Finding line number when matching text
- src = open('linuxlaptop.htm').read()
- pattern = '<P>([^<]+)<SUP>' # or anything else
- for m in re.finditer(pattern, src):
- start = m.start()
- lineno = src.count('\n', 0, start) + 1
- offset = start - src.rfind('\n', 0, start)
- word = m.group(1)
- print "linuxlaptop.htm(%s,%s): %s" % (lineno, offset, word)