Created
October 12, 2010 10:14
-
-
Save JaimeObregon/621982 to your computer and use it in GitHub Desktop.
This file contains 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/bash | |
for i in `seq 0 50 550`; do wget "http://comerciocantabria.com/index.php?option=com_comprofiler&task=usersList&listid=4&Itemid=174&limitstart=$i" -Ocomercios.`expr $i / 50 + 1`.txt; done | |
for i in comercios*txt; do grep "<table id=\"cbUserTable\"" $i -A1000 | grep "</table" -B 1000 | grep span | sed 's/\t*<div class=\"cbUserListFieldLine\"><span class=\"cbListFieldCont cbUserListFC_//' | sed 's/<\/span><\/div>//' | cut -d ">" -f 2,3,4; done | grep -i "http://[^comercio]" | sort | uniq > urls.txt | |
for i in `cat urls.txt` ; do wget "$i/index.php?option=com_virtuemart&Itemid=60&category_id=0&page=shop.browse&limitstart=0&limit=10000" -q -O`echo $i | sed 's/http:\/\///'`; done | |
for i in www*; do cat $i | grep "id=\"product_list\"" -A10000 | grep "r class=\"clr" -B10000 | grep -i h3 | cut -d "\"" -f 4 | grep -v "h3" | sort > productos.$i; done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment