Skip to content

Instantly share code, notes, and snippets.

@Gijs-Koot
Created February 13, 2017 14:22
Show Gist options
  • Save Gijs-Koot/ee2bd8b2da0e56c7ab13fc25d8ef4291 to your computer and use it in GitHub Desktop.
Save Gijs-Koot/ee2bd8b2da0e56c7ab13fc25d8ef4291 to your computer and use it in GitHub Desktop.
Download and parse current year KNVB eredivisie results and schedule from their site.
from bs4 import BeautifulSoup
import requests
import dateparser
import pandas as pd
uitslagen_url = "http://www.knvb.nl/competities/eredivisie/uitslagen"
programma_url = "http://www.knvb.nl/competities/eredivisie/programma"
uitslagen_soup = BeautifulSoup(requests.get(uitslagen_url).content, "lxml")
programma_soup = BeautifulSoup(requests.get(programma_url).content, "lxml")
def parse_timetable_page(soup, parse_score=True):
records = list()
for table in soup.select(".table-timetable"):
date = dateparser.parse(table.select_one(".header span").text)
for row in table.select("div.row"):
try:
home = row.select_one(".home > .team").text
away = row.select_one(".away > .team").text
r = {
"date": date,
"home": home,
"away": away
}
if parse_score:
home_score, away_score = row.select_one(".value.center").text.split("-")
r.update({
"home_score": int(home_score),
"away_score": int(away_score)
})
records.append(r)
except Exception as e:
print(e)
return records
uitslagen = parse_timetable_page(uitslagen_soup)
programma = parse_timetable_page(programma_soup, parse_score=False)
ed = pd.DataFrame(uitslagen + programma)
ed.to_csv("./games.csv")
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment