Created
May 11, 2015 21:59
-
-
Save neil90/982a38daed295f5f7f73 to your computer and use it in GitHub Desktop.
This file contains 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 bs4 import BeautifulSoup | |
| def make_soup(url): | |
| response = requests.get(website) | |
| return BeautifulSoup(response.text) | |
| def initial_links(website): | |
| soup = make_soup(website) | |
| links = [link["href"] for link in soup.findAll('a') | |
| if link.getText() in map(str, range(2009, 2016))] | |
| return links | |
| if __name__ == '__main__': | |
| website = 'http://www.presidency.ucsb.edu/sou.php' | |
| links = initial_links(website) # gets alll links | |
| # Now Im just looking at the first link and trying to figure out how to get the text | |
| links0 = make_soup(links[0]) | |
| text = links0.find('span', {'class' : 'displaytext'} ) | |
| print text | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment