Last active
December 30, 2015 00:19
-
-
Save edwardtoday/7748789 to your computer and use it in GitHub Desktop.
script to convert file from txt in gb18030 encoding to mobi
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/sh | |
| echo "convert to utf8" | |
| iconv -c -f GB18030 -t UTF8 $1 > $1.tmp | |
| echo "txt cleanup" | |
| sed 's/.$//' $1.tmp > $1.tmp.tmp && mv $1.tmp.tmp $1.tmp # dos2unix | |
| sed '/^$/d;G' $1.tmp > $1.tmp.tmp && mv $1.tmp.tmp $1.tmp # double spacing | |
| sed 's/^[ \t]*//;s/[ \t]*$//' $1.tmp > $1.tmp.tmp && mv $1.tmp.tmp $1.tmp # delete leading and trailing spaces | |
| sed 's/#//' $1.tmp > $1.tmp.tmp && mv $1.tmp.tmp $1.tmp # delete # char | |
| sed 's/^第.*[卷部篇]/##&/' $1.tmp > $1.tmp.tmp && mv $1.tmp.tmp $1.tmp # make headings | |
| sed 's/^第.*[章节集回]/###&/' $1.tmp > $1.tmp.tmp && mv $1.tmp.tmp $1.tmp # make headings | |
| echo "convert to html" | |
| markdown -o $1.html $1.tmp | |
| echo "<HTML><BODY>" | cat - $1.html > $1.tmp && mv $1.tmp $1.html | |
| echo "</BODY></HTML>" >> $1.html | |
| echo "convert to mobi" | |
| kindlegen $1.html -c2 -verbose -o $2 | |
| rm $1.html |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment