1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
from bs4 import BeautifulSoup
from datetime import datetime, timezone, timedelta
from enum import Enum
class ParserVersion(Enum):
ALPHA=1
def make_maimaidx_intl_parser(identifier: str, parser: ParserVersion):
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
parse_maimaidx_intl_prism_news_site = make_maimaidx_intl_parser("MAIMAIDX_INTL_PRISM", ParserVersion.ALPHA)
|
