wgetter2.bash

BASH Shell 编程 经典教程 《高级SHELL脚本编程》中文版

list_func() #  Gives the user the option to use the -i option to wget,
            #+ and a list of URLs.
{
while [ 1 ]; do
   echo "Enter the name of the file containing URL's (press q to change your 
mind)."
   read urlfile
   if [ ! -e "$urlfile" ] && [ "$urlfile" != q ]; then
       # Look for a file, or the quit option.
       echo "That file does not exist!"
   elif [ "$urlfile" = q ]; then # Check quit option.
       echo "Not using a url list."
       return
   else
      echo "using $urlfile."
      echo "If you gave me url's on the command line, I'll use those first."
                            # Report wget standard behaviour to the user.
      lister=" -i $urlfile" # This is what we want to pass to wget.
      return
   fi
done
}


cookie_func() # Give the user the option to use a different cookie file.
{
while [ 1 ]; do
   echo "Change the cookies file. Press return if you don't want to change 
it."
   read Cookies
   # NB: this is not the same as Cookie, earlier.
   # There is an 's' on the end.
   # Bit like chocolate chips.
   if [ -z "$Cookies" ]; then                 # Escape clause for wusses.
      return
   elif [ ! -e "$Cookies" ]; then
      echo "File does not exist.  Try again." # Keep em going . . .
   else
       CookiesON=" --load-cookies $Cookies"   # File is good -- let's use it!
       return
   fi
done
}



run_func()
{
if [ -z "$OPTARG" ]; then
# Test to see if we used the in-line option or the query one.
   if [ ! -d "$savePath" ]; then      # In case directory doesn't exist . . .
      echo "$savePath does not appear to exist."
      echo "Please supply path and filename of saved wget commands:"
      read newFile
         until [ -f "$newFile" ]; do  # Keep going till we get something.
            echo "Sorry, that file does not exist.  Please try again."
            # Try really hard to get something.
            read newFile
         done


# -------------------------------------------------------------------------
#         if [ -z ( grep wget ${newfile} ) ]; then
          # Assume they haven't got the right file and bail out.
#         echo "Sorry, that file does not contain wget commands.  Aborting."
#         exit
#         fi
#
# This is bogus code.
# It doesn't actually work.
# If anyone wants to fix it, feel free!
# -------------------------------------------------------------------------


      filePath="${newFile}"
   else
   echo "Save path is $savePath"
      echo "Please enter name of the file which you want to use."
      echo "You have a choice of:"
      ls $savePath                                    # Give them a choice.
      read inFile
         until [ -f "$savePath/$inFile" ]; do         # Keep going till we get something.
            if [ ! -f "${savePath}/${inFile}" ]; then # If file doesn't exist.
               echo "Sorry, that file does not exist.  Please choose from:"
               ls $savePath                           # If a mistake is made.
               read inFile
            fi
         done
      filePath="${savePath}/${inFile}"  # Make one variable . . .
   fi
else filePath="${savePath}/${OPTARG}"   # Which can be many things . . .
fi

if [ ! -f "$filePath" ]; then           # If a bogus file got through.
   echo "You did not specify a suitable file."
   echo "Run this script with the -${save} option first."
   echo "Aborting."
   exit $E_NO_SAVEFILE
fi
echo "Using: $filePath"
while read; do
    eval $REPLY
    echo "Completed: $REPLY"
done < $filePath  # Feed the actual file we are using into a 'while' loop.

exit
}



# Fish out any options we are using for the script.
# This is based on the demo in "Learning The Bash Shell" (O'Reilly).
while getopts ":$save$cook$help$list$runn:$inpu$wopt" opt
do
  case $opt in
     $save) save_func;;   #  Save some wgetter sessions for later.
     $cook) cookie_func;; #  Change cookie file.
     $help) usage;;       #  Get help.
     $list) list_func;;   #  Allow wget to use a list of URLs.
     $runn) run_func;;    #  Useful if you are calling wgetter from, for example,
                          #+ a cron script.
     $inpu) run_func;;    #  When you don't know what your files are named.
     $wopt) wopts;;       #  Pass options directly to wget.
        \?) echo "Not a valid option."
            echo "Use -${wopt} if you want to pass options directly to wget,"
            echo "or -${help} for help";;      # Catch anything else.
  esac
done
shift $((OPTIND - 1))     # Do funky magic stuff with $#.


if [ -z "$1" ] && [ -z "$lister" ]; then
                          #  We should be left with at least one URL
                          #+ on the command line, unless a list is 
			  #+ being used -- catch empty CL's.
   echo "No URL's given!  You must enter them on the same line as wgetter2."
   echo "E.g.,  wgetter2 http://somesite http://anothersite."
   echo "Use $help option for more information."
   exit $E_NO_URLS        # Bail out, with appropriate error code.
fi

URLS=" $@"
# Use this so that URL list can be changed if we stay in the option loop.

while [ 1 ]; do
   # This is where we ask for the most used options.
   # (Mostly unchanged from version 1 of wgetter)
   if [ -z $curDepth ]; then
      Current=""
   else Current=" Current value is $curDepth"
   fi
       echo "How deep should I go? (integer: Default is $depthDefault.$Current)"
       read Depth   # Recursion -- how far should we go?
       inputB=""    # Reset this to blank on each pass of the loop.
       echo "Enter the name of the referring page (default is none)."
       read inputB  # Need this for some sites.

       echo "Do you want to have the output logged to the terminal"
       echo "(y/n, default is yes)?"
       read noHide  # Otherwise wget will just log it to a file.

       case $noHide in    # Now you see me, now you don't.
          y|Y ) hide="";;
          n|N ) hide=" -b";;
            * ) hide="";;
       esac

       if [ -z ${Depth} ]; then       #  User accepted either default or current depth,
                                      #+ in which case Depth is now empty.
          if [ -z ${curDepth} ]; then #  See if a depth was set on a previous iteration.
             Depth="$depthDefault"    #  Set the default recursion depth if nothing
                                      #+ else to use.
          else Depth="$curDepth"      #  Otherwise, set the one we used before.
          fi
       fi
   Recurse=" -l $Depth"               # Set how deep we want to go.
   curDepth=$Depth                    # Remember setting for next time.

       if [ ! -z $inputB ]; then
          RefA=" --referer=$inputB"   # Option to use referring page.
       fi

   WGETTER="${CommandA}${pattern}${hide}${RefA}${Recurse}${CookiesON}${lister}${Woptions}${URLS}"
   #  Just string the whole lot together . . .
   #  NB: no embedded spaces.
   #  They are in the individual elements so that if any are empty,
   #+ we don't get an extra space.

   if [ -z "${CookiesON}" ] && [ "$cFlag" = "1" ] ; then
       echo "Warning -- can't find cookie file"
       # This should be changed, in case the user has opted to not use cookies.
   fi

   if [ "$Flag" = "S" ]; then
      echo "$WGETTER" >> $savePath/wget-${today}
      #  Create a unique filename for today, or append to it if it exists.
      echo "$inputB" >> $savePath/site-list-${today}
      #  Make a list, so it's easy to refer back to,
      #+ since the whole command is a bit confusing to look at.
      echo "Command saved to the file $savePath/wget-${today}"
           # Tell the user.
      echo "Referring page URL saved to the file $savePath/site-list-${today}"
           # Tell the user.
      Saver=" with save option"
      # Stick this somewhere, so it appears in the loop if set.
   else
       echo "*****************"
       echo "*****Getting*****"
       echo "*****************"
       echo ""
       echo "$WGETTER"
       echo ""
       echo "*****************"
       eval "$WGETTER"
   fi

       echo ""
       echo "Starting over$Saver."
       echo "If you want to stop, press q."
       echo "Otherwise, enter some URL's:"
       # Let them go again. Tell about save option being set.

       read
       case $REPLY in                # Need to change this to a 'trap' clause.
          q|Q ) exit $E_USER_EXIT;;  # Exercise for the reader?
            * ) URLS=" $REPLY";;
       esac

       echo ""
done


exit 0