def test_gettables():
"""py.test for gettables"""
thedata = (
([('Site and Source Energy', [['a', '2'], ['3', '4']]),
('Site to Source Energy Conversion Factors', [['b', '6'], ['7',
'8']]),
('Custom Monthly Report', [['c', '16'], ['17', '18']]),
('Custom Monthly Report', [['d', '26'],
['27',
'28']])], False), # titlerows, tofloat
([('Site and Source Energy', [['a', 2], [3, 4]]),
('Site to Source Energy Conversion Factors', [['b', 6], [7, 8]]),
('Custom Monthly Report', [['c', 16], [17, 18]]),
('Custom Monthly Report', [['d', 26],
[27, 28]])], True), # titlerows, tofloat
)
for titlerows, tofloat in thedata:
# print titlerows
result = readhtml.titletable(SAMPLE_HTML, tofloat=tofloat)
for (title1, rows1), (title2, rows2) in zip(result, titlerows):
# print title1, title2
assert title1 == title2
# print rows1, rows2
assert rows1 == rows2
assert result == titlerows
def test_gettables():
"""py.test for gettables"""
thedata = (([('Site and Source Energy',
[['a', '2'], ['3', '4']]),
('Site to Source Energy Conversion Factors',
[['b', '6'], ['7', '8']]),
('Custom Monthly Report',
[['c', '16'], ['17', '18']]),
('Custom Monthly Report',
[['d', '26'], ['27', '28']])], False), # titlerows, tofloat
([('Site and Source Energy',
[['a', 2], [3, 4]]),
('Site to Source Energy Conversion Factors',
[['b', 6], [7, 8]]),
('Custom Monthly Report',
[['c', 16], [17, 18]]),
('Custom Monthly Report',
[['d', 26], [27, 28]])], True), # titlerows, tofloat
)
for titlerows, tofloat in thedata:
# print titlerows
result = readhtml.titletable(SAMPLE_HTML, tofloat=tofloat)
for (title1, rows1), (title2, rows2) in zip(result, titlerows):
# print title1, title2
assert title1 == title2
# print rows1, rows2
assert rows1 == rows2
assert result == titlerows
def test_gettables():
"""py.test for gettables"""
thedata = (("""<b>this is the title</b>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>1</td>
<td>2</td>
</tr>
<tr>
<td>3</td>
<td>4</td>
</tr>
</table>
""",
[('this is the title',
[['1', '2'], ['3', '4']])]), # html_doc, titlerows
("""<b>this is the title 1</b>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>1</td>
<td>2</td>
</tr>
<tr>
<td>3</td>
<td>4</td>
</tr>
</table>
<b>this is the title 2</b>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>11</td>
<td>22</td>
</tr>
<tr>
<td>33</td>
<td>44</td>
</tr>
</table>
""",
[('this is the title 1',
[['1', '2'], ['3', '4']]),
('this is the title 2',
[['11', '22'], ['33', '44']])]), # html_doc, titlerows
("""<b>this is the title 1</b>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>1</td>
<td>2</td>
</tr>
<tr>
<td>3</td>
<td>4</td>
</tr>
</table>
<b>this is the title 2</b>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>11</td>
<td>22</td>
</tr>
<tr>
<td>33</td>
<td>44</td>
</tr>
</table>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>111</td>
<td>222</td>
</tr>
<tr>
<td>333</td>
<td>444</td>
</tr>
</table>
<b>this is the title 1</b>
<table border="1" cellspacing="0" cellpadding="4">
<tr>
<td>1</td>
<td>2</td>
</tr>
<tr>
<td>3</td>
<td>4</td>
</tr>
</table>
""",
[('this is the title 1',
[['1', '2'], ['3', '4']]),
('this is the title 2',
[['11', '22'], ['33', '44']]),
('this is the title 2',
[['111', '222'], ['333', '444']]),
('this is the title 1',
[['1', '2'], ['3', '4']])]), # html_doc, titlerows
)
for html_doc, titlerows in thedata:
result = readhtml.titletable(html_doc)
assert result == titlerows
#
# The number you want is in the third row, second column and it's value is "47694.47"
#
# Let us use eppy to extract this number
# <codecell>
from eppy import readhtml # the eppy module with functions to read the html
fname = (
"../eppy/resources/outputfiles/V_7_2/5ZoneCAVtoVAVWarmestTempFlowTable_ABUPS.html"
) # the html file you want to read
filehandle = open(fname, "r").read() # get a file handle to the html file
htables = readhtml.titletable(filehandle) # reads the tables with their titles
# <markdowncell>
# If you open the python file readhtml.py and look at the function titletable, you can see the function documentation.
#
# It says the following
# <rawcell>
# """return a list of [(title, table), .....]
# title = previous item with a <b> tag
# table = rows -> [[cell1, cell2, ..], [cell1, cell2, ..], ..]"""
#
# <markdowncell>
# Let us say you want to find the "Net Site Energy". # # This is in table "Site and Source Energy". # # The number you want is in the third row, second column and it's value is "47694.47" # # Let us use eppy to extract this number # <codecell> from eppy import readhtml # the eppy module with functions to read the html fname = "../eppy/resources/outputfiles/V_7_2/5ZoneCAVtoVAVWarmestTempFlowTable_ABUPS.html" # the html file you want to read filehandle = open(fname, 'r').read() # get a file handle to the html file htables = readhtml.titletable(filehandle) # reads the tables with their titles # <markdowncell> # If you open the python file readhtml.py and look at the function titletable, you can see the function documentation. # # It says the following # <rawcell> # """return a list of [(title, table), .....] # title = previous item with a <b> tag # table = rows -> [[cell1, cell2, ..], [cell1, cell2, ..], ..]""" # # <markdowncell>
