def postproc(file):
# Share
file.set_value("share", ["everybody"])
# Title
if file.class_id != "webpage":
return
handler = file.get_handler()
events = handler.events
elem = get_element(events, "h1")
if elem:
title = [unicode(x[1], "utf8") for x in elem.get_content_elements() if x[0] == TEXT]
if title[-1] == u"¶":
title.pop()
title = u"".join(title)
file.set_property("title", title, language)
handler.events = events[: elem.start] + events[elem.end + 1 :]
def postproc(file):
# Share
file.set_value('share', ['everybody'])
# Title
if file.class_id != 'webpage':
return
handler = file.get_handler()
events = handler.events
elem = get_element(events, 'h1')
if elem:
title = [
unicode(x[1], 'utf8')
for x in elem.get_content_elements() if x[0] == TEXT ]
if title[-1] == u'¶':
title.pop()
title = u''.join(title)
file.set_property('title', title, language)
handler.events = events[:elem.start] + events[elem.end+1:]
def postproc(file):
# Share
file.set_value('share', ['everybody'])
# Title
if file.class_id != 'webpage':
return
handler = file.get_handler()
events = handler.events
elem = get_element(events, 'h1')
if elem:
title = [
unicode(x[1], 'utf8')
for x in elem.get_content_elements() if x[0] == TEXT ]
if title[-1] == u'¶':
title.pop()
title = u''.join(title)
file.set_property('title', title, language)
handler.events = events[:elem.start] + events[elem.end+1:]
def filter(path, mimetype, body):
# HTML
if mimetype == 'text/html':
source = XHTMLFile(string=body)
target = XHTMLFile()
elem = get_element(source.events, 'div', **{'class': 'body'})
if not elem:
print 'E', path
return None
elements = elem.get_content_elements()
elements = rewrite_uris(elements, rewrite)
elements = list(elements)
target.set_body(elements)
return target.to_str()
# Skip
elif mimetype in skip:
return None
# Keep
elif mimetype in keep:
return body
# Unknown
else:
print 'X', path, mimetype
return body
def filter(path, mimetype, body):
# HTML
if mimetype == 'text/html':
source = XHTMLFile(string=body)
target = XHTMLFile()
elem = get_element(source.events, 'div', **{'class': 'body'})
if not elem:
print 'E', path
return None
elements = elem.get_content_elements()
elements = rewrite_uris(elements, rewrite)
elements = list(elements)
target.set_body(elements)
return target.to_str()
# Skip
elif mimetype in skip:
return None
# Keep
elif mimetype in keep:
return body
# Unknown
else:
print 'X', path, mimetype
return body
def filter(path, mimetype, body):
# HTML
if mimetype == "text/html":
source = XHTMLFile(string=body)
target = XHTMLFile()
elem = get_element(source.events, "div", **{"class": "body"})
if not elem:
print "E", path
return None
elements = elem.get_content_elements()
elements = rewrite_uris(elements, rewrite)
elements = list(elements)
target.set_body(elements)
return target.to_str()
# Skip
elif mimetype in skip:
return None
# Keep
elif mimetype in keep:
return body
# Unknown
else:
print "X", path, mimetype
return body
def get_body(self):
"""Returns the body element.
"""
return get_element(self.events, 'body')
def get_head(self):
"""Returns the head element.
"""
return get_element(self.events, 'head')
