def SearchCategorymember(self,categoryname):
try:
self.subcategoryresultlist.DeleteAllItems();
self.pageresultlist.DeleteAllItems();
wikiextractor = Extractor.wikiextractor()
query = configuration.api_url_zh +'&list=categorymembers&cmtitle=Category:%s&cmsort=timestamp&' \
'cmdir=desc&cmlimit=max' % categoryname
json_content = wikiextractor.getjson(query)
members = json_content['query']['categorymembers']
for member in members:
#TODO:如果没有Category属性,无法判断是否为子类(?)
pageid = str(member['pageid'])
if 'Category:' in member['title']:
subcategory = member['title'].lstrip('Category:')
index = self.subcategoryresultlist.InsertStringItem(sys.maxint, subcategory)
self.subcategoryresultlist.SetStringItem(index, 0, subcategory)
else:
page = member['title']
#TODO:待完善
# 说明不是有效的page
if ':' in page:
continue
index = self.pageresultlist.InsertStringItem(sys.maxint, pageid)
self.pageresultlist.SetStringItem(index, 0, pageid)
self.pageresultlist.SetStringItem(index, 1, page)
except Exception,e:
self.statusbar.SetStatusText(e.message,0)
def OnGeoExtract(self,evt):
try:
wikiextractor = Extractor.wikiextractor()
data_dict={}
members=self.GetGeoList()
wikiextractor.get_data_dict_from_pageid(members, data_dict,'f')
filewriter=FileWriter.filewriter()
filewriter.SaveToSQLite(data_dict)
#filewriter.SaveToExcel(data_dict)
self.statusbar.SetStatusText("保存成功，请检查excel文件",0)
except Exception,e:
self.statusbar.SetStatusText(e.message,0)
def OnExtract(self,evt):
try:
categoryname = self.categoryname.GetValue()
wikiextractor = Extractor.wikiextractor()
data_dict = {}
if self.extractsubcategoryck.Get3StateValue() == wx.CHK_CHECKED:
wikiextractor.parse_members(categoryname, data_dict,'t')
else:
wikiextractor.parse_members(categoryname, data_dict,'f')
filewriter=FileWriter.filewriter()
#filewriter.SaveToSQLite(data_dict)
filewriter.SaveToExcel(data_dict)
self.statusbar.SetStatusText(u"保存成功，请检查excel文件",0)
except Exception,e:
self.statusbar.SetStatusText(e.message,0)
def SearchbyPrex(self,prex):
try:
self.subcategoryresultlist.DeleteAllItems();
wikiextractor = Extractor.wikiextractor()
query = configuration.api_url_zh + '&list=allcategories&acprefix=%s'% prex
json_content = wikiextractor.getjson(query)
members = json_content['query']['allcategories']
for member in members:
#TODO:如果没有Category属性,无法判断是否为子类(?)
category = member['*']
index = self.subcategoryresultlist.InsertStringItem(sys.maxint, category)
self.subcategoryresultlist.SetStringItem(index, 0, category)
except Exception,e:
self.statusbar.SetStatusText(e.message,0)
def SearchbyGeo(self, lat, lon,primay):
try:
self.geopageresultlist.DeleteAllItems();
sourcelist = self.GetSourceList()
wikiextractor = Extractor.wikiextractor()
query =""
queries = {}
pagedatalist=[]
for source in sourcelist:
lastcount =-1
geopagelist = []
while(len(geopagelist)<100):
while True:
if primay:
query = source + '&list=geosearch&gscoord=%s|%s&gsradius=10000&gsglobe=earth&gsnamespace=0&gslimit=500&gsprop=dim&gsprimary=primary' %(lat,lon)
else:
query = source + '&list=geosearch&gscoord=%s|%s&gsradius=10000&gsglobe=earth&gsnamespace=0&gslimit=500&gsprop=dim&gsprimary=all' %(lat,lon)
json_content = wikiextractor.getjson(query)
queries = json_content['query']
nowcount =len(geopagelist)
if('geosearch' in queries.keys() and len(queries['geosearch'])>0):
break;
lat+=0.003;
lon+=0.003;
if(nowcount==lastcount):
break;
lastcount=len(geopagelist)
pages = queries['geosearch']
for page in pages:
try:
#TODO:如果没有Category属性,无法判断是否为子类(?)
lat = page['lat']
lon = page['lon']
pageid = page['pageid']
strpageid=str(pageid).decode('utf-8')
title = page['title'].decode('utf8')
strlat = str(page['lat']).decode('utf-8')
strlon = str(page['lat']).decode('utf-8')
strdim=str(page['dim']).decode('utf-8')
if(pageid in self.geopagelist):
continue
else:
geopagelist.append(pageid)
#测试写入查询结果信息
pagedata = {}
pagedata[u'文章ID']= pageid
pagedata[u'标题']= title
pagedata[u'经度']= lon
pagedata[u'纬度']= lat
pagedata[u'大小']= strdim
pagedatalist.append(pagedata);
index = self.geopageresultlist.InsertStringItem(sys.maxint, strpageid)
self.geopageresultlist.SetStringItem(index, 0, strpageid)
self.geopageresultlist.SetStringItem(index, 1, title)
self.geopageresultlist.SetStringItem(index, 2, strlat)
self.geopageresultlist.SetStringItem(index, 3, strlon)
self.geopageresultlist.SetStringItem(index, 4, strdim)
except Exception,e:
continue
#最后存储查询结果
self.resultdict[u'查询结果']=pagedatalist
