TIF2022 日別ラインナップ抽出スクリプト

tif2022_lineup_scraper.py

from bs4 import BeautifulSoup as bs
import requests

URL = "https://official.idolfes.com/s/tif2022/page/lineup?ima=0210"
DAYS = {
    "5日": "p-lineup_artist_data tif22-day1",
    "6日": "p-lineup_artist_data tif22-day2",
    "7日": "p-lineup_artist_data tif22-day3",
}
DAY1_2 = "p-lineup_artist_data tif22-day1_2"
DAY1_3 = "p-lineup_artist_data tif22-day1_3"
DAY2_3 = "p-lineup_artist_data tif22-day2_3"


def extract_lineup(soup, klass):
    day1_groups = soup.find_all("div", class_=klass)
    names = [
        g.find("div", class_="p-lineup_artist_data__name")
        .find("div", class_="p-lineup_artist_data__name-text")
        .text.strip()
        for g in day1_groups
    ]
    names = [name.split("\n")[0] for name in names]
    return names


res = requests.get(URL)
content = res.content

soup = bs(content, "html.parser")

lineups = {}

for day, cls in DAYS.items():
    names = extract_lineup(soup, cls)
    lineups[day] = names

names_day1_2 = extract_lineup(soup, DAY1_2)
lineups["5日"].extend(names_day1_2)
lineups["6日"].extend(names_day1_2)

names_day2_3 = extract_lineup(soup, DAY2_3)
lineups["6日"].extend(names_day2_3)
lineups["7日"].extend(names_day2_3)

names_day1_3 = extract_lineup(soup, DAY1_3)
lineups["5日"].extend(names_day1_3)
lineups["7日"].extend(names_day1_3)

with open("tif2022_lineup_by_day.md", "w") as fout:
    for day in ["5日", "6日", "7日"]:
        fout.write(f"## {day}\n")
        for group in lineups[day]:
            if group.startswith("#"):
                group = f"\{group}" # 01familiaグループ対策
            elif group == "4864.":
                group = "4864\." # Markdownで1..となる謎現象対策
            fout.write(f"- {group}\n")