def echo(*filenames):
"""
Parse and then print.
"""
for f in filenames:
doc = read_xml(f)
print ET.tostring(doc.getroot())
def _get_points(filename, node, the_class):
xpath = "./div[@class='%s']" % the_class
points = node.findall(xpath)
if not points:
return None
points = points[0].findall(".//ul")
assert len(points) == 1, \
'No list of type %s in section' % the_class
points = points[0]
points.tail = ''
return ET.tostring(points)
def _sections(filename, doc):
for s in doc.findall(".//section"):
title = _get_section_title(s)
if title is None:
continue
title = ET.tostring(title)
understand = _get_points(filename, s, 'understand')
keypoints = _get_points(filename, s, 'keypoints')
if (not understand) and (not keypoints):
continue
assert understand and keypoints, \
'Section %s in %s has understanding/keypoints mis-match' % (title, filename)
print ' <a href="%s#%s">%s</a>' % \
(filename, s.attrib.get('id'), title)
print '<p><strong>Understand:</strong></p>%s\n<p><strong>Summary:</strong></p>%s' % \
(understand, keypoints)
def ideas(*filenames):
"""
Extract ideas from files and display in groups.
"""
all_ideas = {}
for f in filenames:
doc = read_xml(f)
for section in doc.findall(".//div[@class='keypoints']"):
for example in section.findall(".//li[@idea]"):
ideas = example.attrib['idea'].split(';')
del example.attrib['idea']
example.tag = 'a'
example.attrib['href'] = '%s#%s' % (f, section.attrib.get('id'))
example.tail = ''
for i in ideas:
if i not in all_ideas:
all_ideas[i] = []
all_ideas[i].append(ET.tostring(example))
for idea in all_ideas:
print '<h2>%s</h2>' % idea
print '<ul>'
for item in all_ideas[idea]:
print ' <li>%s</li>' % item
print '</ul>'
def _lecture(filename, doc):
title = doc.findall(".//div[@class='title']")[0]
title.text = title.text.strip()
title.tag = 'h2'
title.tail = ''
print '<a href="%s">%s</a>' % (filename, ET.tostring(title))