def set_fields_xblock(self, path_to_file):
path_index_page = 'index.html'
try:
tree = ET.parse('{}/imsmanifest.xml'.format(path_to_file))
except IOError:
pass
else:
namespace = ''
for node in [node for _, node in ET.iterparse('{}/imsmanifest.xml'.format(path_to_file), events=['start-ns'])]:
if node[0] == '':
namespace = node[1]
break
root = tree.getroot()
if namespace:
resource = root.find('{{{0}}}resources/{{{0}}}resource'.format(namespace))
schemaversion = root.find('{{{0}}}metadata/{{{0}}}schemaversion'.format(namespace))
else:
resource = root.find('resources/resource')
schemaversion = root.find('metadata/schemaversion')
if resource:
path_index_page = resource.get('href')
if (not schemaversion is None) and (re.match('^1.2$', schemaversion.text) is None):
self.version_scorm = 'SCORM_2004'
self.scorm_file = os.path.join(settings.PROFILE_IMAGE_BACKEND['options']['base_url'],
'{}/{}'.format(self.location.block_id, path_index_page))
python类iterparse()的实例源码
def process_file(self, file_name):
data = self.read_file(file_name, self.encoding)
data = self.preprocess_data(data)
try:
stream = IO_Stream(bytearray("\n".join(data), encoding="utf-8"))
self.tree = ET.iterparse(stream)
if self._strip_namespace:
for _, element in self.tree:
element.tag = element.tag.rpartition("}")[-1]
except Exception as e:
print(self._current_file)
print_error_context(str(e), "\n".join(data).split("\n"))
raise e
self.process_tree(self.tree)
def __xml_iter(file, tag):
"""
:param file: xml ????.
:param tag: ???????? ???.
:return: ??? ???????? ? ????????? ?????? ? xml.
"""
return (elem for event, elem in etree.iterparse(file, events=['end']) if event == 'end' and elem.tag == tag)
def parse_and_remove(filename, path):
path_parts = path.split('/')
doc = iterparse(filename, ('start', 'end'))
# Skip the root element
next(doc)
tag_stack = []
elem_stack = []
for event, elem in doc:
if event == 'start':
tag_stack.append(elem.tag)
elem_stack.append(elem)
elif event == 'end':
if tag_stack == path_parts:
yield elem
elem_stack[-2].remove(elem)
try:
tag_stack.pop()
elem_stack.pop()
except IndexError:
pass
# Find zip code with most potholes
def iterators():
"""
Test iterators.
>>> e = ET.XML("<html><body>this is a <i>paragraph</i>.</body>..</html>")
>>> summarize_list(e.iter())
['html', 'body', 'i']
>>> summarize_list(e.find("body").iter())
['body', 'i']
>>> summarize(next(e.iter()))
'html'
>>> "".join(e.itertext())
'this is a paragraph...'
>>> "".join(e.find("body").itertext())
'this is a paragraph.'
>>> next(e.itertext())
'this is a '
Method iterparse should return an iterator. See bug 6472.
>>> sourcefile = serialize(e, to_string=False)
>>> next(ET.iterparse(sourcefile)) # doctest: +ELLIPSIS
('end', <Element 'i' at 0x...>)
>>> tree = ET.ElementTree(None)
>>> tree.iter()
Traceback (most recent call last):
AttributeError: 'NoneType' object has no attribute 'iter'
"""
def iterators():
"""
Test iterators.
>>> e = ET.XML("<html><body>this is a <i>paragraph</i>.</body>..</html>")
>>> summarize_list(e.iter())
['html', 'body', 'i']
>>> summarize_list(e.find("body").iter())
['body', 'i']
>>> summarize(next(e.iter()))
'html'
>>> "".join(e.itertext())
'this is a paragraph...'
>>> "".join(e.find("body").itertext())
'this is a paragraph.'
>>> next(e.itertext())
'this is a '
Method iterparse should return an iterator. See bug 6472.
>>> sourcefile = serialize(e, to_string=False)
>>> next(ET.iterparse(sourcefile)) # doctest: +ELLIPSIS
('end', <Element 'i' at 0x...>)
>>> tree = ET.ElementTree(None)
>>> tree.iter()
Traceback (most recent call last):
AttributeError: 'NoneType' object has no attribute 'iter'
"""
def iterators():
"""
Test iterators.
>>> e = ET.XML("<html><body>this is a <i>paragraph</i>.</body>..</html>")
>>> summarize_list(e.iter())
['html', 'body', 'i']
>>> summarize_list(e.find("body").iter())
['body', 'i']
>>> summarize(next(e.iter()))
'html'
>>> "".join(e.itertext())
'this is a paragraph...'
>>> "".join(e.find("body").itertext())
'this is a paragraph.'
>>> next(e.itertext())
'this is a '
Method iterparse should return an iterator. See bug 6472.
>>> sourcefile = serialize(e, to_string=False)
>>> next(ET.iterparse(sourcefile)) # doctest: +ELLIPSIS
('end', <Element 'i' at 0x...>)
>>> tree = ET.ElementTree(None)
>>> tree.iter()
Traceback (most recent call last):
AttributeError: 'NoneType' object has no attribute 'iter'
"""
def getDataFromExternal2(self, xmltvFile, date, ch_list, progress_callback=None):
if xbmcvfs.exists(xmltvFile):
f = FileWrapper(xmltvFile)
if f:
context = ElementTree.iterparse(f, events=("start", "end"))
size = f.size
return self.parseXMLTV(context, f, size, self.logoFolder, progress_callback)
def ensure_elementtree_imported(verbosity, logfile):
global ET, ET_has_iterparse, Element_has_iter
if ET is not None:
return
if "IronPython" in sys.version:
import xml.etree.ElementTree as ET
#### 2.7.2.1: fails later with
#### NotImplementedError: iterparse is not supported on IronPython. (CP #31923)
else:
try: import xml.etree.cElementTree as ET
except ImportError:
try: import cElementTree as ET
except ImportError:
try: import lxml.etree as ET
except ImportError:
try: import xml.etree.ElementTree as ET
except ImportError:
try: import elementtree.ElementTree as ET
except ImportError:
raise Exception("Failed to import an ElementTree implementation")
if hasattr(ET, 'iterparse'):
_dummy_stream = BYTES_IO(b'')
try:
ET.iterparse(_dummy_stream)
ET_has_iterparse = True
except NotImplementedError:
pass
Element_has_iter = hasattr(ET.ElementTree, 'iter')
if verbosity:
etree_version = repr([
(item, getattr(ET, item))
for item in ET.__dict__.keys()
if item.lower().replace('_', '') == 'version'
])
print(ET.__file__, ET.__name__, etree_version, ET_has_iterparse, file=logfile)
def own_process_stream(self, stream, heading=None):
if self.verbosity >= 2 and heading is not None:
fprintf(self.logfile, "\n=== %s ===\n", heading)
getmethod = self.tag2meth.get
row_tag = U_SSML12 + "row"
self_do_row = self.do_row
for event, elem in ET.iterparse(stream):
if elem.tag == row_tag:
self_do_row(elem)
elem.clear() # destroy all child elements (cells)
elif elem.tag == U_SSML12 + "dimension":
self.do_dimension(elem)
elif elem.tag == U_SSML12 + "mergeCell":
self.do_merge_cell(elem)
self.finish_off()
def tcx_parser(fh):
it = ElementTree.iterparse(fh, events=('start','end'))
# look for the start TrainingCenterDatabase tag to fail fast
for event, elem in it:
if event == 'start' and elem.tag.endswith('}TrainingCenterDatabase'):
break
else:
raise ValueError('Not a tcx file: %s' % fh.name)
# do the main parse
for event, elem in it:
if event == 'end' and elem.tag.endswith('}Trackpoint'):
latlon = None
elev = np.nan
time = None
for child in elem:
tag_name = child.tag.rsplit('}', 1)[1]
if tag_name == 'Time':
time = child.text
elif tag_name == 'AltitudeMeters':
elev = float(child.text)
elif tag_name == 'Position':
vals = dict((c.tag.rsplit('}', 1)[1], float(c.text)) for c in child)
latlon = (vals['LatitudeDegrees'], vals['LongitudeDegrees'])
if latlon is not None:
yield latlon, time, elev
elem.clear()
def ensure_elementtree_imported(verbosity, logfile):
global ET, ET_has_iterparse, Element_has_iter
if ET is not None:
return
if "IronPython" in sys.version:
import xml.etree.ElementTree as ET
#### 2.7.2.1: fails later with
#### NotImplementedError: iterparse is not supported on IronPython. (CP #31923)
else:
try: import xml.etree.cElementTree as ET
except ImportError:
try: import cElementTree as ET
except ImportError:
try: import lxml.etree as ET
except ImportError:
try: import xml.etree.ElementTree as ET
except ImportError:
try: import elementtree.ElementTree as ET
except ImportError:
raise Exception("Failed to import an ElementTree implementation")
if hasattr(ET, 'iterparse'):
_dummy_stream = BYTES_IO(b'')
try:
ET.iterparse(_dummy_stream)
ET_has_iterparse = True
except NotImplementedError:
pass
Element_has_iter = hasattr(ET.ElementTree, 'iter')
if verbosity:
etree_version = repr([
(item, getattr(ET, item))
for item in ET.__dict__.keys()
if item.lower().replace('_', '') == 'version'
])
print(ET.__file__, ET.__name__, etree_version, ET_has_iterparse, file=logfile)
def own_process_stream(self, stream, heading=None):
if self.verbosity >= 2 and heading is not None:
fprintf(self.logfile, "\n=== %s ===\n", heading)
getmethod = self.tag2meth.get
row_tag = U_SSML12 + "row"
self_do_row = self.do_row
for event, elem in ET.iterparse(stream):
if elem.tag == row_tag:
self_do_row(elem)
elem.clear() # destroy all child elements (cells)
elif elem.tag == U_SSML12 + "dimension":
self.do_dimension(elem)
elif elem.tag == U_SSML12 + "mergeCell":
self.do_merge_cell(elem)
self.finish_off()
def ensure_elementtree_imported(verbosity, logfile):
global ET, ET_has_iterparse, Element_has_iter
if ET is not None:
return
if "IronPython" in sys.version:
import xml.etree.ElementTree as ET
#### 2.7.2.1: fails later with
#### NotImplementedError: iterparse is not supported on IronPython. (CP #31923)
else:
try: import xml.etree.cElementTree as ET
except ImportError:
try: import cElementTree as ET
except ImportError:
try: import lxml.etree as ET
except ImportError:
try: import xml.etree.ElementTree as ET
except ImportError:
try: import elementtree.ElementTree as ET
except ImportError:
raise Exception("Failed to import an ElementTree implementation")
if hasattr(ET, 'iterparse'):
_dummy_stream = BYTES_IO(b'')
try:
ET.iterparse(_dummy_stream)
ET_has_iterparse = True
except NotImplementedError:
pass
Element_has_iter = hasattr(ET.ElementTree, 'iter')
if verbosity:
etree_version = repr([
(item, getattr(ET, item))
for item in ET.__dict__.keys()
if item.lower().replace('_', '') == 'version'
])
print(ET.__file__, ET.__name__, etree_version, ET_has_iterparse, file=logfile)
def own_process_stream(self, stream, heading=None):
if self.verbosity >= 2 and heading is not None:
fprintf(self.logfile, "\n=== %s ===\n", heading)
getmethod = self.tag2meth.get
row_tag = U_SSML12 + "row"
self_do_row = self.do_row
for event, elem in ET.iterparse(stream):
if elem.tag == row_tag:
self_do_row(elem)
elem.clear() # destroy all child elements (cells)
elif elem.tag == U_SSML12 + "dimension":
self.do_dimension(elem)
elif elem.tag == U_SSML12 + "mergeCell":
self.do_merge_cell(elem)
self.finish_off()
def detect_xspf_header(data):
data = data[0:150]
if b'xspf' not in data.lower():
return False
try:
data = io.BytesIO(data)
for event, element in elementtree.iterparse(data, events=(b'start',)):
return element.tag.lower() == '{http://xspf.org/ns/0/}playlist'
except elementtree.ParseError:
pass
return False
def detect_asx_header(data: bytes):
data = data[0:50]
if b'asx' not in data.lower():
return False
try:
bytesIO = io.BytesIO(data)
for event, element in elementtree.iterparse(bytesIO, events=(b'start',)):
return element.tag.lower() == 'asx'
except elementtree.ParseError:
pass
return False
def parse_xspf(data: bytes):
try:
# Last element will be root.
element = None
for event, element in elementtree.iterparse(io.BytesIO(data)):
element.tag = element.tag.lower() # normalize
if element is not None:
ns = 'http://xspf.org/ns/0/'
for track in element.iterfind('{%s}tracklist/{%s}track' % (ns, ns)):
yield track.findtext('{%s}location' % ns)
except elementtree.ParseError:
return
def parse_asx(data):
try:
# Last element will be root.
element = None
for event, element in elementtree.iterparse(io.BytesIO(data)):
element.tag = element.tag.lower() # normalize
if element is not None:
for ref in element.findall('entry/ref[@href]'):
yield ref.get('href', '').strip()
for entry in element.findall('entry[@href]'):
yield entry.get('href', '').strip()
except elementtree.ParseError:
return
def ensure_elementtree_imported(verbosity, logfile):
global ET, ET_has_iterparse, Element_has_iter
if ET is not None:
return
if "IronPython" in sys.version:
import xml.etree.ElementTree as ET
#### 2.7.2.1: fails later with
#### NotImplementedError: iterparse is not supported on IronPython. (CP #31923)
else:
try: import xml.etree.cElementTree as ET
except ImportError:
try: import cElementTree as ET
except ImportError:
try: import lxml.etree as ET
except ImportError:
try: import xml.etree.ElementTree as ET
except ImportError:
try: import elementtree.ElementTree as ET
except ImportError:
raise Exception("Failed to import an ElementTree implementation")
if hasattr(ET, 'iterparse'):
_dummy_stream = BYTES_IO(b'')
try:
ET.iterparse(_dummy_stream)
ET_has_iterparse = True
except NotImplementedError:
pass
Element_has_iter = hasattr(ET.ElementTree, 'iter')
if verbosity:
etree_version = repr([
(item, getattr(ET, item))
for item in ET.__dict__.keys()
if item.lower().replace('_', '') == 'version'
])
print(ET.__file__, ET.__name__, etree_version, ET_has_iterparse, file=logfile)
