rsparse.py

   1 # generator
   2 def find_all_tags(content, tag):
   3         tag_end = ' \t\n/>'
   4         def find_next_tag_start(content, tag, start=0):
   5                 l = len(tag)
   6                 lc = len(content)
   7                 while start < lc:
   8                         if content[start] != '<':
   9                                 start += 1
  10                                 continue
  11                         i = 0
  12                         while i < l and start+1+i < lc:
  13                                 if content[start+1+i] != tag[i]: break
  14                                 i += 1
  15                         if i == l and start+1+i < lc and content[start+1+i] in tag_end:
  16                                 return start
  17                         start += 1
  18                 return -1
  19
  20         def find_next_tag_end(content, tag, start=0):
  21                 s = '</%s>'%tag
  22                 i = content.find(s, start)
  23                 if i == -1: return i
  24                 return i + len(s)
  25
  26         def find_next_tag(content, tag, start=0):
  27                 s = find_next_tag_start(content, tag, start)
  28                 if s == -1: return (-1, -1)
  29                 e = find_next_tag_end(content, tag, s+1+len(tag))
  30                 if e == -1: return (-1, -1)
  31                 return (s, e)
  32
  33         start = 0
  34         while start != -1:
  35                 s,e = find_next_tag(content, tag, start)
  36                 if s == -1: break
  37                 yield content[s:e]
  38                 start = e
  39
  40 if __name__ == '__main__':
  41         import sys
  42         with open(sys.argv[1], "r") as h:
  43                 s = h.read()
  44                 for a in find_all_tags(s, 'a'):
  45                         print a