Question

我是编程和python的新手。因此我有一个问题。我的同学们已经创建了很少的python脚本，但现在我们陷入困境，没有更多的想法。我们需要将几个python脚本合并为一个工作脚本。请问有人可以帮助我们吗？脚本：

# Script: webpage_get.py
# Desc: Fetches data from a webpage, and parses out hyperlinks.
# Author: Wojciech Kociszewski
# Created: Nov, 2013
#
import sys, urllib

def wget(url):
    ''' Try to retrieve a webpage via its url, and return its contents'''
    print '[*] wget()'
    #open file like url object from web, based on url
    url_file = urllib.urlopen(url)
    # get webpage contents
    page = url_file.read()
    return page

def main():
    #temp testing url argument
    sys.argv.append('http://www.soc.napier.ac.uk/~cs342/CSN08115/cw_webpage/index.html')
    #check args
    if len(sys.argv) != 2:
        print '[-] Usage: webpage_get URL'
        return

    #Get and analyse web page
    print wget(sys.argv[1])

if __name__ == '__main__':
    main()
# Script: webpage_getlinks.py
# Desc: Basic web site info gathering and analysis script. From a URL gets
# page content, parsing links out.
# Author: Wojciech Kociszewski
# Created: Nov, 2013
#
import sys, re
import webpage_get

def print_links(page):
    ''' find all hyperlinks on a webpage passed in as input and print '''
    print '[*] print_links()'
    # regex to match on hyperlinks, returning 3 grps, links[1] being the link itself
    links = re.findall(r'(\<a.*href\=.*)(http\:.+)(?:[^\'" >]+)', page)
    # sort and print the links
    links.sort()
    print '[+]', str(len(links)), 'HyperLinks Found:'
    for link in links:
        print link[1]

def main():
    # temp testing url argument
    sys.argv.append('http://www.soc.napier.ac.uk/~cs342/CSN08115/cw_webpage/index.html')
    # 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()
# Script: webpage_getemails.py
# Desc: Basic web site info gathering and analysis script. From a URL gets
# page content, parsing emails out.
# Author: Wojciech Kociszewski
# Created: Nov, 2013
#
import sys, re
import webpage_get

def print_emails(page):
    ''' find all emails on a webpage passed in as input and print '''
    print '[*] print_emails()'
    # regex to match on emails
    emails = re.findall(r'([\d\w\.-_]+@[\w\d\.-_]+\.\w+)', page)
    # sort and print the emails
    emails.sort()
    print '[+]', str(len(emails)), 'Emails Found:'
    for email in emails:
        print email

def main():
    # temp testing url argument
    sys.argv.append('http://www.soc.napier.ac.uk/~cs342/CSN08115/cw_webpage/index.html')
    # Check args
    if len(sys.argv) != 2:
        print '[-] Usage: webpage_getemails'
        return

    # Get the web page
    page = webpage_get.wget(sys.argv[1])
    # Get the emails
    print_emails(page)

if __name__ == '__main__':
    main()

Answer 1

分析您的脚本并找到公共代码

将公共代码转换为模块

使用公共代码重写单个程序

如果您希望将各个程序组合成一个大程序，那将会更容易

如何将几个python脚本合并为一个？

1 个答案: