Python打印scrapy蜘蛛抓取树结构的方法

通过下面这段代码可以一目了然的知道scrapy的抓取页面结构，调用也非常简单

#!/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' (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()

希望本文所述对大家的Python程序设计有所帮助。