Python ElementTree.find方法代码示例

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
class Parser(object):

    def __init__(self, template_name):
        self.template_name = template_name
        self.file_path = join(TEMPLATE_PATH, self.template_name)
        self.doc = ElementTree(file = self.file_path)
        
    def _onepage_metadata(self):
        self.onepage_dict = {}	
        page = {'page': int(self.doc.find('OnePage').attrib['page'])}
        self.onepage_dict.update(page)
        for elem in self.doc.iterfind('OnePage/metadata'):
            for sub_elem in list(elem):
                key = elem.attrib['id'] + '_' + sub_elem.tag
                value = sub_elem.text.encode('utf-8')
                if value.isdigit():
                    value = int(value)
                elif '\\n' in value:
                    value = value.replace('\\n', '\n').split(',')
                else:
                    value = value.split(',')
                self.onepage_dict.update({key: value})
        return self.onepage_dict
		
    def _variouspages_metadata(self):
        self.variouspages_dict = {}
        various_pages = self.doc.find('VariousPages')
        if various_pages is not None:
            first_page = int(self.doc.find('VariousPages').attrib['startpage'])
            end_page = int(self.doc.find('VariousPages').attrib['endpage'])
            pages_parse = [first_page, end_page]
            pages = {'pages': pages_parse}
            self.variouspages_dict.update(pages)
            for elem in self.doc.iterfind('VariousPages/metadata'):
                for sub_elem in list(elem):
                    key = elem.attrib['id'] + '_' + sub_elem.tag
                    value = sub_elem.text.encode('utf-8')
                    if value.isdigit():
                        value = int(value)
                    elif '\\n' in value:
                        value = value.replace('\\n', '\n').split(',')
                    else:
                        value = value.split(',')    
                    self.variouspages_dict.update({key: value})
        return self.variouspages_dict

    def xml_template_metadata(self):
        onepage_metadata = self._onepage_metadata()
        variouspages_metadata = self._variouspages_metadata()
        onepage_metadata.update(variouspages_metadata)
        all_template_metadata = onepage_metadata
        return all_template_metadata

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
    def produce_settings_file(self, printer):
        printer_name = printer['name']
        
        tree = ElementTree()
        tree.parse(StringIO(XML_TEMPLATE.replace('\n', '').replace('\r', '').replace('\t', '')))

        name_node = tree.find('name')
        name_node.text = 'AirPrint %s @ %%h' % printer_name

        service_node = tree.find('service')

        port_node = service_node.find('port')
        port_node.text = '%d' % printer['port']
        
        host = printer['host']
        if host:
            if self.dnsdomain:
                pair = host.rsplit('.', 1)
                if len(pair) > 1:
                    host = '.'.join((pair[0], self.dnsdomain))
            service_node.append(self.new_node('host-name', host))

        txt = printer['txt']
        for key in txt:
            if self.adminurl or key != 'adminurl':
                service_node.append(self.new_txtrecord_node('%s=%s' % (key, txt[key])))

        source = printer['SOURCE'] if printer.has_key('SOURCE') else ''

        fname = '%s%s%s.service' % (self.prefix, '%s-' % source if len(source) > 0 else '', printer_name)
        
        if self.directory:
            fname = os.path.join(self.directory, fname)
        
        f = open(fname, 'w')

        if etree:
            tree.write(f, pretty_print=True, xml_declaration=True, encoding="UTF-8")
        else:
            xmlstr = tostring(tree.getroot())
            doc = parseString(xmlstr)
            dt= minidom.getDOMImplementation('').createDocumentType('service-group', None, 'avahi-service.dtd')
            doc.insertBefore(dt, doc.documentElement)
            doc.writexml(f)
        f.close()
        
        if self.verbose:
            src = source if len(source) > 0 else 'unknown'
            sys.stderr.write('Created from %s: %s%s' % (src, fname, os.linesep))

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
  def getFirmwares(self):
#    print 'refreshing'
    url = urlparse(self.url)
    params =  '<?xml version="1.0" encoding="utf-8" ?>\n' +\
              '<D:propfind xmlns:D="DAV:">\n'+\
              '<D:allprop/>\n' +\
              '</D:propfind>'
    base64string = base64.encodestring('%s:%s' % (self.username, self.password))[:-1]
    authheader =  "Basic %s" % base64string
    headers = {
      "Content-Type" :  "application/xml; charset=\"utf-8\"",
      "Authorization": authheader,
      "Depth" : "1"}
    conn = httplib.HTTPConnection(url.netloc)
    conn.request("PROPFIND", url.path, params, headers)
    response = conn.getresponse()
    data = response.read()
    conn.close()

    if "Authorization Required" in data:
      self.authenticated = False
      return

    data_elements = HTML(data)
    xml_etree = ElementTree(data_elements)
    all_response_elements = xml_etree.findall("//response")
    self.folders = []
    for response in all_response_elements:
      resp_tree = ElementTree(response)
      if resp_tree.find('//collection') is None:
        uri = resp_tree.find("//href").text
        getcontentlength = getattr(resp_tree.find('//getcontentlength'), 'text', None)
        getlastmodified = getattr(resp_tree.find('//getlastmodified'), 'text', None)
        name = os.path.basename(uri)
        self.firmwares[name] = FirmWare(name,url.scheme+'://'+url.netloc+uri,getlastmodified,getcontentlength)
      else:
        self.folders.append(resp_tree.find("//href").text)

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
 def __init__(self, name):
     self.name = name
     tree = ElementTree(file = name)
     labels = tuple((elt.tag.strip(), elt.text.strip()) for elt in tree.find("labels"))
     self.labels = tuple(pair[0] for pair in labels)
     self.descrs = dict(labels)
     self.date = tree.getroot().get("date")
     for elt in tree.findall("validation_status"):
         status = elt.get("status")
         uri = elt.text.strip()
         if status.startswith("rsync_transfer_") or elt.get("generation") != "current":
             continue
         if uri not in self:
             self[uri] = Object(self, uri)
         self[uri].add(status)

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
class H248Message:
	def __init__(self, msg):
		self.msg = msg
		self.xml = self.msg.asXML()
		self.tree = ElementTree(fromstring(self.xml))

	def xpath(self, path):
		elem = self.tree.find(path)
		if elem is None:
			raise InvalidXPath()
		return elem.text
	
	def abstract(self):
		return self.xml
	
	def __str__(self):
		return self.xml

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
def timeandweather():
    # If this ever dies, there's always Microsoft:
    # http://weather.service.msn.com/find.aspx?outputview=search&src=Windows7&weasearchstr=02139&weadegreetype=F&culture=en-US

    f = urllib.urlopen("http://weather.yahooapis.com/forecastrss?w=12758738&u=f")
    e = ElementTree(file=f)
    
    cond = e.find(".//{http://xml.weather.yahoo.com/ns/rss/1.0}condition")

    img = e.findtext(".//item/description")
    img = parse(StringIO("<doc>%s</doc>" % img)).find(".//img").get("src")

    # cond.get("text") is nice too
    return '<table class="weather" align="center" cellspacing="20"><tr><td>' + \
        "<h2>"+time.strftime("%l:%M %p<br />%b %e")+"</h2>" + \
        "</td><td>" + \
        '<img src="%s" /><h2>%s&deg;F</h2>' % (img, cond.get("temp")) + \
        "</td></tr></table>"

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
 def __init__(self, name):
   self.name = name
   tree = ElementTree(file = name)
   self.labels = [elt.tag.strip() for elt in tree.find("labels")]
   for elt in tree.findall("validation_status"):
     generation = elt.get("generation")
     status = elt.get("status")
     uri = elt.text.strip()
     if not show_rsync_transfer and status.startswith("rsync_transfer_"):
       continue
     if show_backup_generation:
       key = (uri, generation)
     elif generation == "backup":
       continue
     else:
       key = uri
     if key not in self:
       self[key] = Object(self, uri, generation)
     self[key].add(status)

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
    def get_committees(self, term, chamber, laws_year):
        committee_list = []

        committee_list_url = self.committee_list_url_template % laws_year
        list_page = ElementTree(lxml.html.fromstring(self.urlopen(committee_list_url)))
        com_select = list_page.find('//select[@name="P_COM_NM"]')

        for option in com_select.findall("option"):
            if option.text:
                committee_url = self.committee_url_template % (laws_year,
                                                               urllib.quote(option.text.strip()))
                c_chamber, name = option.text.split(" ", 1)
                c_chamber = c_chamber[1]
                if (('H' == c_chamber and 'lower' == chamber) or
                   ('S' == c_chamber and 'upper' == chamber)):
                    # committee = Committee(term['name'], chamber, name)
                    committee = Committee(chamber, name)
                    committee.add_source(committee_url)
                    committee_list.append(committee)
        return committee_list

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
def getterm(request, lang, code):
    params = urllib.urlencode({
        'tree_id': code or '',
        'lang': lang,
        })
    resource = urllib.urlopen(settings.DECS_SERVICE, params)

    tree = ElementTree()
    tree.parse(resource)

    result = tree.find("decsws_response/tree/self/term_list/term")
    if result is None:
        result = tree.findall('decsws_response/tree/term_list[@lang="%s"]/term' % lang)
        json = '[%s]' % ','.join((JSON_TERM % (r.text.capitalize(),r.attrib['tree_id']) for r in result))
    else:
        descriptors = tree.findall('decsws_response/record_list/record/descriptor_list/descriptor')
        description = ','.join(['"%s":"%s"'%(d.attrib['lang'],d.text) for d in descriptors])
        json = '[%s]' % (JSON_MULTILINGUAL_TERM % (description,result.attrib['tree_id']))
    
    return HttpResponse(json, mimetype='application/json')

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
    def load(self, path):
        parser = ElementTree(file=open(path, 'r'))
        circles = parser.find('circles')
        outline = parser.find('outline')

        bb = outline.find('bounding_box')
        bs = bb.find('width'), bb.find('height')
        w, h = [float(b.text) for b in bs]

        use_label = parser.find('use_label')
        if use_label is not None:
            use_label = to_bool(use_label.text.strip())
        else:
            use_label = True

        data = ArrayPlotData()
        p = Plot(data=data, padding=100)
        p.x_grid.visible = False
        p.y_grid.visible = False

        p.x_axis.visible = False
        p.y_axis.visible = False

        p.x_axis.title = 'X cm'
        p.y_axis.title = 'Y cm'

        # font = 'modern 22'
        # p.x_axis.title_font = font
        # p.x_axis.tick_label_font = font
        # p.y_axis.title_font = font
        # p.y_axis.tick_label_font = font
        #         p.x_axis_visible = False
        #         p.y_axis_visible = False
        p.index_range.low_setting = -w / 2
        p.index_range.high_setting = w / 2

        p.value_range.low_setting = -h / 2
        p.value_range.high_setting = h / 2

        thetas = linspace(0, 2 * pi)

        radius = circles.find('radius').text
        radius = float(radius)

        face_color = circles.find('face_color')
        if face_color is not None:
            face_color = face_color.text
        else:
            face_color = 'white'
        labels = []
        for i, pp in enumerate(circles.findall('point')):
            x, y, l = pp.find('x').text, pp.find('y').text, pp.find('label').text

            #             print i, pp, x, y
            # load hole specific attrs
            r = pp.find('radius')
            if r is None:
                r = radius
            else:
                r = float(r.text)

            fc = pp.find('face_color')
            if fc is None:
                fc = face_color
            else:
                fc = fc.text

            x, y = list(map(float, (x, y)))
            xs = x + r * sin(thetas)
            ys = y + r * cos(thetas)

            xn, yn = 'px{:03d}'.format(i), 'py{:03d}'.format(i)
            data.set_data(xn, xs)
            data.set_data(yn, ys)

            plot = p.plot((xn, yn),
                          face_color=fc,
                          type='polygon')[0]
            labels.append((x, y, l))
            # if use_label:
            #     label = myDataLabel(component=plot,
            #                         data_point=(x, y),
            #                         label_text=l,
            #                         bgcolor='transparent')
            #     plot.overlays.append(label)
        if use_label:
            p.overlays.append(LabelsOverlay(component=plot, labels=labels))

        self.container.add(p)
        self.container.invalidate_and_redraw()

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
        # encode the payload explicitly as UTF-8, since it contains chinese characters
        page_source = page_source.encode(encoding='UTF-8',errors='strict')

    html_file = open(html_filename, 'wb')
    html_file.write(page_source)
    html_file.close()
    print "Html retrieved successfully"

# decode the payload explicitly as UTF-8
html_content = open(html_filename).read()
if hasattr(html_content, 'decode'):
    html_content = html_content.decode('utf-8')

# search in the tree to find the elements containing the image url and the score
tree = ElementTree(lxml.html.document_fromstring(html_content))
element = tree.find("//div[@id='ColumnContainer']")
children = list(element)
print "Number of images:", len(children)
image_urls = []
scores = []
for child in children:
    image_element = child.find("./a")
    score_element = child.find(".//div[@class='d-name']")
    image_urls.append(image_element.get('href'))
    text_contents = score_element.text_content().split()
    scores.append(text_contents.pop(-1))

# dump the URLs to a file
images_filename = os.path.join(images_folder, 'all-images-url.pkl')
if not os.path.exists(images_filename):
    images_file = open(images_filename, 'wb')

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
    def load(self, path):
        parser = ElementTree(file=open(path, 'r'))
        circles = parser.find('circles')
        outline = parser.find('outline')

        bb = outline.find('bounding_box')
        bs = bb.find('width'), bb.find('height')
        w, h = map(lambda b:float(b.text), bs)


        data = ArrayPlotData()
        p = Plot(data=data)
        p.x_grid.visible = False
        p.y_grid.visible = False

        p.index_range.low_setting = -w / 2
        p.index_range.high_setting = w / 2

        p.value_range.low_setting = -h / 2
        p.value_range.high_setting = h / 2

        thetas = linspace(0, 2 * pi)

        radius = circles.find('radius').text
        radius = float(radius)

        face_color = circles.find('face_color')
        if face_color is not None:
            face_color = face_color.text
        else:
            face_color = 'white'

        for i, pp in enumerate(circles.findall('point')):
            x, y, l = pp.find('x').text, pp.find('y').text, pp.find('label').text

            # load hole specific attrs
            r = pp.find('radius')
            if r is None:
                r = radius
            else:
                r = float(r.text)

            fc = pp.find('face_color')
            if fc is None:
                fc = face_color
            else:
                fc = fc.text

            x, y = map(float, (x, y))
            xs = x + r * sin(thetas)
            ys = y + r * cos(thetas)

            xn, yn = 'px{:03n}'.format(i), 'py{:03n}'.format(i)
            data.set_data(xn, xs)
            data.set_data(yn, ys)

            plot = p.plot((xn, yn),
                   face_color=fc,
                   type='polygon',
                   )[0]

            label = myDataLabel(component=plot,
                              data_point=(x, y),
                              label_text=l,
                              bgcolor=fc
                              )
            plot.overlays.append(label)

        self.container.add(p)

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
    def parse(self, data):
        """ Parse a webdav reply. Retrieve any resources as objects
            and return them as a list.

            :param data: The webdav reply to parse
            :type data: String


            :return: self.response_objects

        """
        data_elements = HTML(data)
        xml_etree = ElementTree(data_elements)
        all_response_elements = xml_etree.findall("//response")
        for response in all_response_elements:
            new_response = Response()
            resp_tree = ElementTree(response)
            new_response.href = resp_tree.find('//href').text
            if resp_tree.find('//collection') is not None:
                new_response.resourcetype = 'collection'
            else:
                new_response.resourcetype = 'resource'
                new_response.executable = getattr(
                    resp_tree.find('//executable'), 'text', None)
            new_response.creationdate = getattr(
                resp_tree.find('//creationdate'), 'text', None)
            new_response.getcontentlength = getattr(
                resp_tree.find('//getcontentlength'), 'text', None)
            new_response.getlastmodified = getattr(
                resp_tree.find('//getlastmodified'), 'text', None)
            new_response.getetag = getattr(
                resp_tree.find('//getetag'), 'text', None)
            new_response.getcontenttype = getattr(
                resp_tree.find('//getcontenttype'), 'text', None)
            new_response.status = getattr(
                resp_tree.find('//status'), 'text', None)

            # Now we have the properties that are easy to get,
            # lets get the lock information
            lock_tree = resp_tree.findall('//lockentry')
            for lock in lock_tree:
                lock_tree = ElementTree(lock)
                lock_obj = Lock()
                lock_obj.locktype = lock_tree.find(
                    '//locktype').getchildren()[-1].tag
                lock_obj.lockscope = lock_tree.find(
                    '//lockscope').getchildren()[-1].tag
                new_response.locks.append(lock_obj)

            self.response_objects.append(new_response)

        return self.response_objects

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
    def generate(self):
        if not self.host:
            conn = cups.Connection()
        else:
            if not self.port:
                self.port = 631
            conn = cups.Connection(self.host, self.port)
            
        printers = conn.getPrinters()
        
        for p, v in printers.items():
            if v['printer-is-shared']:
                attrs = conn.getPrinterAttributes(p)
                uri = urlparse.urlparse(v['printer-uri-supported'])

                tree = ElementTree()
                tree.parse(StringIO(XML_TEMPLATE.replace('\n', '').replace('\r', '').replace('\t', '')))

                name = tree.find('name')
                name.text = 'AirPrint %s @ %%h' % (p)

                service = tree.find('service')

                port = service.find('port')
                port_no = None
                if hasattr(uri, 'port'):
                  port_no = uri.port
                if not port_no:
                    port_no = self.port
                if not port_no:
                    port_no = cups.getPort()
                port.text = '%d' % port_no

                if hasattr(uri, 'path'):
                  rp = uri.path
                else:
                  rp = uri[2]
                
                re_match = re.match(r'^//(.*):(\d+)(/.*)', rp)
                if re_match:
                  rp = re_match.group(3)
                
                #Remove leading slashes from path
                #TODO XXX FIXME I'm worried this will match broken urlparse
                #results as well (for instance if they don't include a port)
                #the xml would be malform'd either way
                rp = re.sub(r'^/+', '', rp)
                
                path = Element('txt-record')
                path.text = 'rp=%s' % (rp)
                service.append(path)

                desc = Element('txt-record')
                desc.text = 'note=%s' % (v['printer-info'])
                service.append(desc)

                product = Element('txt-record')
                product.text = 'product=(GPL Ghostscript)'
                service.append(product)

                state = Element('txt-record')
                state.text = 'printer-state=%s' % (v['printer-state'])
                service.append(state)

                ptype = Element('txt-record')
                ptype.text = 'printer-type=%s' % (hex(v['printer-type']))
                service.append(ptype)

                pdl = Element('txt-record')
                fmts = []
                defer = []

                for a in attrs['document-format-supported']:
                    if a in DOCUMENT_TYPES:
                        if DOCUMENT_TYPES[a]:
                            fmts.append(a)
                    else:
                        defer.append(a)

                if 'image/urf' not in fmts:
                    sys.stderr.write('image/urf is not in mime types, %s may not be available on ios6 (see https://github.com/tjfontaine/airprint-generate/issues/5)%s' % (p, os.linesep))

                fmts = ','.join(fmts+defer)

                dropped = []

                # TODO XXX FIXME all fields should be checked for 255 limit
                while len('pdl=%s' % (fmts)) >= 255:
                    (fmts, drop) = fmts.rsplit(',', 1)
                    dropped.append(drop)

                if len(dropped) and self.verbose:
                    sys.stderr.write('%s Losing support for: %s%s' % (p, ','.join(dropped), os.linesep))

                pdl.text = 'pdl=%s' % (fmts)
                service.append(pdl)

                if self.adminurl:
                    admin = Element('txt-record')
                    admin.text = 'adminurl=%s' % (v['printer-uri-supported'])
#.........这里部分代码省略.........

# 需要导入模块: from lxml.etree import ElementTree [as 别名]
# 或者: from lxml.etree.ElementTree import find [as 别名]
def genPrinterService(p,v,airprint):

	attrs = conn.getPrinterAttributes(p)
	uri = urlparse.urlparse(v['printer-uri-supported'])
	
	tree = ElementTree()
	tree.parse(StringIO(SERVICE_TEMPLATE.replace('\n', '').replace('\r', '').replace('\t', '')))

	name = tree.find('name')
	name.text = '%s @ %%h' % (p if not airprint else 'AirPrint ' + p)

	service = tree.find('service')
	
	# Add subtype to AirPrint service definitions
	if airprint:
		path = Element('subtype')
		path.text = "_universal._sub._ipp._tcp"
		service.append(path)


	port = service.find('port')
	port_no = None

	if hasattr(uri, 'port'): port_no = uri.port
	if not port_no: port_no = self.port
	if not port_no: port_no = cups.getPort()
	port.text = '%d' % port_no

	if hasattr(uri, 'path'): rp = uri.path
	else: rp = uri[2]
				
	re_match = re.match(r'^//(.*):(\d+)(/.*)', rp)
	if re_match: rp = re_match.group(3)
				
	#Remove leading slashes from path
	#TODO XXX FIXME I'm worried this will match broken urlparse
	#results as well (for instance if they don't include a port)
	#the xml would be malform'd either way
	rp = re.sub(r'^/+', '', rp)
				
	path = Element('txt-record')
	path.text = 'rp=%s' % (rp)
	service.append(path)

	# This is reported to Apple products as the location
	if v['printer-location'] != '':
		desc = Element('txt-record')
		desc.text = 'note=%s' % (v['printer-location'])
		service.append(desc)

	# AirPrint and Non-AirPrint specific
	if airprint:
		
		product = Element('txt-record')
		product.text = 'product=(GPL Ghostscript)'
		service.append(product)
		
	else:

		product = Element('txt-record')
		product.text = 'product=(%s)' %(v['printer-make-and-model'])
		service.append(product)
		
		# Add name
		ptype = Element('txt-record')
		ptype.text = 'ty=%s' %(v['printer-make-and-model'])
		
		# USB manufacturer and model
		if usbdevs.get(v['device-uri'], None) is not None:
		
			usbdev = usbdevs.get(v['device-uri']).get('device-id',None)
			
			if usbdev is not None:

				manuf = None
				model = None
				
				# Tokenize values
				kvs = usbdev.split(';')				
				for kv in kvs:
					if not kv.find(':') > 0: continue
					[k,val] = kv.split(':')
					if k == 'MFG': manuf = val
					elif k == 'MODEL' or k == 'MDL': model = val
				
				if manuf is not None and model is not None:
					man = Element('txt-record')
					man.text = 'usb_MFG=%s' %(manuf)
					service.append(man)
					man = Element('txt-record')
					man.text = 'usb_MDL=%s' %(model)
					service.append(man)
			
	# Color
	if attrs.get('color-supported', True):
		extTag = Element('txt-record')
		extTag.text = 'Color=T'
		service.append(extTag)
	
	# Duplex
#.........这里部分代码省略.........