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：

 1 import urllib2,random
 2 from sets import Set
 3
 4 def get_responses(url):
 5     global good_list
 6     global bad_list
 7     if not url.startswith("http:"):
 8         http_url = "http://" + url
 9     headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 5.1; rv:10.0.1) Gecko/20100101 Firefox/10.0.1‘,}
10     try:
11         request = urllib2.Request(http_url, headers=headers)
12         resp = urllib2.urlopen(request)
13     print url
14     except urllib2.URLError, e:
15         print e
16         bad_list.append(url)
17         return 0
18
19     retcode = resp.getcode()
20     if retcode == 200:
21         good_list.append(url)
22         #return 1
23     else:
24         bad_list.append(url)
25         #return 0
26
27 def readFile():
28     try:
29         urllist = open(r‘C:\Users\888\Desktop\urls.txt‘,‘r‘)
30     except IOError:
31         print "file does not exist.\n"
32     for item in urllist:
33         item = item.strip(‘\n‘)
34         r = get_responses(item)
35
36     urllist.close()
37     print "Total URLs: %d, Good URLs:%d, Bad URLs: %d." %((len(good_list)+len(bad_list)),len(good_list),len(bad_list))
38
39 def writeFile(linenum):
40     result = []
41     linelen = len(good_list)
42     while len(Set(result)) < int(linenum):
43         s = random.randint(0,linelen-1)
44         result.append(good_list[s])
45
46     # Put the good_url in goodurl.txt file
47     try:
48         goodurl = open(r‘C:\Users\888\Desktop\goodurl.txt‘,‘w+‘)
49     except IOError:
50         print "file does not exist.\n"
51
52     for item in result:
53         goodurl.write(item+‘\n‘)
54     goodurl.close()
55
56     print "The mission is done, Please check the goodurl.txt file"
57
58 if __name__ == "__main__":
59     good_list = []
60     bad_list = []
61     readFile()
62     writeFile(100)