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
|
from bs4 import BeautifulSoup
from datetime import datetime
from urllib.parse import urljoin
import time
import re
def parse_museca_plus_news_site(html: str) -> list:
soup = BeautifulSoup(html, "html.parser")
news_posts = []
base_url = "https://museca.plus/"
for p in soup.select("div.subcontainer.center.text > p"):
text = p.get_text(strip=True, separator=' ')
date_match = re.search(r'(\d{4}-\d{2}-\d{2})', text)
if not date_match:
continue
date_str = date_match.group(1)
try:
dt = datetime.strptime(date_str, "%Y-%m-%d")
timestamp = int(time.mktime(dt.timetuple()))
except ValueError:
continue
images = []
for img in p.find_all("img"):
img_url = urljoin(base_url, img.get("src"))
images.append({"image": img_url, "link": None})
content = p.get_text(separator=' ', strip=True)
news_posts.append({
'date': date_str,
'identifier': 'MUSECA_PLUS',
'type': None,
'timestamp': timestamp,
'headline': None,
'content': content,
'url': None,
'images': images,
'is_ai_summary': False
})
return news_posts
|
