def extractDict(self):
for url in self.urls:
if checkPath(homepath,self.folder,url):
pass
else:
self.fd["posttime"] = 0
if self.kind=="1":
self.ChuShou(url)
elif self.kind=="2":
self.ChuZu(url)
elif self.kind=="3":
self.QiuGou(url)
else:
self.QiuZu(url)
self.fd['city'] = urlparse(url)[1].replace('.58.com',"")
#makePath(homepath,self.folder,url)
#超过七天
if (time.time() -self.fd["posttime"]) > 7*24*36000:return
self.fd["c"]="houseapi"
self.fd["a"]="savehouse"
self.fd["is_checked"] = 0
self.fd["web_flag"] = "58"
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
def extractDict(self):
for url in self.urls:
if checkPath(homepath,self.folder,url):
pass
else:
try:
self.fd["posttime"] = 0
if self.kind=="1":
self.sell(url)
elif self.kind=="2":
self.rent(url)
elif self.kind=="3":
self.buy(url)
else:
self.require(url)
self.fd['city'] = urlparse(url)[1].replace('.58.com',"")
makePath(homepath,self.folder,url)
#超过七天
if (time.time() -self.fd["posttime"]) > 7*24*36000:return
except:pass
if self.fd['city'] == 'su':self.fd['city'] = 'suzhou'
self.fd["c"]="houseapi"
self.fd["a"]="savehouse"
self.fd["is_checked"] = 1
self.fd["web_flag"] = "58"
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
req=urllib2.Request("http://site.jjr360.com/app.php", urllib.urlencode(self.fd))
p=self.br.open(req).read().strip()
print p.decode('gbk')
def extractDict(self):
for url in self.urls:
if checkPath(homepath,self.folder,url):
pass
else:
try:
if self.kind=="1":
self.sell(url)
elif self.kind=="2":
self.rent(url)
elif self.kind=="3":
self.buy(url)
else:
self.require(url)
makePath(homepath,self.folder,url)
#超过七天
if (time.time() -self.fd["posttime"]) > 7*24*36000:return
except:pass
self.fd["c"]="houseapi"
self.fd["a"]="savehouse"
self.fd["is_checked"] = 1
self.fd["web_flag"] = "gj"
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
print "*"*80
if len(self.fd)==7 or len(self.fd)==17:
print "#####################################"
continue
req=urllib2.Request("http://site.jjr360.com/app.php", urllib.urlencode(self.fd))
p=self.br.open(req).read().strip()
print p.decode('gbk')
print "*"*80
def extractDict(self):
if checkPath(homepath,self.folder,self.urls):
pass
else:
try:
if self.kind=="1":
self.sell(self.urls)
elif self.kind=="2":
self.rent(self.urls)
elif self.kind=="3":
self.buy(self.urls)
else:
self.require(self.urls)
makePath(homepath,self.folder,self.urls)
#超过七天
# if (time.time() -self.fd["posttime"]) > 7*24*36000:return
except Exception,e:
msglogger.info("%s 链接采集异常"%self.urls)
# print "%s||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||"%self.urls
self.fd["c"]="houseapi"
self.fd["a"]="savehouse"
self.fd["is_checked"] = 1
self.fd["web_flag"] = "gj"
print "%s %s %s %s %s"%(("%s.soufun.com"% self.citycode),self.citycode, self.kind ,time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(time.time())), self.urls)
return self.fd
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
print "*"*80
def extractDict(self):
if checkPath(homepath,self.folder,self.urls):
pass
else:
try:
if self.kind=="1":
self.sell(self.urls)
elif self.kind=="2":
self.rent(self.urls)
elif self.kind=="3":
self.buy(self.urls)
else:
self.require(self.urls)
makePath(homepath,self.folder,self.urls)
#超过七天
if (time.time() -self.fd["posttime"]) > 7*24*36000:return
except:pass
self.fd["c"]="houseapi"
self.fd["a"]="savehouse"
self.fd["is_checked"] = 1
self.fd["web_flag"] = "gj"
return self.fd
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
print "*"*80
def extractDict(self):
if checkPath(homepath,self.folder,self.urls):
pass
else:
try:
self.fd["posttime"] = 0
if self.kind=="1":
self.sell(self.urls)
elif self.kind=="2":
self.rent(self.urls)
elif self.kind=="3":
self.buy(self.urls)
else:
self.require(self.urls)
self.fd['city'] = urlparse(self.urls)[1].replace('.58.com',"")
makePath(homepath,self.folder,self.urls)
#超过七天
# if self.fd["posttime"]:
# if (time.time() -self.fd["posttime"]) > 7*24*36000:return
except Exception,e:
msglogger.info("%s 链接采集异常"%self.urls)
# print "%s||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||"%self.urls
if isDEV:
# self.fd.update(getDefaultVal(4))
dfv=getDefaultVal(self.kind)
for item in dfv.items() :
# print item[0],item[1]
if item[0] not in self.fd:
self.fd[item[0]]=dfv.get(item[0])
for item in dfv.items() :
print item[0],self.fd[item[0]],type(self.fd[item[0]])
return
else:
dfv=getDefaultVal(self.kind)
for item in dfv.items() :
# print item[0],item[1]
if item[0] not in self.fd:
self.fd[item[0]]=dfv.get(item[0])
try:
if self.fd['city'] == 'su':self.fd['city'] = 'suzhou'
except:
self.fd['city'] = 'suzhou'
self.fd["is_checked"] = 1
self.fd["web_flag"] = "58"
if self.fd.get('is_ok')==False:
# print "jjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj"
self.fd={}
#print "%s %s %s %s %s"%(("%s.soufun.com"% self.citycode),self.citycode, self.kind ,time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(time.time())), self.urls)
return self.fd
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
req=urllib2.Request("http://site.jjr360.com/app.php", urllib.urlencode(self.fd))
p=self.br.open(req).read().strip()
print p.decode('gbk')
def __getAllNeedLinks(self):
cond=True
idx=0
checkit="0"
while cond:
url=self.baseUrl+self.urlpath%(str(idx+1))
# print url
req=urllib2.Request(url, None, self.header)
try:
p=self.br.open(req).read()
except:
continue
check=PyQuery(p)("div.pager strong span").text()
if check ==None or check==checkit:
cond=False
break
else:
checkit=check
if self.kind=="1" or self.kind=="3":
links=PyQuery(p)("table.tbimg td.t")
elif self.kind=="2" or self.kind=="4":
links=PyQuery(p)("table.tblist tr")
p=None
# print len(links)
for link in links:
if self.kind=="1" or self.kind=="3":
if re.search(ur'''更新时间：(.*)''',PyQuery(link).text()):
tm=re.search(ur'''更新时间：(.*)''',PyQuery(link).text()).group(1)
elif self.kind=="2"or self.kind=="4":
tm=PyQuery(link)("td.tc").eq(2).text()
if u"今天" in tm:
pass
elif u"小时" in tm:
pass
elif u"分钟" in tm:
pass
else:
Y=int(time.strftime('%Y', time.localtime()))
ttt="%s-%s"%(Y,tm)
if ttt<self.endtime:
cond=False
break
lk=PyQuery(link)("a.t").attr("href")
# print lk
if not checkPath(homepath,self.folder,lk):
LinkLog.info("%s|%s"%(self.kind,lk))
try:
getContent(lk,self.citycode,self.kind,self.upc)
except Exception,e:print "58 getContent Exception %s"%e
time.sleep(int(self.st))
def __getAllNeedLinks(self):
cond=True
idx=0
checkit="0"
while cond:
url=self.baseUrl+self.urlpath%("f"+str(idx*32))
#url="http://gz.ganji.com/fang2/u2f0/a1f768/"
# print url
try:
req=urllib2.Request(url, None, self.header)
p=self.br.open(req).read()
except:
continue
else:
check=PyQuery(p)("ul.pageLink li a.c").text()
if check==None or check==checkit:
cond=False
break
else:
checkit=check
links=PyQuery(p)("div.list dl")
p=None
# print len(links)
for link in links:
lk=self.baseUrl+PyQuery(link)(" a.list_title").attr("href")
# print lk
if self.kind=="3" or self.kind=="4":
tm=PyQuery(link)("dd span.time").text()
if re.match('''\d{2}-\d{2}''', tm):
Y=int(time.strftime('%Y', time.localtime()))
tm="%s-%s"%(Y,tm.strip())
if tm<self.endtime:
cond=False
break
elif "分钟" in tm:
pass
elif "小时" in tm:
pass
else:
cond=False
break
if not checkPath(homepath,self.folder,lk):
LinkLog.info("%s|%s"%(self.kind,lk))
try:
getContent(lk,self.citycode,self.kind,self.upc)
except Exception,e:print "ganji getContent Exception %s"%e
# fetch_quere.put({"mod":"ganji","link":lk,"citycode":self.citycode,"kind":self.kind})
# if lk not in self.clinks:
# self.clinks.append(lk)
idx=idx+1
def extractDict(self):
self.fd["citycode"]=self.citycode
for url in self.urls:
if checkPath(homepath,self.folder,url):
continue
req=urllib2.Request(url, None, self.header)
page=self.br.open(req).read()
if re.search(self.ht_r, page):
if "商铺"==re.search(self.ht_r, page).group(1):
continue
else:
ht=housetype(re.search(self.ht_r, page).group(1))
self.fd["house_type"]=ht
#lambda a: a and self.fd["borough_section"]=a.group(1) or self.fd["borough_section"]=""
self.fd["borough_section"]=re.search(self.ad_r, page)!=None and re.search(self.ad_r, page).group(1) or ""
self.fd["cityarea"]=re.search(self.ca_r, page)!=None and re.search(self.ca_r, page).group(1) or ""
self.fd["house_fitment"]=re.search(self.fm_r, page)!=None and re.search(self.fm_r, page).group(1) or ""
self.fd["house_kind"]=self.kind
self.fd["belong"]=re.search(self.bl_r, page)!=None and re.search(self.bl_r, page).group(1) or ""
self.fd["house_price"]=re.search(self.hp_r, page)!=None and re.search(self.hp_r, page).group(1) or ""
self.fd["house_totalarea"]=re.search(self.hta_r, page)!=None and re.search(self.hta_r, page).group(1) or ""
house_type=re.search(self.hrht_r, page)!=None and re.search(self.hrht_r, page).group(1) or ""
blank=0
if house_type.find("室")!= -1:
self.fd["house_room"]=house_type[blank:house_type.find("室")]
blank=house_type.find("室")+3
else:
self.fd["house_room"]=""
if house_type.find("厅")!=-1:
self.fd["house_hall"]=house_type[blank:house_type.find("厅")]
blank=house_type.find("厅")+3
else:
self.fd["house_hall"]=""
if house_type.find("卫")!=-1:
self.fd["house_toilet"]=house_type[blank:house_type.find("卫")]
else:
self.fd["house_toilet"]=""
self.fd["house_floor"]=re.search(self.hf_r, page)!=None and re.search(self.hf_r, page).group(1) or ""
self.fd["house_topfloor"]=re.search(self.hf_r, page)!=None and re.search(self.hf_r, page).group(2) or ""
self.fd["house_age"]=re.search(self.ha_r, page)!=None and re.search(self.ha_r, page).group(1) or ""
self.fd["house_sup"]=re.search(self.hs_r, page)!=None and re.search(self.hs_r, page).group(1) or ""
self.fd["house_desc"]=re.search(self.hd_r, page)!=None and re.search(self.hd_r, page).group(1) or ""
self.fd["borough_name"]=re.search(self.nm_r, page)!=None and re.search(self.nm_r, page).group(1) or ""
makePath(homepath,self.folder,url)
for ddd in self.fd.items():
print ddd[0],ddd[1]
print "="*60
def extractDict(self):
if checkPath(homepath,self.folder,self.urls):
pass
else:
try:
if self.kind=="1":
self.sell(self.urls)
elif self.kind=="2":
self.rent(self.urls)
elif self.kind=="3":
self.buy(self.urls)
else:
self.require(self.urls)
makePath(homepath,self.folder,self.urls)
#超过七天
# if (time.time() -self.fd["posttime"]) > 7*24*36000:return
except Exception,e:
self.fd['house_title']=None
msglogger.info("%s 链接采集异常"%self.urls)
# print "%s||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||"%self.urls
if isDEV:
# self.fd.update(getDefaultVal(4))
dfv=getDefaultVal(self.kind)
for item in dfv.items() :
# print item[0],item[1]
if item[0] not in self.fd:
self.fd[item[0]]=dfv.get(item[0])
for item in dfv.items() :
print item[0],self.fd[item[0]],type(self.fd[item[0]])
return
else:
dfv=getDefaultVal(self.kind)
for item in dfv.items() :
# print item[0],item[1]
if item[0] not in self.fd:
self.fd[item[0]]=dfv.get(item[0])
self.fd["is_checked"] = 1
self.fd["web_flag"] = "gj"
#print "%s %s %s %s %s"%(("%s.soufun.com"% self.citycode),self.citycode, self.kind ,time.strftime("%Y-%m-%d %H:%M:%S",time.localtime(time.time())), self.urls)
return self.fd
if not self.fd["is_checked"]:
for i in self.fd.items():
print i[0],i[1]
print "*"*80