-
-
Save anonymous/0401933cdd71b426eb25 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
doc = Hpricot(URI.parse(url).read) | |
(doc/"//*[@id=\"ctl00_PlaceHolderMain_CommonQuestionsDisplayEditModePanel_Search_dvsearchresult\"]/table/tr").each do |item| #pull the result table | |
page = item.to_html.scan(/<td><a id="ctl00_PlaceHolderMain_CommonQuestionsDisplayEditModePanel_Search_lvRegisterRecordsList_ctrl.*_IndNameHyperlink" href="(.+?)">.*<\/a><\/td>/) | |
name = item.to_html.scan(/<td><a id="ctl00_PlaceHolderMain_CommonQuestionsDisplayEditModePanel_Search_lvRegisterRecordsList_ctrl.*_IndNameHyperlink" href=".*">(.*)<\/a><\/td>/)[0]#need | |
business = item.to_html.scan(/<span id="ctl00_PlaceHolderMain_CommonQuestionsDisplayEditModePanel_Search_lvRegisterRecordsList_ctrl.*_spanOrgName">(.*)<\/span>/)#need | |
suburb = item.to_html.scan(/<span id="ctl00_PlaceHolderMain_CommonQuestionsDisplayEditModePanel_Search_lvRegisterRecordsList_ctrl.*_spanOrgName">.*<\/span>\s*<\/td>\s*<td>(.*)<\/td>\s*<td>.*<\/td>/)#need | |
town = item.to_html.scan(/<span id="ctl00_PlaceHolderMain_CommonQuestionsDisplayEditModePanel_Search_lvRegisterRecordsList_ctrl.*_spanOrgName">.*<\/span>\s*<\/td>\s*<td>.*<\/td>\s*<td>(.*)<\/td>/)#need | |
#now go to personal page | |
src = open(page).read() | |
#phone = pp.scan(/<th class="pieIE">Phone:<\/th>\s*<td>(.*)<\/td>/) | |
#puts phone | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment