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
|
from bs4 import BeautifulSoup
from datetime import datetime
import pytz
from urllib.parse import urljoin
import re
CATEGORY_MAP = {
"i_01": "NEWS",
"i_02": "MUSIC",
"i_03": "EVENT",
"i_04": "OTHER"
}
def parse_polaris_chord_news_site(html: str) -> list[dict]:
base_url = "https://p.eagate.573.jp/"
soup = BeautifulSoup(html, 'html.parser')
news_list = []
for li in soup.select('#info-news li.news'):
raw_date = li.find('li', class_='news_date').text.strip()
match = re.search(r'(\d{4}/\d{1,2}/\d{1,2})', raw_date)
if not match:
continue
date_str = match.group(1)
try:
dt = datetime.strptime(date_str, '%Y/%m/%d')
except ValueError:
continue
jst = pytz.timezone('Asia/Tokyo')
dt_jst = jst.localize(dt)
timestamp = int(dt_jst.timestamp())
raw_type = li.get('data-category')
post_type = CATEGORY_MAP.get(raw_type)
headline = li.find('li', class_='news_title').text.strip()
detail = li.find('li', class_='news_detail')
content = detail.get_text().strip()
first_a = detail.find('a', href=True)
url = urljoin(base_url, first_a['href']) if first_a else None
images = []
for img in detail.find_all('img'):
img_url = img.get('src')
link = None
if img.parent.name == 'a' and img.parent.has_attr('href'):
link = img.parent['href']
images.append({'image': img_url, 'link': link})
entry = {
'date': date_str,
'identifier': "POLARIS_CHORD",
'type': post_type,
'timestamp': timestamp,
'headline': headline,
'content': content,
'url': url,
'images': images,
'is_ai_summary': False,
}
news_list.append(entry)
return news_list
|
