html2text.sh

   1 #!/bin/bash
   2
   3 ##################################################################
   4 # START_IP_HEADER                                                #
   5 #                                                                #
   6 # Written by Francois Fleuret                                    #
   7 # Contact <francois.fleuret@idiap.ch> for comments & bug reports #
   8 #                                                                #
   9 # END_IP_HEADER                                                  #
  10 ##################################################################
  11
  12 set -e
  13
  14 echo "(From html)"
  15
  16 elinks -no-numbering -no-references -dump -dump-width 80 -dump-charset utf-8 | \
  17     sed -e "s/\[IMG\]//g" -e "s/^[ \t]*$//" -e "s/^    //" | \
  18     awk '/^$/{ if (! blank++) print; next } { blank=0; print }'
  19  # | \
  20     # sed -e "s/^ *//"