cyril/RSSEbra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add possible description in RSS item

Browse source
This commit is contained in:
Cyril NOVEL 2026-05-22 20:59:52 +02:00
commit 3b217a6501
1 changed files with 14 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

17
gen_feed.py
View file

@ -16,19 +16,30 @@ class Article:
self.title = title self.title = title
self.link = link self.link = link
res = re.search(regex_date, link) res = re.search(regex_date, link)
h_m = self._get_time() self.text = ""
h_m = self._get_time_and_text()
self.date = datetime.datetime(int(res.group(1)), int(res.group(2)), int(res.group(3)), h_m[0], h_m[1]) self.date = datetime.datetime(int(res.group(1)), int(res.group(2)), int(res.group(3)), h_m[0], h_m[1])
self.date = self.date.replace(tzinfo=ZoneInfo("Europe/Paris")) self.date = self.date.replace(tzinfo=ZoneInfo("Europe/Paris"))
self.date = self.date.astimezone(datetime.timezone.utc) self.date = self.date.astimezone(datetime.timezone.utc)
self.is_paid = is_paid self.is_paid = is_paid
def _get_time(self): def _get_time_and_text(self):
response = requests.get(self.link) response = requests.get(self.link)
print(f" Retrieving {self.link} to get pub time...") print(f" Retrieving {self.link} to get pub time...")
if response.status_code != 200: if response.status_code != 200:
print(f" Failed to get it ({response.status_code}, defaulting to 3AM)") print(f" Failed to get it ({response.status_code}, defaulting to 3AM)")
return (3, 0) # Default to 3:00 AM return (3, 0) # Default to 3:00 AM
soup = BeautifulSoup(response.text, 'html.parser') soup = BeautifulSoup(response.text, 'html.parser')
# Handle text
text = []
if soup.find("div", class_="chapo") is not None:
text.append(soup.find("div", class_="chapo").text)
paragraphs = soup.find_all("div", class_="textComponent")
for p in paragraphs:
text.append(p.text)
self.text = "\n".join(text)
publish = soup.find("span", class_="publish").text publish = soup.find("span", class_="publish").text
res = re.search(regex_time, publish) res = re.search(regex_time, publish)
if not res: if not res:
@ -76,7 +87,7 @@ def generate_feed(town_url, feed_url, feed_path):
print("Generating feed...") print("Generating feed...")
items = [] items = []
for a in articles: for a in articles:
item = Item(title = a.full_title(), link= a.link, guid = Guid(a.link), pubDate = a.date) item = Item(title = a.full_title(), link= a.link, guid = Guid(a.link), pubDate = a.date, description = a.text)
items.append(item) items.append(item)
feed = Feed(title = soup.title.string, feed = Feed(title = soup.title.string,
link = feed_url, link = feed_url,