mirrorweb

#!/bin/bash

wget \
    --mirror \
    --page-requisites \
    --html-extension \
    --restrict-file-names=windows \
    --convert-links \
    --waitretry=30 \
    $1
#    --random-wait \
#    --wait=1 \
#    --limit-rate=10k \
#    --no-clobber \
#    --domains website.org \
#    --no-parent \

#The options are:
#--mirror: recursive mirroring with infinite depth
#--domains website.org: don't follow links outside website.org.
#--no-parent: don't follow links outside the directory tutorials/html/.
#--page-requisites: get all the elements that compose the page
#  (images, CSS and so on).
#--html-extension: save files with the .html extension.
#--convert-links: convert links so that they work locally, off-line.
#--restrict-file-names=windows: modify filenames so that they will
#  work in Windows as well.
#--no-clobber: don't overwrite any existing files
#  (used in case the download is interrupted and resumed).
#--limit-rate: Limit download speed
#--wait: wait n seconds between retrievals
#--random-wait: wait between 0.5 to 1.5 seconds between retrievals
#--waitretry: use linear backoff - wait 1 second after first failure,
#  2 seconds after second ut to defined value