...

								<table border="1" cellpadding="3" cellspacing="0">
<tbody>
<tr>



</tr>
<tr>
<td nowrap="nowrap" valign="top"><p><strong>AA Number. 3-456</strong></p></td>
<td style="text-align: justify;" valign="top">
<p>The quick brown fox jumps over the lazy dog near the bank of the 
river. The quick brown fox jumps over the lazy dog near the bank of the 
river.<br><em>(Hello World May 20, 2016)</em>&nbsp;<br>
<a href="http://www.mydomain.com/folder/pdf/abcd.pdf">Summary</a>&nbsp;|&nbsp;<a href="http://www.mydomain.com/folder/pdf/abcfull.pdf">Full Story</a></p>
</td>
<td style="text-align: center;" valign="top"><p>May 18, 2016</p></td>
</tr>

col1,col2,col3,col4,col5,col6

BEGIN {
# Each csv line will take several prints.  Blank ORS and OFS to handle processing ourself
ORS="" ; OFS=""
# These are indexes for the DATA and LINKS arrays it accumulates data in.
LINK=1; COL=0 }

# Prints OFS " S " then sets OFS=","
# In effect this prints a single column of CSV and sets it up to prepend
# a comma to the next column.  It quotes and escapes S for you.
function csv(S) {
        # Escape all quotes and commas before printing.
        # Might be overkill but better safe than sorry.
        gsub(/[,"]/, "\\\\&", S);
        printf("%s\"%s\"", OFS, S); OFS=","
}

# This prints a full line of collected data.
# It tells when by looking for a <TR> tag or a </TABLE> tag.
# It also checks that COL is nonzero to avoid printing blank rows.
(TAG=="TR" || CTAG=="TABLE") && COL {
        OFS="" # Begin new line of CSV

        # Print current row if any, one column at a time.
        # csv() will intelligently escape and wrap stuff for us.
        # Delete contents of arrays so duplicates aren't printed next time.
        for(C=1; C<=COL; C++) { csv(DATA[C]);   delete DATA[C]; }
        for(C=1; C in LINKS; C++) { csv(LINKS[C]); delete LINKS[C]; }
        printf("\n"); # csv does not print newline, we do
        COL=0; LINK=1 # Reset indexes for arrays
}

# Count colums in table.  This moves the index of DATA[] whenever it
# encounters a <TD> tag or an <EM> tag.
TAG=="TD" || TAG=="EM" { COL++ }

# Clean up HTML garbage.  All whitespace, &nbsp;, and | are converted to 
# a single space each.
{ gsub(/([|])|([ \r\n\t]+)|(&nbsp;)/, " ", $2); }

# Collect attachments when found by looking for HREF arguments
# whenever we're nesed inside a TABLE tag, however deep.
TAGS ~ /TABLE/ && ARGS["HREF"] {
        # Delete everything up to and including last slash in URL.
        # This leaves nothing but the filename.
        sub(/.*[/]/, "", ARGS["HREF"]);

        # They go into LINKS, not DATA, as we must print them last.
        LINKS[LINK++]=ARGS["HREF"];
        # ARGS does not clear itself, delete to prevent duplicates
        delete ARGS["HREF"];
        # Skip to next tag, prevents below code from appending CDATA to DATA
        next 
}

# When we find CDATA that isn't blank, and are inside a TD tag anywhere,
# append CDATA i.e. column two, to DATA[COL].
TAGS ~ /(^|%)TD%/ && !($2 ~ /^[ \r\n\t]+$/) {DATA[COL] = DATA[COL] $2 }

$ awk -f yanx.awk -f html.awk input.html

"AA Number. 3-456","The quick brown fox jumps over the lazy dog etc...","(Hello World May 20\, 2016)","May 18\, 2016","abcd.pdf","abcfull.pdf"
"BB Number. 7-890","The quick brown fox jumps over the lazy dog etc...","(Lord of the rings May 30\, 2016)","May 28\, 2016","efghi.pdf","efghifull.pdf","efghisum.pdf"

$