Question

我有一个脚本，可以从文件中收集给定网址的response header信息。我现在经过的Argument/Input File来自外面。 Execution Method: python collect.py <Input.txt>。

输入文件：

1,http://www.example.com
2,http://www.blahblah.com
3,......

现在，我希望将带有URL的ID作为单个参数传递，如

python collect.py 1,http://www.example.com

并执行结果并将其写入outfile。

#!/usr/bin/python
import subprocess
import json
import sys
import httplib
import urlparse
import pickle
import sys



class HeaderFetcher:
        def __init__(self,url,headers={'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB;    rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3'}):
                self.report = {}
                self.initial_url = url
                self.request_headers = headers

        def fetch(self):
                self.fetchheaders(self.initial_url,self.request_headers)

        def fetchheaders(self,url,req_headers):
                try:
                        u = urlparse.urlparse(url)
                        scheme = u.scheme
                        ServerConnection = None
                        con = None
                        if 'http' == scheme:
                                ServerConnection = httplib.HTTPConnection
                        elif 'https' == scheme:
                                ServerConnection = httplib.HTTPSConnection
                        if None != ServerConnection:
                                con = ServerConnection(u.hostname,u.port,timeout=10)
                                con.request("GET",url,None,req_headers)
                                res = con.getresponse()
                                #print res
                                self.report[url] = res.getheaders()
                                if 301 == res.status or 302 == res.status:
                                        redirect_url = res.getheader('Location')
                                        if not redirect_url in self.report:
                                                if len(self.report.keys())<40:
                                                        self.fetchheaders(redirect_url,req_headers)
                except:
                        test="Error In Loading"
                        #print test

def process(infile='Input.txt'):
        #f = open('Input.txt','r')
        f = open(sys.argv[1],"r")
        agents= {'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB;    rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3'}
        finalJson = {}
        for line in f.readlines():
            App=line.strip().split(',')
            #print "Processing " + App[1]
            App_URL=App[1]
            ua=agents
            fetcher = HeaderFetcher(App_URL,{'User-Agent':ua})
            fetcher.fetch()
            url=fetcher.report
            keys = list(url)
            headerJson = {}
            for k in keys:
                headers=url[k]
                for header in headers:
                    headerJson[header[0]] = header[1]
            finalJson[App[0]] = headerJson
        header_final=json.dumps(finalJson,indent=4)
        #server_details = json.loads(response.read(header_final))
        #print header_final
        #json_data=open(header_final)
        #server_details = json.loads(header_final)
        server_details=json.loads(unicode(header_final),"ISO-8859-1")
        with open("Headers_Final_List.txt",'wb') as f :
                for appid, headers in server_details.iteritems():
                        htypes = [h for h in headers if h in (
                         'x-powered-by','server','x-aspnet-version','x-aspnetmvc-version')]
                        headers='{},{}'.format(appid, ','.join(htypes))
                        f.write(headers+'\n')
        f.close()

if __name__ == '__main__':
        process(sys.argv[-1])

有关如何从命令行解析单个参数的任何建议。

Answer 1

sys.argv不是一个文件，但你试图像一个文件一样阅读。

这样：

@Singleton
@Lock(LockType.READ)
public class SomeSingleton {}

应该更像：

def process(infile='Input.txt'):
        #f = open('Input.txt','r')
        f = open(sys.argv[1],"r")
        agents= {'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB;    rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3'}
        finalJson = {}
        for line in f.readlines():

然后您可以在其他方法中使用id和url。

Answer 2

#!/usr/bin/python

import sys

print 'Number of arguments:', len(sys.argv), 'arguments.'
print 'Argument List:', str(sys.argv)
n = len(sys.argv) -1
args = []
for i in sys.argv[n].split(','):
 args.append(i)
for i in args:
 print i

python arg.py 1，abc.txt

Number of arguments: 2 arguments.
Argument List: ['arg.py', '1,abc.txt']
1
abc.txt

如果在没有参数的情况下调用程序或者参数中没有逗号

，则此方法不会因IndexError：list index超出范围而失效

Answer 3

id, url = sys.argv[1].split(',')

Python：命令行参数问题

3 个答案: