Getting none when trying to parse description tag of rss feed

Question

so i'm acessing this rss feed as you can see there is a description tag. when i'm parsing the feed it returns back none for the description tag

and this is the error message i get

AttributeError: 'NoneType' object has no attribute 'text'
Traceback:
File "C:\Users\User\Desktop\news-recommendation\env\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 535, in _run_script
    exec(code, module.__dict__)
File "C:\Users\User\Desktop\news-recommendation\app.py", line 66, in <module>
    data=parseRSS('https://rss.app/feeds/6BJraU9Ff0IeqC3c.xml')
File "C:\Users\User\Desktop\news-recommendation\parseRSS.py", line 23, in parseRSS
    description_content = BeautifulSoup(item.description.text, "html.parser"

this is the code i'm using

    resp=requests.get(url)
    soup = BeautifulSoup(resp.content, features="xml")
    soup.prettify()
    items = soup.findAll('item')

    news_items = []
    for item in items:
        news_item={}
        news_item['title']=item.title.text
        news_item['link']=item.link.text
        news_item['pubDate']=item.pubDate.text
        news_items.append(news_item)
     
        description_content = BeautifulSoup(item.description.text, "html.parser")
        # Remove the img tag
        img_tag = description_content.find('img')
        if img_tag:
         img_tag.decompose()
    
         # Assuming you want to keep the rest of the content as HTML
        news_item['description'] = str(description_content)

Answer 1

Some <item> don't have <description> tag so you need to handle that:

import requests
from bs4 import BeautifulSoup


def get_data(url):
    resp = requests.get(url)
    soup = BeautifulSoup(resp.content, features="xml")
    soup.prettify()
    items = soup.findAll("item")

    news_items = []
    for item in items:
        news_item = {}
        news_item["title"] = item.title.text
        news_item["link"] = item.link.text
        news_item["pubDate"] = item.pubDate.text
        news_items.append(news_item)

        if item.description:
            description_content = BeautifulSoup(item.description.text, "html.parser")

            # Remove the img tag
            img_tag = description_content.find("img")
            if img_tag:
                img_tag.decompose()

            description_content = str(description_content)
        else:
            description_content = ""

        # Assuming you want to keep the rest of the content as HTML
        news_item["description"] = description_content

    return news_items


print(get_data("https://rss.app/feeds/6BJraU9Ff0IeqC3c.xml"))