From caa3cf245186ab0f6fb33e63a7dd838d834da12e Mon Sep 17 00:00:00 2001 From: Pinapelz Date: Thu, 12 Mar 2026 13:56:30 -0700 Subject: refactor: move to common NewsSource interface cleanup imports by defining initaliazers modules and decorator remove legacy scrapers remove single factory for sega games (sites don't change that much) --- sega/maimaidx_intl.py | 49 ------------------------------------------------- 1 file changed, 49 deletions(-) (limited to 'sega/maimaidx_intl.py') diff --git a/sega/maimaidx_intl.py b/sega/maimaidx_intl.py index 3e26a37..8182117 100644 --- a/sega/maimaidx_intl.py +++ b/sega/maimaidx_intl.py @@ -1,53 +1,7 @@ from bs4 import BeautifulSoup from datetime import datetime, timezone, timedelta -from enum import Enum import json -class ParserVersion(Enum): - ALPHA=1 - -def make_maimaidx_intl_parser(identifier: str, parser: ParserVersion): - """ - Parses the download page of maimai dx intl site. API route method below is preferred as information is the same - """ - def alpha_parser(html: str): - """ - Confirmed on: - PRISM - """ - soup = BeautifulSoup(html, "html.parser") - items = soup.select(".dl--pop__item") - - entries = [] - for item in items: - date_text = item.select_one(".dl--pop__head").text.strip().replace(" UP", "") - dt = datetime.strptime(date_text, "%Y.%m.%d").replace(tzinfo=timezone(timedelta(hours=9))) - timestamp = int(dt.timestamp()) - - img_tag = item.select_one("a.dl--pop__thumb img") - image_url = img_tag["srcset"] if img_tag else None - full_image_url = image_url.replace("../", "https://maimai.sega.com/") if image_url else None - - entry = { - "date": date_text, - "identifier": identifier, - "type": None, - "timestamp": timestamp, - "headline": None, - "content": f"New maimai DX International News / maimai DX International の新しいお知らせ\n\n{full_image_url}", - "url": None, - "images": [ - { - "image": full_image_url, - "link": None - } - ], - 'is_ai_summary': False - } - entries.append(entry) - return entries - if parser == ParserVersion.ALPHA: - return alpha_parser def parse_maimaidx_intl_api_route(raw_api_data: str, identifier: str, limit: int): route_data = json.loads(raw_api_data) @@ -84,6 +38,3 @@ def parse_maimaidx_intl_api_route(raw_api_data: str, identifier: str, limit: int } entries.append(entry) return entries - - -parse_maimaidx_intl_news_site = make_maimaidx_intl_parser("MAIMAIDX_INTL", ParserVersion.ALPHA) -- cgit v1.2.3