Created
November 16, 2014 06:21
-
-
Save jmcph4/00d7459bc2b1e2200631 to your computer and use it in GitHub Desktop.
A small Python script that retrieves headlines from Bloomberg and counts the number of occurrences of a given keyword.
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
| from bs4 import BeautifulSoup | |
| import urllib2 | |
| def get_headlines(): | |
| url = "http://www.bloomberg.com/quickview" | |
| html = urllib2.urlopen(url).read() | |
| soup = BeautifulSoup(html) | |
| headlines = {} | |
| for link in soup.find_all('a', class_="q story_link black"): | |
| headlines.update({link.text:link.get('href')}) | |
| return headlines | |
| def print_headlines(): | |
| headlines = get_headlines() | |
| for headline in headlines: | |
| print(headline) | |
| def count_occurrences(keyword): | |
| headlines = get_headlines() | |
| per_headline = 0 | |
| total = 0 | |
| for headline in headlines: | |
| per_headline = headline.count(keyword) | |
| total = total + per_headline | |
| per_headline = 0 | |
| return total | |
| keyword = raw_input("Enter keyword: ") | |
| print(count_occurrences(keyword)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment