From e8feae4c42fcf1027c82c2392e3c998989c46cf3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eirik=20Eik=C3=A5s?= Date: Thu, 25 Oct 2018 12:53:25 +0200 Subject: [PATCH] Update scraper.py --- scraper.py | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/scraper.py b/scraper.py index f4d809f..0f31aee 100644 --- a/scraper.py +++ b/scraper.py @@ -58,13 +58,12 @@ def get_cell_value(element, css): result_cells = result_table.cssselect("tr") for result_cell in result_cells: if len(result_cell.cssselect("td")) > 1: + athlete = result_cell.cssselect("td a")[0] + print athlete.text_content() + athlete_url = athlete.cssselect("a")[0].get("href") + parsed = urlparse.urlparse(athlete_url) + athlete_id = urlparse.parse_qs(parsed.query)['competitorid'] result = { - athlete = result_cell.cssselect("td a")[0] - print athlete.text_content() - athlete_url = athlete.cssselect("a")[0].get("href") - parsed = urlparse.urlparse(athlete_url) - athlete_id = urlparse.parse_qs(parsed.query)['competitorid'] - 'event': raceinfo['codex'], 'rank': result_cell.cssselect("td")[0].text_content(), 'athlete': result_cell.cssselect("td")[1].text_content(),