HTML parser module

Author: weilixu

BuildSimHubAPI/__pycache__/buildsimhub.cpython-36.pyc

@@ -2,7 +2,6 @@
 from BuildSimHubAPI.helpers import simulationJob
 from BuildSimHubAPI.helpers import simulationType
 from BuildSimHubAPI.helpers import energyModel
-from BuildSimHubAPI.helpers import htmlResults
 
 class BuildSimHubAPIClient():
     """
@@ -40,6 +39,3 @@ def get_model(self, simulationJob):
         modelKey = vars(simulationJob)['_trackToken']
         model = energyModel.Model(self._userAPI,modelKey)
         return model
-
-    def get_html(self, simulationJob):
-        html = htmlResults.HTMLResults(self._userAPI,simulaitonJob)

BuildSimHubAPI/__pycache__/eplusHTMLParser.cpython-36.pyc

@@ -0,0 +1,6 @@
+from BuildSimHubAPI.htmlParser import numericValueParser
+
+def extract_a_value_from_table(html, report, table, column, row, category = "EntireFacility"):
+    data_reader = numericValueParser.NumericValueParser(report, table, column, row, category)
+    data_reader.feed(html)
+    return {'value':data_reader.data, 'unit':data_reader.unit}

BuildSimHubAPI/buildsimhub.py

@@ -0,0 +1,116 @@
+
+import re
+from html.parser import HTMLParser
+
+class NumericValueParser(HTMLParser):
+    def __init__(self, report, table, column_name, row_name, reportFor = "EntireFacility"):
+        HTMLParser.__init__(self)
+
+        r = re.sub('\W','',report);
+        t = re.sub('\W','',table);
+        rf = re.sub('\W','',reportFor);
+
+        self._tableId = r+":" + rf + ":" + t
+        self._column = column_name
+        self._row = row_name
+        #put the end point
+        self._in_table = False
+        self._in_header = False
+        self._in_row = False
+        self._correct_row = False
+
+        self._col_index = 0
+        self._current_col_index = 0
+        self._unit = ''
+        self._data = ''
+
+    @property
+    def data(self):
+        return self._data
+
+    @property
+    def unit(self):
+        return self._unit
+
+    def handle_starttag(self, tag, attributes):
+        #this means if we are processing table
+        #but we met another start tag table,
+        #we then are out of the target table, should skip
+        if(self._in_table & (tag=='table')):
+            self._in_table = False
+            return
+        #print("This is beginning ==> " + tag)
+        #search for matching table
+        if(tag=='table'):
+            for name, value in attributes:
+                if name == 'tableid' and value == self._tableId:
+                    self._in_table = True
+                    self._in_header = True
+                    break
+        #if we are in a row - reset the row specs
+        elif((tag=='tr')):
+            self._current_col_index = 0
+            self._in_row = True
+
+
+    def handle_endtag(self, tag):
+        #print("This is end: ==> " + tag)
+        if(self._in_header & (tag=='td')):
+            #in header, any td is one column
+            self._col_index += 1
+        elif(tag =='tr'):
+            #this is the end of a row
+            self._in_header = False
+            self._in_row = False
+
+            #we are outside of correct row now,
+            #turn the flag off
+            if(self._correct_row):
+                self._correct_row = False
+        elif(tag =='table'):
+            self._in_table = False
+            #didn't find the value, return
+
+    def handle_data(self, data):
+        data = data.strip()
+
+        #if it is empty data, return
+        if(data == ''):
+            return
+
+        #if not in this table, return
+        if(not self._in_table):
+            return
+
+        #check whether the data has unit
+        index = data.find('[')
+        unit = ''
+        #reform the string & separate the unit
+        if(index > -1):
+            unit = data[index:]
+            data = data[:index-1]
+
+        #print(self._correct_row)
+        #print("******" + str(self._current_col_index) + "#####" + str(self._col_index))
+
+        if(self._in_header & (data == self._column)):
+            self._in_header = False
+            self._unit = unit
+        elif(self._correct_row & (self._current_col_index == self._col_index)):
+            #print("This is data: " + data + " " + str(self._current_col_index) + " (*&^%$#@" + str(self._col_index))
+            self._correct_row = False #turn off the flag
+            self._data = data
+
+        elif(self._in_row):
+            #means we find the correct row
+            if(data == self._row):
+                self._correct_row = True
+
+            self._current_col_index+=1
+
+###############LOCAL TEST########################
+#tableReader = NumericValueParser('Climatic Data Summary','Sizing Period Design Day','Maximum Dry Bulb','CHICAGO ANN HTG 99.6% CONDNS DB')
+#file = open('testTable.html', 'r') 
+#tableReader.feed(file.read())
+#print(tableReader.data)
+#print(tableReader.unit)