Python parser.parse函数代码示例

def kml2pykml():
    "Parse a KML file and generates a pyKML script"
    import urllib2
    from pykml.parser import parse
    from optparse import OptionParser
    
    parser = OptionParser(
        usage="usage: %prog FILENAME_or_URL",
        version="%prog 0.1",
    )
    (options, args) = parser.parse_args()
    if len(args) != 1:
        parser.error("wrong number of arguments")
    else:
        uri = args[0]
    try:
        with open(uri) as f:
            doc = parse(f, schema=None)
    except IOError:
        try:
            f = urllib2.urlopen(uri)
            doc = parse(f, schema=None)
        finally:
            #pass
            try:
                f
            except NameError:
                pass #variable was not defined
            else:
                f.close
    print write_python_script_for_kml_document(doc)

 def test_parse_kml_document(self):
     """Tests the parsing of an valid KML file object"""
     test_kml = b'<kml xmlns="http://www.opengis.net/kml/2.2"/>'
     fileobject = BytesIO(test_kml)
     schema = Schema('ogckml22.xsd')
     tree = parse(fileobject, schema=schema)
     self.assertEqual(etree.tostring(tree), test_kml)
     tree = parse(fileobject, schema=schema)
     self.assertEqual(etree.tostring(tree), test_kml)

 def test_parse_kml_file_with_cdata(self):
     "Tests the parsing of a local KML file, with a CDATA description string"
     test_datafile = path.join(
         path.dirname(__file__),
         'testfiles',
         'google_kml_tutorial/using_the_cdata_element.kml'
     )
     # parse with validation
     with open(test_datafile) as f:
         doc = parse(f, schema=Schema('ogckml22.xsd'))
     self.assertEquals(
         etree.tostring(doc),
         '<kml xmlns="http://www.opengis.net/kml/2.2">'
           '<Document>'
             '<Placemark>'
               '<name>CDATA example</name>'
               '<description>'
                 '<![CDATA[\n'
                 '          <h1>CDATA Tags are useful!</h1>\n'
                 '          <p><font color="red">Text is <i>more readable</i> and \n'
                 '          <b>easier to write</b> when you can avoid using entity \n'
                 '          references.</font></p>\n'
                 '        ]]>'
               '</description>'
             '<Point>'
               '<coordinates>102.595626,14.996729</coordinates>'
             '</Point>'
           '</Placemark>'
         '</Document>'
       '</kml>'
     )
     # parse without validation
     with open(test_datafile) as f:
         doc2 = parse(f)
     self.assertEquals(
         etree.tostring(doc2),
         '<kml xmlns="http://www.opengis.net/kml/2.2">'
           '<Document>'
             '<Placemark>'
               '<name>CDATA example</name>'
               '<description>'
                 '<![CDATA[\n'
                 '          <h1>CDATA Tags are useful!</h1>\n'
                 '          <p><font color="red">Text is <i>more readable</i> and \n'
                 '          <b>easier to write</b> when you can avoid using entity \n'
                 '          references.</font></p>\n'
                 '        ]]>'
               '</description>'
             '<Point>'
               '<coordinates>102.595626,14.996729</coordinates>'
             '</Point>'
           '</Placemark>'
         '</Document>'
       '</kml>'
     )

 def test_parse_kml_file(self):
     "Tests the parsing of a local KML file, with validation"
     test_datafile = path.join(
         path.dirname(__file__),
         'testfiles',
         'google_kml_developers_guide/complete_tour_example.kml'
     )
     # parse with validation
     with open(test_datafile) as f:
         doc = parse(f, schema=Schema('kml22gx.xsd'))
     # parse without validation
     with open(test_datafile) as f:
         doc = parse(f)
     self.assertTrue(True)

    def test_parse_invalid_ogc_kml_document(self):
        """Tests the parsing of an invalid KML document.  Note that this KML
        document uses elements that are not in the OGC KML spec.
        """
        url = 'https://developers.google.com/kml/documentation/kmlfiles/altitudemode_reference.kml'
        context = ssl._create_unverified_context()
        try:
            with urlopen(url, context=context) as fileobject:
                with self.assertRaises(etree.XMLSyntaxError):
                    # tree =
                    parse(fileobject, schema=Schema('ogckml22.xsd'))

        except URLError:
            print('Unable to access the URL. Skipping test...')

def process():
    shapes = ['shape_id', 'shape_pt_lat', 'shape_pt_lon', 'shape_pt_sequence']
    # Open system.kml file in go/data/routes
    with open('{}/route/kml/shapes.kml'.format(DATA_PATH)) as file:
        doc = parser.parse(file)
        shape = None
        for t in doc.getiterator():

            # If the tag is a description, find the shape_id in the CDATA
            if re.sub('\{.*\}', '', t.tag).lower() == 'description':
                shape = int(parse_cdata(t.text))
                if shape in Segment.objects:
                    shape = Shape(shape) if shape not in Shape.objects else Shape.objects[shape]
                else:
                    print('Shape {} does not have a matching segment.'.format(shape))
                    shape = None

            # Save coordinates
            if re.sub('\{.*\}', '', t.tag).lower() == 'coordinates' and shape:
                # A new Path must be created for the discovered coordinates
                shape.add_path([re.split(',', x) for x in re.split('\s', t.text) if len(re.split(',', x)) == 3])

    # Open writer
    writer = open('{}/gtfs/files/shapes.txt'.format(REPORT_PATH), 'w')
    writer.write('{}\n'.format(','.join(shapes)))

    for obj in sorted(Shape.objects.keys()):
        shape = Shape.objects[obj]
        shape.order_paths()

        for path, reverse in shape.order:
            for point in path.get_points(reverse):
                writer.write('{}\n'.format(','.join([str(s) for s in [shape.id, point[1], point[0], shape.index]])))
                shape.index += 1

    def _load_waypoints(kml_stream):
        """Loads and returns the waypoints from a KML string."""

        def get_child(element, tag_name):
            """Returns the child element with the given tag name."""
            try:
                return getattr(element, tag_name)
            except AttributeError:
                raise ValueError('No {tag} element found'.format(tag=tag_name))

        root = parser.parse(kml_stream).getroot()
        if 'kml' not in root.tag:
            raise ValueError('Not a KML file')

        document = get_child(root, 'Document')
        placemark = get_child(document, 'Placemark')
        line_string = get_child(placemark, 'LineString')
        # Unlike all of the other tag names, "coordinates" is not capitalized
        coordinates = get_child(line_string, 'coordinates')

        waypoints = []
        text = coordinates.text.strip()
        for csv in re.split(r'\s', text):
            (
                longitude,
                latitude,
                altitude  # pylint: disable=unused-variable
            ) = csv.split(',')

            waypoints.append((
                Telemetry.longitude_to_m_offset(float(longitude), float(latitude)),
                Telemetry.latitude_to_m_offset(float(latitude))
            ))
        return waypoints

def get_boundaries():
    """ Parse the KML file to get the boundaries
    """
    with open(kml_file) as f:
        tree = parser.parse(f)
        root = tree.getroot()

        N = 0
        placemarks = {}
        for ch in root.Document.Folder.getchildren():
            if 'Placemark' in ch.tag:
                # Found a placemark
                N += 1
                pname = int(ch.name.text)
                
                # Get the coordinates
                pcoords = ch.MultiGeometry.Polygon.outerBoundaryIs.LinearRing.coordinates.text
                pcoords = pcoords.strip()
                pcoords = re.split(',| ', pcoords)
                pcoords = [float(c) for c in pcoords]

                lons = pcoords[0::3]
                lats = pcoords[1::3]
                assert len(lons) == len(lats)
                #print "Polygon has %d vertices" % len(lons)
                
                placemarks[pname] = (lats, lons)

        print "Found %d placemarks" % N
        return placemarks

def checkKML(filename):
	with open(filename) as f:
		doc = parser.parse(f)
		if schema_ogc.validate(doc) or schema_gx.validate(doc):
			return True
		else:
			return False

def buildCwbStaticStationDict():
    
    url = 'http://www.cwb.gov.tw/wwwgis/kml/cwbobs.kml'
    #url = 'http://code.google.com/apis/kml/documentation/KML_Samples.kml'

    fileobject = urlopen(url)
    root = parser.parse(fileobject).getroot()
    cwbStaticStationDict={}

    for i in range(100):
        try:
            k=root.Document.Placemark[i]
            stationName=k.name.text[0:len(k.name.text)-9]
            stationNumber=k.name.text[-5:]
            longitude=float(k.LookAt.longitude.text)
            latitude=float(k.LookAt.latitude.text)
            altitude=float(k.LookAt.altitude.text)
            #print stationName,stationNumber,longitude,latitude,altitude
            cwbStaticStationDict[stationName.encode('utf-8')]=[stationNumber,longitude,latitude,altitude]
            
        except IndexError:
            pass
            #print i, 'index out of range'
    #check if dic is OK        
    #print cwbStaticStationDict['金門'], len(cwbStaticStationDict)
    return(cwbStaticStationDict)

def readOrigFolder(foldername):
    if not os.path.exists(foldername):
        return {}
    onlyfiles = [f for f in os.listdir(foldername) if os.path.isfile(os.path.join(foldername, f))]
    result = {}
    for f in onlyfiles:
        fullpath = os.path.join(foldername, f)
        with open(fullpath) as kmlfile:
            kmldoc = parser.parse(kmlfile)
            root = kmldoc.getroot()
            for x in root.Document.Folder.Placemark:
                # print etree.tostring(x, pretty_print=True)
                coords = [y for y in str(x.LineString.coordinates).rstrip().lstrip().split(" ")]
                coords_filtered = []
                for y in coords:
                    lat, lon, h = y.split(",")
                    coords_filtered.append([float(lat), float(lon)])
                    #if "Path" in str(x.name) or "Line" in x.name or "," in str(x.name) or "." in str(x.name):
                     #   print x.name
                try:
                    name = str(x.name).replace("Path", "").replace("Line", "").replace(",", "").replace(".", "").rstrip().lstrip()
                    #if int(name) in result.keys():
                    #    print "Error: key in orig already exists!", name, result[int(name)], coords
                    result[int(name)] = coords_filtered
                except:
                    print "##################", fullpath, x.name
    return result

def getImagesFromGSV(kmlfile):
    svdirectory = "streetviewimages"
    if not os.path.exists(svdirectory):
        os.makedirs(svdirectory)
    family = os.path.basename(kmlfile).split('.')[0]
    fov=120
    pitches = [5]#,-11
    with open(kmlfile) as f:
        doc = parser.parse(f)
        root = doc.getroot()
        for placemark in root.Document.Placemark:
            pt = placemark.find(".//{http://earth.google.com/kml/2.1}Point")
            name = placemark.name
            if pt is not None:   
                lon,lat,x = placemark.Point.coordinates.text.strip().split(',')
                for data in placemark.ExtendedData.findall(".//*[@name='headings']/{http://earth.google.com/kml/2.1}value"):
                    headings = data.text.strip().split(",")
                    h_count = 0
                    for h in headings:
                        for pitch in pitches:
                            imgname = str(family) + '_' + str(name) + '_' + str(h_count) + '.jpg'    
                            p = os.path.join(svdirectory,imgname)
                            if not os.path.isfile(p):
                                gsv_base_url = "http://maps.googleapis.com/maps/api/streetview?size=640x360&location="+str(lat)+","+str(lon)
                                gsv_url = gsv_base_url + "&fov="+str(fov) + "&heading="+str(h) + "&pitch=" + str(pitch) +"&key=" + GSV_KEY
                                urllib.urlretrieve(gsv_url, p)
                                print "Downloaded", p
                            else:
                                print p, "Image already exist"
                        h_count+=1

def extract_tracks(f):
    from pykml import parser

    doc = parser.parse(f)
    root = doc.getroot()
    tracks = find_tracks(root.Document.Placemark)

    return tracks

def extractKML( ridingID, path ) :  
  
    kmlFileName = path + 'ridingMapData_' + str( ridingID ) + '.kml'

    with open(kmlFileName, 'r') as f:
      doc = parser.parse(f)
      
    print "Opening riding map file:", ridingID 
      
    poll_list = []  
    pol = {}
    
    firstPoll = True

    for element in doc.iter("{http://www.opengis.net/kml/2.2}ExtendedData", "{http://www.opengis.net/kml/2.2}Polygon" ):
        if element.tag == "{http://www.opengis.net/kml/2.2}ExtendedData":
          if firstPoll == False:
            poll_list.append( pol.copy())
            
          firstPoll = False
          pol = {}
          parseData( pol, element )
        elif element.tag == "{http://www.opengis.net/kml/2.2}Polygon": # or element.tag == "{http://www.opengis.net/kml/2.2}MultiGeometry":
          #pprint( pol )
          parsePolygon( pol, element )
          
    poll_list.append( pol.copy()) 
     
    f.close()
    
    riding = {}  
    riding['ridingID'] = ridingID
    riding['num_polls'] = len(poll_list)
    riding['polls'] = poll_list
    
    outputFile = path + 'ridingMapData_' + str( ridingID ) + '.json'

    with open(outputFile, 'w') as f:
      json.dump(riding, f)
      f.close()
      
    print "Successfully wrote riding map file:", ridingID 
    
    
    outputFile = path + 'ridingMapBoundaryData_' + str( ridingID ) + '.json'
    
    boundary = {}
    boundary['ridingID'] = ridingID
    boundary['coords'] = calculateRidingBoundary( poll_list )
    
    with open(outputFile, 'w') as f:
      json.dump(boundary, f)
      f.close()
      
    print "Successfully wrote riding map boundary file:", ridingID 
    

    return True

def get_station_objects(start_year=1980, end_year=2010, sel_names=None):
    # read ice depth values
    df = get_obs_data()

    lon_min, lon_max = -100, 0
    lat_min, lat_max = 40, 90

    nvals_min = 100

    p = parser.parse(STATION_COORDS_FILE.open())

    root = p.getroot()

    station_elts = root.Document.Placemark

    # select points based on the lat/lon limits?
    stations = []
    for el in station_elts:

        lon, lat, _ = [float(c.strip()) for c in el.Point.coordinates.text.split(",")]

        # Check if the station
        if sel_names is not None:

            is_ok = False

            for sel_name in sel_names:
                if sel_name.lower() in el.name.text.lower():
                    is_ok = True
                    break

            if not is_ok:
                continue

        if (lon_min <= lon <= lon_max) and (lat_min <= lat <= lat_max):
            print("{}: {}".format(el.name, el.Point.coordinates))

            df_s = df.loc[df.station_name.str.lower().str.startswith(el.name.text.lower())]

            df_s = df_s.loc[(df_s.year >= start_year) & (df_s.year <= end_year)]

            if len(df_s) < nvals_min:
                continue

            print(len(df_s))
            d_to_v = dict(zip(df_s["Date"][:], df_s["ice_depth"][:]))

            # df_s.plot(x="Date", y="ice_depth")
            # plt.title(el.name.text)
            # plt.show()

            # print(df_s.station_name)

            stations.append(Station(st_id=df_s.station_name.iloc[0], lon=lon, lat=lat, date_to_value=d_to_v))

    return stations