Lua Requires Chilkat v9.5.0.77+
Lua
HTML Table to CSV
See more HTML-to-XML/Text Examples
Demonstrates a method for converting an HTML table to a CSV file.Chilkat Lua Downloads
local chilkat = require("chilkat")
-- This example requires the Chilkat API to have been previously unlocked.
-- See Global Unlock Sample for sample code.
-- First download the HTML containing the table
local http = chilkat.Http.new()
local bdHtml = chilkat.BinData.new()
local success = http:quick_get_bd("https://example-code.com/data/etf_table.html", bdHtml)
if not success then
print(http.last_error_text)
return
end
-- Convert to XML.
local htx = chilkat.HtmlToXml.new()
htx:set_html_bd(bdHtml)
local sbXml = chilkat.StringBuilder.new()
htx:to_xml_sb(sbXml)
local xml = chilkat.Xml.new()
xml:load_sb(sbXml, true)
-- Remove attributes and sub-trees we don't need.
-- (In other words, we're getting rid of clutter...)
local numRemoved = xml:prune_tag("thead")
numRemoved = xml:prune_attribute("style")
numRemoved = xml:prune_attribute("class")
-- Scrub the element and attribute content.
xml:scrub("ContentTrimEnds,ContentTrimInside,AttrTrimEnds,AttrTrimInside")
-- Let's see what we have...
print(xml:get_xml())
-- We have the following XML.
-- Copy this XML into the online tool at Generate Parsing Code from XML
-- as a starting point for accessing the data..
-- <?xml version="1.0" encoding="utf-8"?>
-- <root>
-- <html>
-- <head>
-- <meta http-equiv="content-type" content="text/html; charset=UTF-8"/>
-- </head>
-- <body text="#000000" bgcolor="#FFFFFF">
-- <div>
-- <div>
-- <table role="grid" data-scrollx="true" data-sortdirection="desc" data-sorton="-1"/>
-- </div>
-- </div>
-- <div>
-- <table id="topHoldingsTable" role="grid" data-scrollx="true" data-sortdirection="desc" data-sorton="-1">
-- <tbody>
-- <tr role="row">
-- <td>
-- <text>ITUB4</text>
-- </td>
-- <td>
-- <text>ITAU UNIBANCO HOLDING PREF SA</text>
-- </td>
-- <td>
-- <text>Financials</text>
-- </td>
-- <td>
-- <text>Brazil</text>
-- </td>
-- <td>
-- <text>10.94</text>
-- </td>
-- <td>
-- <text>998,954,813.73</text>
-- </td>
-- </tr>
-- <tr role="row">
-- <td>
-- <text>BBDC4</text>
-- </td>
-- <td>
-- <text>BANCO BRADESCO PREF SA</text>
-- </td>
-- <td>
-- <text>Financials</text>
-- </td>
-- <td>
-- <text>Brazil</text>
-- </td>
-- <td>
-- <text>9.01</text>
-- </td>
-- <td>
-- <text>822,164,622.75</text>
-- </td>
-- </tr>
-- ...
-- ...
-- ...
-- </tbody>
-- </table>
-- </div>
-- </body>
-- </html>
-- </root>
-- This is the code generated by the online tool:
--
local table_role = ""
local table_data_scrollx = ""
local table_data_sortdirection = ""
local table_data_sorton = ""
local table_id = ""
local j = 0
local count_j = 0
local tr_role = ""
local k = 0
local count_k = 0
local tagPath = ""
local text = ""
local i = 0
local count_i = xml:num_children_having_tag("html|body|div")
while i < count_i do
xml.i = i
table_role = xml:chilkat_path("html|body|div[i]|div|table|(role)")
table_data_scrollx = xml:chilkat_path("html|body|div[i]|div|table|(data-scrollx)")
table_data_sortdirection = xml:chilkat_path("html|body|div[i]|div|table|(data-sortdirection)")
table_data_sorton = xml:chilkat_path("html|body|div[i]|div|table|(data-sorton)")
table_id = xml:chilkat_path("html|body|div[i]|table|(id)")
table_role = xml:chilkat_path("html|body|div[i]|table|(role)")
table_data_scrollx = xml:chilkat_path("html|body|div[i]|table|(data-scrollx)")
table_data_sortdirection = xml:chilkat_path("html|body|div[i]|table|(data-sortdirection)")
table_data_sorton = xml:chilkat_path("html|body|div[i]|table|(data-sorton)")
j = 0
count_j = xml:num_children_having_tag("html|body|div[i]|table|tbody|tr")
while j < count_j do
xml.j = j
tr_role = xml:chilkat_path("html|body|div[i]|table|tbody|tr[j]|(role)")
k = 0
count_k = xml:num_children_having_tag("html|body|div[i]|table|tbody|tr[j]|td")
while k < count_k do
xml.k = k
text = xml:get_child_content("html|body|div[i]|table|tbody|tr[j]|td[k]|text")
k = k + 1
end
j = j + 1
end
i = i + 1
end
-- Let's modify the above code to build the CSV.
local csv = chilkat.Csv.new()
csv:set_column_name(0, "Ticker")
csv:set_column_name(1, "Name")
csv:set_column_name(2, "Sector")
csv:set_column_name(3, "Country")
csv:set_column_name(4, "Weight")
csv:set_column_name(5, "Notional Vaue")
i = 0
count_i = xml:num_children_having_tag("html|body|div")
while i < count_i do
xml.i = i
j = 0
count_j = xml:num_children_having_tag("html|body|div[i]|table|tbody|tr")
while j < count_j do
xml.j = j
k = 0
count_k = xml:num_children_having_tag("html|body|div[i]|table|tbody|tr[j]|td")
while k < count_k do
xml.k = k
csv:set_cell(j, k, xml:get_child_content("html|body|div[i]|table|tbody|tr[j]|td[k]|text"))
k = k + 1
end
j = j + 1
end
i = i + 1
end
csv:save_file("qa_output/brasil_etf.csv")
local csvStr = csv:save_to_string()
print(csvStr)
-- Our CSV looks like this:
-- Ticker,Name,Sector,Country,Weight,Notional Vaue
-- ITUB4,ITAU UNIBANCO HOLDING PREF SA,Financials,Brazil,10.94,"998,954,813.73"
-- BBDC4,BANCO BRADESCO PREF SA,Financials,Brazil,9.01,"822,164,622.75"
-- VALE3,CIA VALE DO RIO DOCE SH,Materials,Brazil,8.60,"785,290,260.07"
-- PETR4,PETROLEO BRASILEIRO PREF SA,Energy,Brazil,5.68,"518,124,434.10"
-- PETR3,PETROBRAS,Energy,Brazil,4.86,"443,254,438.53"
-- B3SA3,B3 BRASIL BOLSA BALCAO SA,Financials,Brazil,4.57,"417,636,740.16"
-- ABEV3,AMBEV SA,Consumer Staples,Brazil,4.57,"417,216,913.63"
-- BBAS3,BANCO DO BRASIL SA,Financials,Brazil,3.25,"296,921,232.15"
-- ITSA4,ITAUSA INVESTIMENTOS ITAU PREF SA,Financials,Brazil,2.90,"265,153,684.52"
-- LREN3,LOJAS RENNER SA,Consumer Discretionary,Brazil,2.25,"205,832,175.98"
--