Gets "top" .cz/sk sites as measured by TOPList.cz/sk

.gitignore

.py[co]
.idea

toplist.py

#!/usr/bin/env python
# pip install pyquery tablib
'''
    Gets "top" .cz/sk sites as measured by TOPList.cz/sk
'''
from __future__ import division
import math

from pyquery import PyQuery as pq
import tablib

def get_sites(count=1, tld='cz'):
    PER_PAGE = 50
    lines = []

    count = count if count < 1001 else 1000
    for offset in xrange(0, int(math.ceil(count/PER_PAGE))):
        page = pq('http://toplist.%(tld)s/all/%(offset)d' % dict(tld=tld, offset=offset * PER_PAGE))
        for line in page.find('table.tabulka tr')[1:]:
            tds = pq(line).find('td[class^="s"]')[3:5]
            if tds:
                web, hits = map(pq, tds)
                lines.append((web.find('a').attr('href'), web.text(), hits.text()))

    return tablib.Dataset(*lines[:count], headers=('url', 'name', 'avg_hits'))

if __name__ == '__main__':
    import argparse
    
    parser = argparse.ArgumentParser(description='Get top sites from TOPList.cz or TOPList.sk')
    parser.add_argument('-c', '--count', action='store', default=50, type=int, help='number of sites (max 1000)')
    parser.add_argument('-o', '--output_format', action='store', default='csv', choices=('json', 'yaml', 'csv', 'xls'),
     help='format to render data')
    parser.add_argument('-t', '--tld', action='store', default='cz', type=str, choices=('cz','sk'), 
        help='use TopList.cz or Toplist.sk')

    args = parser.parse_args()
    print getattr(get_sites(count=args.count, tld=args.tld), args.output_format)