Last active
June 4, 2021 14:28
-
-
Save aritraroy24/cd12cca07b581330ec59dacea91b3600 to your computer and use it in GitHub Desktop.
parsing RSS feed to get text and url
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class ParseFeed(): | |
def __init__(self, url): | |
self.feed_url = url | |
def clean(self, html): | |
''' | |
Getting the text from html and doing some cleaning | |
''' | |
soup = BeautifulSoup(html) | |
text = soup.get_text() | |
text = text.replace('\xa0', ' ') | |
return text | |
def parse(self): | |
''' | |
Parsing URL, and collecting descriptions and URLs of the news of which the character length of the tweet is in between 100 and 200 | |
''' | |
text_list = [] | |
url_list = [] | |
feeds = feedparser.parse(self.feed_url).entries | |
for f in feeds: | |
text = self.clean(f.get("description")) | |
url = f.get("link") | |
count = sum((text[i] != ' ') for i in range(len(text))) | |
if count < 150: | |
text_list.append(text) | |
url_list.append(url) | |
self.follow_back(api) | |
self.tweet(text_list, url_lis | |
feed = ParseFeed(url) | |
feed.parse() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment