From 662ecfcaa542639f039e095265b69d06e6c9d4b0 Mon Sep 17 00:00:00 2001 From: Paul Bradshaw Date: Thu, 25 Jan 2018 12:10:04 +0000 Subject: [PATCH] Update scraper.py --- scraper.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/scraper.py b/scraper.py index df89574..d5b8a1f 100644 --- a/scraper.py +++ b/scraper.py @@ -18,8 +18,9 @@ print link print link.text print link.text_content() - print link.attrib['href'] - fullurl = baseurl+link.attrib['href'].split("?")[0] + cleanurl = link.attrib['href'].split("?")[0] + print cleanurl + fullurl = baseurl+cleanurl linkslist.append(fullurl) for url in linkslist: