|
|
Parse multiple html files in directory
12-17-2014
awk '/^<h2 id="genes"/ {getline
> for (i=1; i<=NF; i++)
> {n1=gsub (".*omim.org/entry/", "", $i)
> n2=gsub (". target = ._blank.>", "\t", $i)
> n3=gsub ("</a>.*", "", $i)
> print $i > FILENAME".parsed"
> }
> }
> ' FS="," "C:\Users\cmccabe\Desktop\list\geneticslab.emory.edu.txt\parse\*"
awk: fatal: cannot open file `C:\Users\cmccabe\Desktop\list\geneticslab.emory.edu.txt\parse\*' for reading (No such file or directory)
.
12-17-2014
awk '/^<h2 id="genes"/ {getline
> print $i > FILENAME".parsed"
for (i=1; i<=NF; i++)
> {n1=gsub (".*omim.org/entry/", "", $i)
> n2=gsub (". target = ._blank.>", "\t", $i)
> n3=gsub ("</a>.*", "", $i)
> print $i > FILENAME".parsed"
> }
> }
> ' FS="," dir "C:\Users\cmccabe\Desktop\list\geneticslab.emory.edu.txt\parse\*"
awk: fatal: cannot open file `dir' for reading (No such file or directory).
12-18-2014
awk '/^<h2 id="genes"/ {getline for (i=1; i<=NF; i++) {n1=gsub (".*omim.org/entry/", "", $i) n2=gsub (". target = ._blank.>", "\t", $i) n3=gsub ("</a>.*", "", $i) print $i > FILENAME".parsed" }
}
' FS="," /home/dnascopev/Desktop/list/geneticslab.emory.edu.txt/parse/*.|
|
|
|