[PYTHON] Erstellen Sie ein Score-Ranking aus den JFL-Match-Ergebnissen

Schaben

import time
import unicodedata
from urllib.parse import urljoin
import re

import requests
from bs4 import BeautifulSoup

def cleaning(info, team, html):

    result = []

    for trs in html:

        data = [i.get_text(strip=True) for i in trs.select("th, td")]

        #Berechnen Sie die Verlängerungszeit nach dem Entfernen von Minuten
        data[0] = eval(data[0].rstrip("Protokoll"))

        #PK des Spielernamens entfernt
        data[2] = re.sub("\(.+\)", "", unicodedata.normalize("NFKC", data[2])).strip()

        result.append(info + [team] + data)

    return result

def scraping(n, url):

    r = requests.get(url)
    r.raise_for_status()

    soup = BeautifulSoup(r.content, "html5lib")

    #Sektion
    score_season = soup.select_one(
        "div.score-header > h2.score-meta > span.score-season"
    ).get_text(strip=True)

    score_season = int(score_season.strip("Sektion"))

    # print(score_season)

    #Datum (und Uhrzeit
    score_date = (
        soup.select_one("div.score-header > h2.score-meta > span.score-date")
        .get_text(strip=True)
        .split()
    )

    # print(score_date)

    #Teamname
    score_table = soup.select_one("table.score-table")

    home_team = score_table.select_one("th.score-team1").get_text(strip=True)
    away_team = score_table.select_one("th.score-team2").get_text(strip=True)

    # print(home_team, away_team)

    #Spielinformationen
    game_info = [n, score_season] + score_date + [home_team, away_team]

    #Ergebnis
    tag = soup.find("h3", text="Ergebnis")

    #Überprüfen Sie, ob es sich um eine Wertungstabelle handelt
    if tag:

        table_home = [
            trs
            for trs in tag.parent.select(
                "div.score-frame > div.score-left > table > tbody > tr"
            )
        ]
        home_data = cleaning(game_info, home_team, table_home)

        table_away = [
            trs
            for trs in tag.parent.select(
                "div.score-frame > div.score-right > table > tbody > tr"
            )
        ]
        away_data = cleaning(game_info, away_team, table_away)

        score_data = home_data + away_data

        return score_data

    return None

url = "http://www.jfl.or.jp/jfl-pc/view/s.php?a=1542&f=2020A001_spc.html"

r = requests.get(url)
r.raise_for_status()

soup = BeautifulSoup(r.content, "html5lib")

links = [urljoin(url, link.get("href")) for link in soup.select("td.detail-link > a") if link.text == "Einzelheiten"]

result = []

for i, link in enumerate(links):

    score_data = scraping(i, link)

    if score_data:

        result.extend(score_data)
    
    time.sleep(1)

Daten-Wrangling

import pandas as pd

df = pd.DataFrame(result, columns=["Spiel", "Sektion", "Datum", "Tageszeiten", "Zuhause", "Weg", "Teamname", "Zeit", "Einheitliche Nummer", "Spielername"])

df

df["Ergebnis"] = 1

#Rangliste der Zielnummern
pv_goal = df.pivot_table(
    values="Ergebnis", index=["Spielername", "Teamname", "Einheitliche Nummer"], aggfunc=sum, fill_value=0
).drop(["Eigenes Ziel"]).reset_index()

pv_goal["Einheitliche Nummer"] = pv_goal["Einheitliche Nummer"].astype(int)

#Rangfolge
pv_goal["Rangfolge"] = pv_goal["Ergebnis"].rank(ascending=False, method="min").astype(int)

#Mannschaft
jfl_2020 = [
    "Ｈｏｎｄａ ＦＣ",
    "Sony Sendai FC",
    "Tokyo Musashino City FC",
    "Tegevajaro Miyazaki",
    "Honda Lock SC",
    "Verspa Oita",
    "FC Osaka",
    "MIO Biwako Shiga",
    "Viatin Mie",
    "FC Maruyasu Okazaki",
    "Suzuka Point Getters",
    "Line Mail Aomori",
    "Nara Club",
    "Matsue City FC",
    "Iwaki FC",
    "Kochi United SC",
]

team = {name: i for i, name in enumerate(jfl_2020, 1)}

pv_goal["Team ID"] = pv_goal["Teamname"].map(team)

#Aufsteigende Reihenfolge nach Rang, Teamname, Spielername
pv_goal.sort_values(["Rangfolge", "Team ID", "Einheitliche Nummer"], ascending=[True, True, True], inplace=True)

pv_goal.drop(["Team ID", "Einheitliche Nummer"], axis=1, inplace=True)

pv_goal.set_index("Rangfolge", inplace=True)

pv_goal.to_csv("goal.csv")

Rangfolge

df_rank = pd.read_html("http://www.jfl.or.jp/jfl-pc/view/s.php?a=1544", index_col=0, header=0)[0]

df_rank["Spielername"] = df_rank["Spielername"].str.normalize("NFKC")

df_rank.to_csv("ranking.csv")