From eb9ae196f443858f62998ae1ebde05f0ab249376 Mon Sep 17 00:00:00 2001 From: Leif Greiss Date: Fri, 1 Dec 2017 16:48:20 -0500 Subject: [PATCH] Update scraper.py --- scraper.py | 5 ----- 1 file changed, 5 deletions(-) diff --git a/scraper.py b/scraper.py index 98ba9aa..d14d87f 100644 --- a/scraper.py +++ b/scraper.py @@ -1,14 +1,9 @@ import scraperwiki html = scraperwiki.scrape('http://inmo.ie/6022') print "Click on the ...more link to see the whole page" - import lxml.html root = lxml.html.fromstring(html) # turn our HTML into an lxml object tds = root.cssselect('td') # get all the tags -print tds -for td in tds: - print lxml.html.tostring(td) # the full HTML tag - print td.text # just the text inside the HTML tag for td in tds: record = { "td" : td.text } # column name and values try: