto,
))
return messages
def from_xml(self, x):
atomget = lambda k, default=None: getattr(
x, '{%s}%s' % (constants.NS.Atom, k), default)
id = unicode(atomget('id') or '')
title = unicode(atomget('title') or '')
author_tag = atomget('author')
if author_tag is None:
author_name = author_id = author_url = author_tag
else:
author_name = unicode(author_tag.name)
author_id = author_url = unicode(author_tag.uri)
source_tag = atomget('source')
if source_tag is None:
source = None
else:
source = ActivitySource()
source.populate(source_tag, InputType.XML)
icon_url = None
preview_url = None
url = None
links = atomget('link', [])
for link in links:
rel = link.attrib.get('rel')
if rel == 'icon':
icon_url = unicode(link.attrib.get('href'))
if rel == 'preview':
preview_url = unicode(link.attrib.get('href'))
if rel == 'alternate' and url is None:
url = unicode(link.attrib.get('href'))
contents = []
for content in atomget('content', []):
contents.append((unicode(content.attrib.get('type')),
htmlutils.render_contents(content)))
self.__dict__.update(
id=id,
title=title,
author_id=author_id,
author_url=author_url,
author_name=author_name,
source=source,
url=url,
icon_url=icon_url,
preview_url=preview_url,
contents=contents,
)
def from_xml(self, x):
atomget = lambda k, default=None: getattr(x, "{%s}%s" % (constants.NS.Atom, k), default)
id = unicode(atomget("id") or "")
title = unicode(atomget("title") or "")
author_tag = atomget("author")
if author_tag is None:
author_name = author_id = author_url = author_tag
else:
author_name = unicode(author_tag.name)
author_id = author_url = unicode(author_tag.uri)
source_tag = atomget("source")
if source_tag is None:
source = None
else:
source = ActivitySource()
source.populate(source_tag, InputType.XML)
icon_url = None
preview_url = None
url = None
links = atomget("link", [])
for link in links:
rel = link.attrib.get("rel")
if rel == "icon":
icon_url = unicode(link.attrib.get("href"))
if rel == "preview":
preview_url = unicode(link.attrib.get("href"))
if rel == "alternate" and url is None:
url = unicode(link.attrib.get("href"))
contents = []
for content in atomget("content", []):
contents.append((unicode(content.attrib.get("type")), htmlutils.render_contents(content)))
self.__dict__.update(
id=id,
title=title,
author_id=author_id,
author_url=author_url,
author_name=author_name,
source=source,
url=url,
icon_url=icon_url,
preview_url=preview_url,
contents=contents,
)
def parse_html_lxml(html):
'parses a logfile with lxml'
messages = []
doc = lxml.html.document_fromstring(html, parser=lxmlparser())
for div in doc.xpath('//html/body/div'):
try:
message_type = div.attrib.get('class', '')
if not 'message' in message_type:
continue
message_type = message_type.replace('message', '').strip()
if not message_type in ('incoming', 'outgoing'):
continue
buddyname = div.find_class('buddy')[0].text
timestamp = div.attrib.get('timestamp')
if timestamp is not None:
timestamp = parse_timestamp(timestamp)
message = render_contents(div.find_class('msgcontent')[0])
auto = boolify(div.attrib.get('auto', 'false'))
except Exception:
print_exc()
else:
messages.append(
Message(
buddy=S(name=buddyname),
timestamp=timestamp,
message=message,
type=message_type,
auto=auto,
has_autotext=auto,
))
return messages
def tree_to_string(tree):
return render_contents(tree)
def tree_to_string(tree):
return render_contents(tree)
