Spider/NewsSpider
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

简单前端查询

Browse Source
This commit is contained in:
lzjqsdd 2016-05-07 00:19:09 +08:00
parent 4692601b5b
commit 088758e67b
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
ml/Search.py
View File

@ -41,7 +41,7 @@ class Search:
#'与'查询：先分词，再合并倒排记录,不考虑权重,返回文档号 #'与'查询：先分词，再合并倒排记录,不考虑权重,返回文档号
def QueryPhrase(self,searchPhrase,ishow = True): def QueryPhrase(self,searchPhrase,isshow = True):
words = jieba.cut(searchPhrase.decode('utf-8'),cut_all=False) words = jieba.cut(searchPhrase.decode('utf-8'),cut_all=False)
cut = Cut() cut = Cut()
result = set(range(1,100000)) result = set(range(1,100000))
@ -56,16 +56,16 @@ class Search:
for rec in record: for rec in record:
re.add(int(rec)) re.add(int(rec))
result = result & re result = result & re
print result if len(result) == 0:
if ishow: print 'Not Exists Record!'
if len(result) == 0: newslist=list()
print 'Not Exists Record!' for rst in result:
else: line = cut.getRow(int(rst),Global.cutnews_origin_dir,Global.filesize)
for rst in result: data = json.loads(line)
line = cut.getRow(int(rst),Global.cutnews_origin_dir,Global.filesize) if isshow:
data = json.loads(line) print data['title'],'\n',data['time'],'\n',data['content'],'\n'
print data['title'],'\n',data['time'],'\n',data['content'],'\n' newslist.append(data)
return result return newslist
#返回热点新闻 #返回热点新闻
def QueryHotNews(self): def QueryHotNews(self):
@ -75,6 +75,6 @@ class Search:
def QueryByTime(self): def QueryByTime(self):
pass pass
search = Search() #search = Search()
#search.QueryPhrase(sys.argv[1])
#search.QueryPhrase(sys.argv[1]) #search.QueryPhrase(sys.argv[1])
search.QueryPhrase(sys.argv[1])