def url_usr_agent(fromsta, tosta, date):
#proxy = {'http':'27.24.158.155:84'}
proxy = {'http': '110.4.24.173:80'}
proxy_support = urllib2.ProxyHandler(proxy)
opener = urllib2.build_opener(proxy_support)
urllib2.install_opener(opener)
i_headers = {
'User-Agent':
'Mozilla/5.0(Windows NT 6.1) AppleWebKit/537.36(KHTML,like Geko) Chrome/31.0.1650.48'
}
staname2code = getstaname2code()
web = (
u"https://kyfw.12306.cn/otn/lcxxcx/query?purpose_codes=ADULT&queryDate=%s&from_station=%s&to_station=%s"
% (date, staname2code[fromsta], staname2code[tosta]))
req = urllib2.Request(web, headers=i_headers)
response = urllib2.urlopen(req)
result = response.read()
if result == "-1":
print "there isn't any train from %s to %s on %s" % (fromsta, tosta,
date)
return -1
try:
data = json.loads(result)["data"]["datas"]
except KeyError:
print "there isn't any train from %s to %s on %s" % (fromsta, tosta,
date)
return -1
recordlist = DoubleLink()
for i, ticketInfo in enumerate(data):
temp = [{"station_train_code":ticketInfo["station_train_code"],\
"start_station_name":ticketInfo["start_station_name"],\
"to_station_name":ticketInfo["to_station_name"],\
"start_time":ticketInfo["start_time"],\
"arrive_time":ticketInfo["arrive_time"],\
"swz_num":ticketInfo["swz_num"],\
"ydz_num":ticketInfo["zy_num"],\
"edz_num":ticketInfo["ze_num"],\
"rw_num":ticketInfo["rw_num"],\
"yw_num":ticketInfo["yw_num"],\
"yz_num":ticketInfo["yz_num"],\
"wz_num":ticketInfo["wz_num"],\
"canWebBuy":ticketInfo["canWebBuy"]}]#,can't omit
if recordlist.getlength() == 0:
recordlist.initlist(temp)
else:
recordlist.append(temp[0])
return recordlist
def spidereasyone(fromsta, tosta, date):
#fromsta = u'合肥'
#tosta = u'淮南'
#date = '2016-02-10'
staname2code = getstaname2code()
requeststr = (
u"https://kyfw.12306.cn/otn/lcxxcx/query?purpose_codes=ADULT&queryDate=%s&from_station=%s&to_station=%s"
% (date, staname2code[fromsta], staname2code[tosta]))
#print requeststr
request = urllib2.Request(requeststr)
print "attempt to get infromation form kyfw.12306.cn"
response = urllib2.urlopen(request)
print "inquiry successly"
result = response.read()
#print result
data = json.loads(result)["data"]["datas"]
recordlist = DoubleLink()
sta2stare = open("./data/sta2stare", "w")
for i, ticketInfo in enumerate(data):
temp = [{"station_train_code":ticketInfo["station_train_code"],\
"start_station_name":ticketInfo["start_station_name"],\
"to_station_name":ticketInfo["to_station_name"],\
"start_time":ticketInfo["start_time"],\
"arrive_time":ticketInfo["arrive_time"],\
"swz_num":ticketInfo["swz_num"],\
"ydz_num":ticketInfo["zy_num"],\
"edz_num":ticketInfo["ze_num"],\
"rw_num":ticketInfo["rw_num"],\
"yw_num":ticketInfo["yw_num"],\
"yz_num":ticketInfo["yz_num"],\
"wz_num":ticketInfo["wz_num"],\
"canWebBuy":ticketInfo["canWebBuy"]}]#,can't omit
if recordlist.getlength() == 0:
recordlist.initlist(temp)
else:
recordlist.append(temp[0])
sta2stare.write(str(recordlist.getitem(i)))
sta2stare.write('\n')
sta2stare.write(str(recordlist))
sta2stare.close()
#display(recordlist)
return recordlist
def spidereasyone(fromsta,tosta,date):
#fromsta = u'合肥'
#tosta = u'淮南'
#date = '2016-02-10'
staname2code = getstaname2code()
requeststr= (u"https://kyfw.12306.cn/otn/lcxxcx/query?purpose_codes=ADULT&queryDate=%s&from_station=%s&to_station=%s"%(date,staname2code[fromsta],staname2code[tosta]))
#print requeststr
request = urllib2.Request(requeststr)
print "attempt to get infromation form kyfw.12306.cn"
response = urllib2.urlopen(request)
print "inquiry successly"
result = response.read()
#print result
data = json.loads(result)["data"]["datas"]
recordlist = DoubleLink()
sta2stare = open("./data/sta2stare","w")
for i,ticketInfo in enumerate(data):
temp = [{"station_train_code":ticketInfo["station_train_code"],\
"start_station_name":ticketInfo["start_station_name"],\
"to_station_name":ticketInfo["to_station_name"],\
"start_time":ticketInfo["start_time"],\
"arrive_time":ticketInfo["arrive_time"],\
"swz_num":ticketInfo["swz_num"],\
"ydz_num":ticketInfo["zy_num"],\
"edz_num":ticketInfo["ze_num"],\
"rw_num":ticketInfo["rw_num"],\
"yw_num":ticketInfo["yw_num"],\
"yz_num":ticketInfo["yz_num"],\
"wz_num":ticketInfo["wz_num"],\
"canWebBuy":ticketInfo["canWebBuy"]}]#,can't omit
if recordlist.getlength() == 0:
recordlist.initlist(temp)
else:
recordlist.append(temp[0])
sta2stare.write(str(recordlist.getitem(i)))
sta2stare.write('\n')
sta2stare.write(str(recordlist))
sta2stare.close()
#display(recordlist)
return recordlist
def url_usr_agent(fromsta,tosta,date):
#proxy = {'http':'27.24.158.155:84'}
proxy = {'http':'110.4.24.173:80'}
proxy_support = urllib2.ProxyHandler(proxy)
opener = urllib2.build_opener(proxy_support)
urllib2.install_opener(opener)
i_headers = {'User-Agent':'Mozilla/5.0(Windows NT 6.1) AppleWebKit/537.36(KHTML,like Geko) Chrome/31.0.1650.48'}
staname2code = getstaname2code()
web = (u"https://kyfw.12306.cn/otn/lcxxcx/query?purpose_codes=ADULT&queryDate=%s&from_station=%s&to_station=%s"%(date,staname2code[fromsta],staname2code[tosta]))
req = urllib2.Request(web,headers = i_headers)
response = urllib2.urlopen(req)
result = response.read()
if result == "-1":
print "there isn't any train from %s to %s on %s"%(fromsta,tosta,date)
return -1
try:
data = json.loads(result)["data"]["datas"]
except KeyError:
print "there isn't any train from %s to %s on %s"%(fromsta,tosta,date)
return -1
recordlist = DoubleLink()
for i,ticketInfo in enumerate(data):
temp = [{"station_train_code":ticketInfo["station_train_code"],\
"start_station_name":ticketInfo["start_station_name"],\
"to_station_name":ticketInfo["to_station_name"],\
"start_time":ticketInfo["start_time"],\
"arrive_time":ticketInfo["arrive_time"],\
"swz_num":ticketInfo["swz_num"],\
"ydz_num":ticketInfo["zy_num"],\
"edz_num":ticketInfo["ze_num"],\
"rw_num":ticketInfo["rw_num"],\
"yw_num":ticketInfo["yw_num"],\
"yz_num":ticketInfo["yz_num"],\
"wz_num":ticketInfo["wz_num"],\
"canWebBuy":ticketInfo["canWebBuy"]}]#,can't omit
if recordlist.getlength() == 0:
recordlist.initlist(temp)
else:
recordlist.append(temp[0])
return recordlist
#/usr/bin/env python
#-*-coding:utf8-*-
import urllib2
import urllib
import json
import sys
import spiderpractice
sys.path.append("data")
from staname2code import getstaname2code
staname2code = getstaname2code()
#print staname2code
stacode = staname2code.keys()
date = u"2016-02-11"
sta2stalist = []
for fromsta in stacode:
for tosta in stacode:
if fromsta != tosta:
tmp = [fromsta, tosta]
sta2stalist.append(tmp)
print len(sta2stalist)
for j in range(1):
print j + 1, "/", len(sta2stalist)
#recordlist = spiderpractice.spidereasyone(sta2stalist[j][0],sta2stalist[j][1],date)
recordlist = spiderpractice.spidereasyone(u"合肥", u"淮南", date)
print recordlist
if recordlist == -1:
continue
else:
sta2stalistfile = open("./database/%s" % (sta2stalist[j]), "w")
"arrive_time":ticketInfo["arrive_time"],\
"swz_num":ticketInfo["swz_num"],\
"ydz_num":ticketInfo["zy_num"],\
"edz_num":ticketInfo["ze_num"],\
"rw_num":ticketInfo["rw_num"],\
"yw_num":ticketInfo["yw_num"],\
"yz_num":ticketInfo["yz_num"],\
"wz_num":ticketInfo["wz_num"],\
"canWebBuy":ticketInfo["canWebBuy"]}]#,can't omit
if recordlist.getlength() == 0:
recordlist.initlist(temp)
else:
recordlist.append(temp[0])
return recordlist
staname2code = getstaname2code()
#print staname2code
stacode = staname2code.keys()
date = u"2016-02-11"
sta2stalist=[]
for fromsta in stacode:
for tosta in stacode:
if fromsta != tosta:
tmp = [fromsta,tosta]
sta2stalist.append(tmp)
#print len(sta2stalist)
#for j in range(len(sta2stalist)):
for j in range(400000,len(sta2stalist)):
num = open("numofscan","r+")
num.write(str(j))
num.close