Downloading an HTTP table to an array https://community.spiceworks.com/topic/543224-downloading-an-http-table-to-an-array
HI all, I would be very grateful for your help with a script.
I have managed to get some parts of it it to work, extracting information from innerHTML, innerText, outerHTML and outerText (below) but I have trouble with presenting results and feeding this into a variable so result can be uploaded to the PRTG monitoring server.
Much appreciating your help,
Thanks!
$ie = New-Object -ComObject "InternetExplorer.Application"
#$ie.visible = $true
$ie.silent = $true
$ie.Navigate("http://download.webpage.com/webpage/test.html")
while($ie.ReadyState -ne 4) {start-sleep -m 100}
#while ($ie.Busy) {Start-Sleep -Milliseconds 50}
Write-Warning "Retrieving information from web"
$body = $ie.Document.getElementsByTagName("table")
Write-Warning "Tables : "
$tables = $body
$tables
$tables2 = $tables | select innerText
Write-Warning "Tables 2: "
$tables2
$RawTables = $body
Write-Verbose "Found $($RawTables.Count) tables in HTML"
$TableNum = 1
ForEach ($RawTable in $RawTables)
{ Write-Verbose "Parsing headers for Table #$TableNum"
$InnerHTML = ($RawTable | select innerText).innerText -split "`n"
Write-Warning "InnerHTML: "
$InnerHTML
$Search = $InnerHTML
Write-Warning "Search: "
$Search
$Fields = [ordered]@{}
ForEach ($Line in $Search)
{ ForEach ($Field in $Line.Matches)
{ $Fields.Add($Field.Groups[1].Value,$null)
}
}
Write-Warning "Parsing table data for Table #$TableNum"
If ($Fields.Count -gt 0)
{ $Search = $InnerHTML | Select-String -Pattern "<t[hd] ?.*?>(.*?)</t[hd]>" -AllMatches
Write-Warning "Search2: "
$Search
$Row = [PSCustomObject]$Fields
$Index = 0
$Table = ForEach ($Match in $Search.Matches)
{ $Field = $Fields.GetEnumerator().Name[$Index]
$Row.$Field = ($Match.Groups[1].Value -replace "<.*?>","").Trim()
If ($Index -eq ($Fields.Count - 1))
{ $Index = 0
Write-Output $Row
$Row = [PSCustomObject]$Fields
}
Else
{ $Index ++
}
}
[PSCustomObject]@{
Raw = $InnerHTML
Data = $Table
Fields = $Fields
}
}
Else
{ Write-Warning "Unable to determine headers for Table #$TableNum, skipping it"
}
$TableNum ++
}
# This code will need to be inserted as well (not finished)
# Sends results to PRTG for monitoring:
#"<prtg>"
#
# "<result>"
# "<channel>Javascript enabled</channel>"
# "<value>$yesno</value>"
# "</result>"
# "<result>"
# "<channel>Client IP address</channel>"
# "<value>$clientip</value>"
# "</result>"
# "<text>$returndescription</text>"
# "<result>"
# "<channel>Real connecting IP address</channel>"
# "<value>$realip</value>"
# "</result>"
# "<result>"
# "<channel>Server IP address</channel>"
# "<value>$serverip</value>"
# "</result>"
# "<text>$returndescription</text>"
# "<result>"
# "<channel>M_IP1</channel>"
# "<value>$m_ip1</value>"
# "</result>"
# "<result>"
# "<channel>M_IP2</channel>"
# "<value>$m_ip2</value>"
# "</result>"
# "<text>$returndescription</text>"
# "<result>"
# "<channel>M_IP1</channel>"
# "<value>$m_ip1</value>"
# "</result>"
# "<result>"
# "<channel>IP mapp DNS mapp</channel>"
# "<value>$imdm</value>"
# "</result>"
# "<text>$returndescription</text>"
# "<result>"
# "<channel>Serial</channel>"
# "<value>$serial</value>"
# "</result>"
# "<result>"
# "<channel>RTT Small hreq</channel>"
# "<value>$rttsmall</value>"
# "</result>"
# "<result>"
# "<channel>BW DL Small</channel>"
# "<value>$bwdlsmalldl</value>"
# "</result>"
# "<result>"
# "<channel>BW UL Med</channel>"
# "<value>$bwmedul</value>"
# "</result>"
# "<result>"
# "<channel>BW DL Large</channel>"
# "<value>$bwlargedl</value>"
# "</result>"
# "<result>"
# "<channel>BW UL Large</channel>"
# "<value>$bwdllargeul</value>"
# "</result>"
#"</prtg>"
[System.Runtime.Interopservices.Marshal]::ReleaseComObject($ie)
Remove-Variable ie
# End of Script
This is the innerHTML, innerText, outerHTML and outerText I retrieve the information out from.
innerHTML :
<tbody><tr>
<th>JavaScript enabled</th>
<td>
<script type="text/javascript">
document.write('Yes');
</script>Yes
<noscript>No</noscript>
</td>
<tr>
<th>Client IP address </th>
<td id="clientip">11.11.11.111</td>
<tr>
<th>Real connecting IP address </th>
<td id="anotherip">11.11.11.111</td>
<tr>
<th>Server IP address </th>
<td id="serverip">33.333.333.33 (machine ip = 44.444.444.44)</td>
<tr>
<th>M_IP1: </th>
<td id="mapip1">66.666.666.66</td>
<tr>
<th>M_IP2: </th>
<td id="mapip2">55.555.555.55</td>
<tr>
<th>IP mapping matches DNS mapping: </th>
<td id="mapping">No</td>
<tr>
<th>Network name: </th>
<td id="network">Network Name</td>
<tr>
<th>Serial: </th>
<td id="serial">1234</td>
<tr>
<th>RTT for small http request </th>
<td id="httplatency">17 ms</td>
<tr>
<th>BW for DL small kbyte to browser </th>
<td id="dlbandwidthsmall">55183.6 kbps (HIT)</td>
<tr>
<th>BW for UL medium kbyte from browser </th>
<td id="uploadbandwidthsmall">29681.1 kbps</td>
<tr>
<th>BW for DL large Mbyte to browser </th>
<td id="dlbandwidthlarge">Calculating...</td>
<tr>
<th>BW for UL Large kbyte from browser </th>
<td id="ulbwxlarge">Calculating...</td>
</tr></tbody>
innerText :
JavaScript enabled
document.write('Yes'); Yes No
Client IP address
11.11.11.111
Real connecting IP address
11.11.11.111
Server IP address
33.333.333.33 (machine ip = 44.444.444.44)
M_IP1:
66.666.666.66
M_IP2:
55.555.555.55
IP mapping matches DNS mapping:
No
Network name:
Network Name
Serial:
1234
RTT for small http request
17 ms
BW for download small kbyte to browser
1001.1 kbps (HIT)
BW for UL medium kbyte from browser
1001.1 kbps
BW for DL large Mbyte to browser
Calculating...
BW for UL Large kbyte from browser
Calculating...
outerHTML : <table>
<tbody><tr>
<th>JavaScript enabled</th>
<td>
<script type="text/javascript">
document.write('Yes');
</script>Yes
<noscript>No</noscript>
</td>
<tr>
<th>Client IP address </th>
<td id="clientip">11.11.11.111</td>
<tr>
<th>Real connecting IP address </th>
<td id="realip">11.11.11.111</td>
<tr>
<th>Server IP address </th>
<td id="Serverip">33.333.333.33 (machine ip = 44.444.444.44)</td>
<tr>
<th>M_IP1: </th>
<td id="mapip1">66.666.666.66</td>
<tr>
<th>M_IP2: </th>
<td id="mapip2">55.555.555.55</td>
<tr>
<th>IP mapping matches DNS mapping: </th>
<td id="mapping">No</td>
<tr>
<th>Network name: </th>
<td id="network">Network Name</td>
<tr>
<th>Serial: </th>
<td id="serial">1234</td>
<tr>
<th>RTT for small http request </th>
<td id="httplatency">17 ms</td>
<tr>
<th>BW for DL small kbyte to browser </th>
<td id="dlbandwidthsmall">1001.1 kbps (HIT)</td>
<tr>
<th>BW for UL medium kbyte from browser </th>
<td id="uploadbandwidthsmall">1001.1 kbps</td>
<tr>
<th>BW for DL large Mbyte to browser </th>
<td id="dlbandwidthlarge">Calculating...</td>
<tr>
<th>BW for UL Large kbyte from browser </th>
<td id="ulbwxlarge">Calculating...</td>
</tr></tbody></table>
outerText :
JavaScript enabled
document.write('Yes'); Yes No
Client IP address
11.11.11.111
Real connecting IP address
11.11.11.111
Server IP address
33.333.333.33 (machine ip = 44.444.444.44)
M_IP1:
66.666.666.66
M_IP2:
55.555.555.55
IP mapping matches DNS mapping:
No
Network name:
Network Name
Serial:
1234
RTT for small http request
17 ms
BW for DL small kbyte to browser
1001.1 kbps (HIT)
BW for UL medium kbyte from browser
1001.1 kbps
BW for DL large Mbyte to browser
Calculating...
BW for UL Large kbyte from browser
Calculating...
Last change on Nov 5, 2018 7:08:24 PM by
Add comment