 
1 import urlparse, csv
2import threading
3from operator import itemgetter
4
5DICTHOSTS = {}
6
7class CSVReader(threading.Thread):
8 def __init__(self, threadname, filename):
9 self._file = filename
10 threading.Thread.__init__(self, name = threadname)
11
12 def run(self):
13 global DICTHOSTS
14 try:
15 _fhandle = open(self._file, 'r')
16 for line in _fhandle:
17 try:
18 host = urlparse.urlsplit(line.split('","')[1])[1]
19 except IndexError:
20 pass
21
22 if host:
23 if DICTHOSTS.has_key(host):
24 DICTHOSTS[host] += 1
25 else:
26 DICTHOSTS[host] = 1
27 finally:
28 _fhandle.close()
29
30 print self.getName(), self._file, 'has been traversed.', 'DICTHOSTS has', len(DICTHOSTS), 'items.'
31
32if __name__ == '__main__':
33 sortedList = []
34 path = 'E:/workspace/URLsSorter/src/titleurl/'
35 for i in range(1, 21):
36 si = str(i)
37 reader = CSVReader('Thread' + si, path + 'titleurl' + si + '.csv')
38 reader.start()
39 reader.join()
40
41
42 sortedList = sorted(DICTHOSTS.items(), key = itemgetter(1), reverse = True)
43
44 writter = csv.writer(open(path + 'Result.csv', 'wb'))
45 writter.writerows(sortedList)
|
|
|
| | 日 | 一 | 二 | 三 | 四 | 五 | 六 |
|---|
| 25 | 26 | 27 | 28 | 29 | 30 | 1 | | 2 | 3 | 4 | 5 | 6 | 7 | 8 | | 9 | 10 | 11 | 12 | 13 | 14 | 15 | | 16 | 17 | 18 | 19 | 20 | 21 | 22 | | 23 | 24 | 25 | 26 | 27 | 28 | 29 | | 30 | 31 | 1 | 2 | 3 | 4 | 5 |
|
导航
统计
- 随笔： 42
- 文章： 0
- 评论： 12
- 引用： 0
常用链接
留言簿(1)
随笔分类(32)
随笔档案(42)
文章分类
最新随笔
最新评论
阅读排行榜
评论排行榜
|
|