Created
August 23, 2019 05:06
-
-
Save reaganscofield/fe8249881d980b77dbeeff2e441be68c to your computer and use it in GitHub Desktop.
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
| import requests | |
| from requests import get | |
| import urllib | |
| from bs4 import BeautifulSoup | |
| from urllib.error import HTTPError | |
| from urllib.request import urlopen | |
| login_url = 'https://slashdot.org/my/login' | |
| scraping_url = 'https://slashdot.org' | |
| class SlashDot: | |
| def actions(): | |
| username = input("Enter username : ") | |
| password = input("Enter password : ") | |
| if username and password: | |
| session = requests.Session() | |
| per_session = session.post(login_url, data={'unickname': username, 'upasswd': password}) | |
| if per_session: | |
| try: | |
| BeautifulSoup(session.get(login_url).content, 'html.parser') | |
| response = get(scraping_url) | |
| html_soup = BeautifulSoup(response.text, 'html.parser') | |
| articles = html_soup.find_all('article', class_ = 'article') | |
| articles_data = [] | |
| for article in articles[:3]: | |
| data = { | |
| "headline": article.header.h2.find('span', class_ = 'story-title').a.text, | |
| "author": article.header.find('div', class_ = 'details').find('span', class_ = "story-byline").find('a'), | |
| "date": article.header.find('div', class_ = 'details').find('span', class_ = "story-byline").time.text | |
| } | |
| articles_data.append(data) | |
| if len(articles_data) > 0: | |
| for article in articles_data: | |
| print(article) | |
| else: | |
| print("articles not found!") | |
| except HTTPError as error: | |
| print(error) | |
| else: | |
| print("username and password is required") | |
| SlashDot.actions() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment