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: