community-eval/stats-html2md

#! /usr/bin/env python
import re, sys
from BeautifulSoup import BeautifulSoup

def parse(stream):
    html = stream.read()
    html = re.sub(r'(?<=[-0-9A-Za-z])"">', '">a', html) # http://meta.stackoverflow.com/questions/167180/invalid-html-in-admin-review-community-eval-stats
    soup = BeautifulSoup(html)
    table = soup.find('table', {'class': 'sorter'})
    heads = [tag.find('span').contents[0]
             for tag in table.find('thead').find('tr').findAll('th')]
    rows = [[cell.contents[0] for cell in row.findAll('td')[1:]] +
            [row.find('a')['href']]
            for row in table.find('tbody').findAll('tr')]
    return rows

def print_markdown(sitename, data, out):
    data = [row[0:3] + row[5:] for row in data]
    digits = map(int, data[0][:-1])
    for row in data[1:]:
        for j in range(len(row)-1):
            n = abs(int(row[j]))
            if n > digits[j]: digits[j] = n
    for j in range(len(digits)): digits[j] = len(str(digits[j]))
    out.write('`Ex Sa NI sc`  \n')
    for row in data:
        for j in range(len(digits)):
            n = row[j]
            padding = digits[j] - len(n)
            if n[0] == '-': n = '&#x2012;' + n[1:]
            else: padding += 1
            out.write('&#x2007;' * padding + n + ' ')
        out.write('&nbsp;' * 2 + 'http://' + site_name + row[-1] + '  \n')
    out.write('\n')
    out.write('<sub> `Ex`/`Sa`/`NI`: number of &ldquo;excellent/satisfactory/needs improvement&rdquo; ratings </sub>  \n')
    out.write('<sup> `sc`: total score </sup>\n')

if __name__ == '__main__':
    if len(sys.argv) <= 1:
        print 'Usage:', sys.argv[0], 'SITE_NAME <community-eval-stats.html'
        sys.exit(1)
    site_name = sys.argv[1]
    if site_name.find('.') < 0: site_name += '.stackexchange.com'
    print_markdown(site_name, parse(sys.stdin), sys.stdout)