Python打印scrapy蜘蛛抓取树结构的方法

#!/usr/bin/env python
import fileinput, re
from collections import defaultdict
def print_urls(allurls, referer, indent=0):
  urls = allurls[referer]
  for url in urls:
    print ‘ ‘*indent + referer
    if url in allurls:
      print_urls(allurls, url, indent+2)
def main():
  log_re = re.compile(r‘<GET (.*?)> \(referer: (.*?)\)‘)
  allurls = defaultdict(list)
  for l in fileinput.input():
    m = log_re.search(l)
    if m:
      url, ref = m.groups()
      allurls[ref] += [url]
  print_urls(allurls, ‘None‘)
main()