Key Information Extraction models for text to text

Question

I'm willing to get a structured text such as xml as an output. And i got unscructed texts as an input. I do little search but all i found is some key information extraction models about pdfs. Is there any model that suits my problem or if i need to create a custom model what should be my start point?

Some example of my inputs and outputs: input:

...
1111    007XXXXXL   007 BOND LLC    1429 CIERRA ST. RICHBURG  SC  29729-9367
1112    321XXXXXM   321 EQUIPMENT COMPANY   PO BOX 2105 GASTONIA  NC  28053
1113    360XXXXXS   360BRANDS, INC. PO BOX 2478 MT. PLEASANT  SC  29465
1114    3IXXXXXG    3iD MANAGEMENT  9634 BOCA GARDENS CRL N #D  BOCA RATON  FL  33496
1115    4XXXXXI     4IMPRINT INC    25303 NETWORK PLACE CHICAGO  IL  60673-1253
1116    911XXXC     911 C&E. L.L.C. 1513 BRIARCLIFF DRIVE   ASHEBORO  NC  27205
...

expected output:

<?xml version="1.0" encoding="utf-8"?>
<PO_Data>
<Vendors>
<Vendor><
Vendor_Number>1111</Vendor_Number>
<Name1>007XXXXXL</Name1>
<Address1>1429 CIERRA ST.</Address1>
<City>RICHBURG</City>
<State>SC</State>
<Zip>29729-9367</Zip>
</Vendor><Vendor>
...
</PO_Data>