【发布时间】:2013-12-02 21:16:25
【问题描述】:
有谁知道我如何将 URL 作为 Python 中的参数作为页面? 只是为了在脚本中读取行,用户输入到 shell 并将其作为参数传递只是为了使脚本更便携?
import sys, re
import webpage_get
def print_links(page):
''' find all hyperlinks on a webpage passed in as input and
print '''
print '\n[*] print_links()'
links = re.findall(r'(\http://\w+\.\w+[-_]*\.*\w+\.*?\w+\.*?\w+\.*[//]*\.*?\w+ [//]*?\w+[//]*?\w+)', page)
# sort and print the links
links.sort()
print '[+]', str(len(links)), 'HyperLinks Found:'
for link in links:
print link
def main():
# temp testing url argument
sys.argv.append('http://www.4chan.org')
# Check args
if len(sys.argv) != 2:
print '[-] Usage: webpage_getlinks URL'
return
# Get the web page
page = webpage_get.wget(sys.argv[1])
# Get the links
print_links(page)
if __name__ == '__main__':
main()
【问题讨论】: