Cleaner way to get time and image

gen_feed.py

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