Python实现随机读取文本N行数据

工作中需要判断某个文本中的URL是否能正常访问，并且随机获取其中N行能正常访问的URL数据，我的思路是：读取文本每一行数据，用urlopen访问，将返回状态码为200的URL保存到一个列表，获得列表长度，使用random产生一个随机值作为列表下标，获取该行数据。具体实现如下：

import urllib2,random
from sets import Set

def get_responses(url):
    global good_list
    global bad_list
    if not url.startswith("http:"):
        http_url = "http://" + url
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 5.1; rv:10.0.1) Gecko/20100101 Firefox/10.0.1',}
    try:
        request = urllib2.Request(http_url, headers=headers)
        resp = urllib2.urlopen(request)
        print url
    except urllib2.URLError, e:
        print e
        bad_list.append(url)
        return 0

    retcode = resp.getcode()
    if retcode == 200:
        good_list.append(url)
        #return 1
    else:
        bad_list.append(url)
        #return 0

def readFile():
    try:
        urllist = open(r'C:Users888Desktopurls.txt','r')
    except IOError:
        print "file does not exist.
"
    for item in urllist:
        item = item.strip('
')
        r = get_responses(item)

    urllist.close()
    print "Total URLs: %d, Good URLs:%d, Bad URLs: %d." %((len(good_list)+len(bad_list)),len(good_list),len(bad_list))
    
def writeFile(linenum):
    result = []
    linelen = len(good_list)
    while len(result) < int(linenum):
        s = random.randint(0,linelen-1)
        result.append(good_list[s])
        result = list(Set(result))
        
    # Put the good_url in goodurl.txt file
    try:
        goodurl = open(r'C:Users888Desktopgoodurl.txt','w+')
    except IOError:
        print "file does not exist.
"

    for item in result:
        goodurl.write(item+'
')
    goodurl.close()

    print "The mission is done, Please check the goodurl.txt file"
    
if __name__ == "__main__":  
    good_list = []
    bad_list = []
    readFile()
    writeFile(150)