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
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
import time
from datetime import datetime
from enum import Enum
from bs4 import BeautifulSoup
class ParserVersion(Enum):
ALPHA = 1
def make_ongeki_parser(identifier: str, parser: ParserVersion):
def alpha_parser(html: str):
soup = BeautifulSoup(html, "html.parser")
items = []
for li in soup.select("li.p-news__listChild"):
a_tag = li.select_one("a.p-news__listLink")
url = a_tag["href"] if a_tag else None
img_tag = li.select_one(".p-news__listThumb img")
image_url = img_tag["src"] if img_tag else None
image_alt = img_tag["alt"] if img_tag else ""
image_link = url if image_url else None
date_type_text = li.select_one(".p-news__listTextUpper")
date_text = (
date_type_text.text.strip().split("/")[0].strip()
if date_type_text
else None
)
type_text = (
date_type_text.text.strip().split("/")[-1].strip()
if "/" in date_type_text.text
else None
)
timestamp = None
if date_text:
try:
dt = datetime.strptime(date_text, "%Y.%m.%d %a")
timestamp = int(time.mktime(dt.timetuple()))
except:
timestamp = None
entry = {
"date": date_text,
"identifier": identifier,
"type": type_text if type_text not in ["GAME", "CARDMAKER"] else None,
"timestamp": timestamp,
"headline": None,
"content": image_alt,
"url": url,
"is_ai_summary": False,
"images": [{"image": image_url, "link": image_link}]
if image_url
else [],
}
items.append(entry)
return items
if parser == ParserVersion.ALPHA:
return alpha_parser
parse_ongeki_news_site = make_ongeki_parser("ONGEKI_JPN", ParserVersion.ALPHA)
|
