"""Print HTML context around a keyword.

Usage: python ctx.py <url> <keyword> [window]
"""
import urllib.request
import sys
import re

UA = 'Mozilla/5.0 (compatible; paperbot/1.0)'
url = sys.argv[1]
kw = sys.argv[2]
win = int(sys.argv[3]) if len(sys.argv) > 3 else 600
req = urllib.request.Request(url, headers={'User-Agent': UA})
t = urllib.request.urlopen(req, timeout=40).read().decode('utf-8', 'ignore')
idx = 0
n = 0
while True:
    i = t.find(kw, idx)
    if i < 0:
        break
    n += 1
    print('--- occurrence %d at %d ---' % (n, i))
    print(t[max(0, i - win):i + win])
    idx = i + 1
    if n >= 5:
        break
print('occurrences found:', n)