From afa57aad122015a71b73c5d1bd814a1ab9ef8ca8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eirik=20Eik=C3=A5s?= Date: Thu, 25 Oct 2018 12:28:04 +0200 Subject: [PATCH] Update scraper.py --- scraper.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/scraper.py b/scraper.py index 3ea3b43..2b7b15a 100644 --- a/scraper.py +++ b/scraper.py @@ -57,19 +57,19 @@ def get_cell_value(element, css): result_table = root.cssselect("table.footable")[0] result_cells = result_table.cssselect("tr") for result_cell in result_cells: - athlete_url = result_cell.cssselect("td")[2].cssselect("a")[0].get("href") + athlete_url = result_cell.cssselect("td")[1].cssselect("a")[0].get("href") parsed = urlparse.urlparse(athlete_url) athlete_id = urlparse.parse_qs(parsed.query)['competitorid'] result = { 'event': raceinfo['codex'], - 'rank': get_cell_value(result_cell.cssselect("td")[1], ""), - 'athlete': get_cell_value(result_cell.cssselect("td")[2], "a"), + 'rank': get_cell_value(result_cell.cssselect("td")[0], ""), + 'athlete': get_cell_value(result_cell.cssselect("td")[1], "a"), 'competitor_id': athlete_id, - 'yob': get_cell_value(result_cell.cssselect("td")[3], ""), - 'nation': get_cell_value(result_cell.cssselect("td")[4], ""), - 'time': get_cell_value(result_cell.cssselect("td")[5], ""), - 'behind': get_cell_value(result_cell.cssselect("td")[6], ""), - 'points': get_cell_value(result_cell.cssselect("td")[7], "") + 'yob': get_cell_value(result_cell.cssselect("td")[2], ""), + 'nation': get_cell_value(result_cell.cssselect("td")[3], ""), + 'time': get_cell_value(result_cell.cssselect("td")[4], ""), + 'behind': get_cell_value(result_cell.cssselect("td")[5], ""), + 'points': get_cell_value(result_cell.cssselect("td")[6], "") } print result print link