cyril/RSSEbra
Watch
1
0
Fork
You've already forked RSSEbra
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Cleaner way to get time and image

Browse source
This commit is contained in:
Cyril NOVEL 2026-07-28 13:34:44 +02:00
commit 6352fb9b97
1 changed files with 14 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

28
gen_feed.py
View file

@ -15,22 +15,24 @@ class Article:
def __init__(self, title: str, link: str, is_paid: bool): def __init__(self, title: str, link: str, is_paid: bool):
self.title = title self.title = title
self.link = link self.link = link
res = re.search(regex_date, link)
self.text = "" self.text = ""
h_m = self._get_time_and_text() self.date = datetime.datetime.now()
self.date = datetime.datetime(int(res.group(1)), int(res.group(2)), int(res.group(3)), h_m[0], h_m[1]) self._get_time_and_text()
self.date = self.date.replace(tzinfo=ZoneInfo("Europe/Paris"))
self.date = self.date.astimezone(datetime.timezone.utc)
self.is_paid = is_paid self.is_paid = is_paid
def _get_time_and_text(self): def _get_time_and_text(self):
response = requests.get(self.link)
print(f" Retrieving {self.link} to get pub time...") print(f" Retrieving {self.link} to get pub time...")
response = requests.get(self.link)
print(f" Response is <{response.status_code}>")
if response.status_code != 200: if response.status_code != 200:
print(f" Failed to get it ({response.status_code}, defaulting to 3AM)") return
return (3, 0) # Default to 3:00 AM
soup = BeautifulSoup(response.text, 'html.parser') soup = BeautifulSoup(response.text, 'html.parser')
# Handle time
publish_date_time = soup.find("meta", property="article:published_time")["content"]
self.date = datetime.datetime.strptime(publish_date_time, '%Y-%m-%dT%H:%M:%SZ')
self.date = self.date.replace(tzinfo=ZoneInfo("UTC"))
# Handle text # Handle text
text = [] text = []
if soup.find("div", class_="chapo") is not None: if soup.find("div", class_="chapo") is not None:
@ -40,12 +42,10 @@ class Article:
text.append(p.text) text.append(p.text)
self.text = "\n".join(text) self.text = "\n".join(text)
publish = soup.find("span", class_="publish").text # Handle image if any
res = re.search(regex_time, publish) img_url = soup.find("meta", property="og:image")
if not res: if img_url is not None:
print(f" Failed to parse it, defaulting to 3AM)") self.text = f"<img alt=\"Image illustrant l'article\" src=\"{img_url["content"]}\" />\n" + self.text
return (3, 0) # Default to 3:00 AM
return (int(res.group(1)), int(res.group(2)))
def full_title(self): def full_title(self):