Quick script for scraping the current rankins from the GEN public choice awards.

gistfile1.txt

"""
Quick script for scraping the current rankins from the GEN public choice
awards.
"""
from pyquery import PyQuery as pq
import requests

URL = "https://app.wizehive.com/voting/dja2013/13447/%d"

entries = []

for i in range(1, 9):
    # Use requests directly to avoid issues with unicode decoding
    doc = pq(requests.get(URL % i).content.decode('utf8', 'ignore'))
    for item in doc(".item"):
        name = item.find("div").text_content().strip()
        raw_votes = item.getchildren()[-1].text_content().strip()
        votes = int(raw_votes.split("\t\t\t")[1]) if raw_votes else 0
        entries.append((name, votes))

i = 0
for entry in sorted(entries, key=lambda a: -a[1]):
    i += 1
    print "%02d - %s: %d" % (i, entry[0], entry[1])