Last active
September 19, 2015 11:39
-
-
Save blha303/a312976c48c84e60b846 to your computer and use it in GitHub Desktop.
Scrape and sort results for Canning by-election. Requirements: python 2.7 probably, requests, beautifulsoup4, tabulate
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 bs4 import BeautifulSoup as Soup | |
from tabulate import tabulate | |
import sys | |
headers = ["Candidate", "Party", "Votes", "%", "Swing (%)"] | |
def get_data(): | |
soup = Soup(requests.get("http://vtr.aec.gov.au/HouseDivisionFirstPrefs-18126-236.htm").text, "html.parser") | |
for row in soup.findAll('tr', id=lambda x: x and x.startswith("repeaterCandidates")): | |
yield [td.text for td in row.findAll('td')] | |
def main(): | |
if len(sys.argv) > 1: | |
if not sys.argv[1].isdigit(): | |
print "Usage: {} <column number to sort on>".format(sys.argv[0]) | |
return 1 | |
col = int(sys.argv[1]) | |
else: | |
col = 3 | |
data = [d for d in get_data()] | |
print tabulate(sorted(data, key=lambda x: float(x[col]), reverse=True), headers=headers) | |
return 0 | |
if __name__ == "__main__": | |
sys.exit(main()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment