def getDistanceAndTimeByLngLat(origin, destination):
url = unicode(
'http://restapi.amap.com/v3/direction/driving?key={0}&origin={1}&destination={2}&strategy=9'
).format(getKey(), origin, destination)
res = httpGet(url)
jo = json.loads(res)
if (int(jo['status']) == 0):
writeWarningLog(
unicode("【高德】驾车 路径规划失败, origin:{0},destination:{1},原因：{2}").format(
origin, destination, jo))
return (None, None)
paths = jo['route']['paths']
if (len(paths) <= 0):
writeWarningLog(
unicode(
"【高德】驾车 没有找到相关路径, origin:{0},destination:{1},原因：{2}").format(
origin, destination, jo))
return (None, None)
distance = unicode("{0}公里").format(
round(float(paths[0]['distance']) / 1000, 1))
minutes = int(float(paths[0]['duration']) / 60)
hour = int(minutes / 60)
minute = int(minutes % 60)
time = unicode("{0}分").format(minute) if hour <= 0 else unicode(
"{0}小时{1}分").format(hour, minute)
return (distance, time)
def getStockInfo(code):
bit = 1 if code.startswith("6") else 2
url = 'http://nuff.eastmoney.com/EM_Finance2015TradeInterface/JS.ashx?id=' + code + str(
bit) + '&_=149941' + str(random.randint(1000000, 9999999))
res = httpGet(url)
res = res[9:-1]
writeLog(unicode("getStockInfo, url:{0}, resule:{1} ").format(url, res))
jo = json.loads(res)
data = jo['Value']
result = {}
result['limitUp'] = data[23]
result['limitDown'] = data[24]
result['avgPrice'] = data[26]
result['volume'] = data[31]
result['amount'] = data[35]
result['highPrice'] = data[30]
result['lowPrice'] = data[32]
result['openPrice'] = data[28]
result['closePrice'] = data[25]
result['changePercent'] = data[29]
result['changeAmount'] = data[27]
result['turnOverRatio'] = data[37]
result['QRR'] = data[36]
result['totalValue'] = data[46]
result['circulatedValue'] = data[45]
result['PE'] = 0 if data[38] == '-' else data[38]
result['PTB'] = 0 if data[43] == '-' else data[43]
result['internalPan'] = data[40]
result['externalPan'] = data[39]
result['code'] = code
return None if float(result['closePrice']) == 0 else result
def getShAvgPe():
url = "http://www.sse.com.cn/"
res = httpGet(url)
# print res
pattern = re.compile(r'RATIO_OF_PE.*')
match = pattern.search(res)
matchData = match.group()
pattern = re.compile(r'\d+\.\d+')
pe = pattern.search(matchData).group()
return round(float(pe), 2)
def getListData(code, page):
url = "http://nufm.dfcfw.com/EM_Finance2014NumericApplication/JS.aspx?type=CT&cmd=" + code + "&sty=FCOIATA&sortType=I&sortRule=1&page=" + str(
page
) + "&pageSize=20&js=var%20quote_123%3d{rank:[(x)],pages:(pc)}&token=7bc05d0d4c3c22ef9fca8c2a912d779c&jsName=quote_123&_g=0.148125620" + str(
random.randint(1000000, 9999999))
res = httpGet(url).decode("utf-8")
# print res
index = res.find("=")
if (index < 0):
return
res = res[14:].replace("rank", "\"rank\"").replace("pages", "\"pages\"")
# print res
jo = json.loads(res)
return jo
def getSzAvgPe():
# sys.setdefaultencoding('gb18030')
url = "http://www.szse.cn/"
res = httpGet(url)
pattern = re.compile(r'<table.*?id=\"REPORTID_tab1\".*?>(.*?)</table>')
tables = pattern.findall(res)
PEs = [0, 0, 0] # [主板，中小板，创业板]
for i in range(1, len(tables)):
if tables[i] is not None:
pattern = re.compile(r'<td.*?>(.*?)</td>')
tdDatas = pattern.findall(tables[i])
PEs[i - 1] = round(float(tdDatas[7]), 2)
return PEs
def getPEGByWC(code):
url = "http://www.iwencai.com/stockpick/search?ts=1&f=1&qs=stockhome_topbar_click&w=" + code + "%20peg"
res = httpGet(url)
res = res.decode(getEncoding(res))
pattern = re.compile(r'<table class=\"upright_table\">([\s\S]*)</table>')
tableData = pattern.search(res)
pattern = re.compile(
r'<div class=\"em alignRight alignRight\">([\s\S]*?)</div>')
divData = pattern.findall(tableData.group())
pattern = re.compile(r'<a[^>]*?>([\s\S]*?)</a>')
pegData = 0 if '--' in divData[0] else pattern.findall(divData[0])[0]
return (pegData, divData[1])
def getPE(code):
bit = 1 if code.startswith("6") else 2
url = "http://nuff.eastmoney.com/EM_Finance2015TradeInterface/JS.ashx?id=" + code + str(
bit)
res = httpGet(url).decode("utf-8")
res = res[9:-1]
jo = json.loads(res)
if jo is None or jo["Value"] is None:
return
info = jo["Value"]
name = info[2]
pe = info[38]
pe = 0 if '-' in pe else pe
# print name, pe
return (name, pe)
def getHouseListByPage(page):
url = "https://tj.lianjia.com/ershoufang/pg" + str(page) + "co32sf1ba45ea10000ep131"
res = httpGet(url, {'Host': 'tj.lianjia.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
'Cookie': 'lianjia_uuid=dfcb3cfc-1367-44d0-ab71-a4371c024f14; _jzqy=1.1497172963.1497172963.1.jzqsr=baidu|jzqct=%E9%93%BE%E5%AE%B6.-; UM_distinctid=15c96766dee1d-02c0d24031f09b-57e1b3c-100200-15c96766def2d0; lianjia_token=2.001caa2ee5666b6ddd0d0707d40582481c; Hm_lvt_efa595b768cc9dc7d7f9823368e795f1=1497173127; select_city=120000; all-lj=6341ae6e32895385b04aae0cf3d794b0; _jzqx=1.1501484606.1501816686.2.jzqsr=tj%2Elianjia%2Ecom|jzqct=/ershoufang/co32sf1ep131/.jzqsr=captcha%2Elianjia%2Ecom|jzqct=/; _jzqckmp=1; Hm_lvt_9152f8221cb6243a53c83b956842be8a=1501566186,1501632151,1501727320,1501816685; Hm_lpvt_9152f8221cb6243a53c83b956842be8a=1501817428; _smt_uid=593d0be2.3137f8c0; CNZZDATA1253477585=1433138464-1497169384-null%7C1501812237; CNZZDATA1254525948=1005085447-1497168099-null%7C1501812362; CNZZDATA1255633284=2082143268-1497171373-null%7C1501817197; CNZZDATA1255604082=911884105-1497168620-null%7C1501813499; _qzja=1.1430239548.1497172962788.1501727321514.1501816685601.1501817373141.1501817428734.0.0.0.86.20; _qzjb=1.1501816685601.5.0.0.0; _qzjc=1; _qzjto=5.1.0; _jzqa=1.3807096351994737700.1497172963.1501727322.1501816686.20; _jzqc=1; _jzqb=1.5.10.1501816686.1; _ga=GA1.2.457334799.1497172965; _gid=GA1.2.1962824039.1501816690; lianjia_ssid=11e953d7-b086-4fcf-a424-b43314c76cca'})
pattern = re.compile(r'<ul class=\"sellListContent\".*?>(.*?)</ul>')
contentUl = pattern.search(res)
pattern = re.compile(r'<li[^>]*?>([\s\S]*?)</li>')
houseInfoList = pattern.findall(contentUl.group())
pattern = re.compile(r'\"totalPage\":(.*?),')
totalPages = pattern.findall(res)
totalPages = 0 if len(totalPages) <= 0 else totalPages[0]
return (totalPages, houseInfoList)
def getGeoCodes(address):
url = unicode(
"http://restapi.amap.com/v3/geocode/geo?key={0}&address={1}&batch=true"
).format(getKey(), address)
res = httpGet(url)
jo = json.loads(res)
if (int(jo['status']) == 0):
writeWarningLog(
unicode("【高德】解析地址失败, address:{0}, 原因：{1}").format(address, jo))
return (None, None)
result = []
for i in range(0, len(jo['geocodes'])):
geoCodes = jo['geocodes'][i]
result.append(geoCodes['location'])
return result
def getTechParamter(code):
sys.setdefaultencoding('gbk')
url = 'http://stock.quote.stockstar.com/tech_' + code + '.shtml'
res = httpGet(url)
pattern = re.compile(r'<div class=\"listInfo\">([\s\S]*)</table>')
tableData = pattern.search(res)
pattern = re.compile(r'<td.*?>(.*?)</td>')
tdData = pattern.findall(tableData.group())
dictData = {}
dictStatus = {}
writeLog(unicode("getTech: code: {0}, url:{1}").format(code, url))
for i in range(0, len(tdData) - 2):
key = tdData[i].strip()
data = tdData[i + 1]
dictData[key] = 0 if '--' in data else data
dictStatus[key] = unicode(tdData[i + 2])
# print code, dictData
stockTechInfo = StockTechInfo(code, dictData)
pattern = re.compile(r'<p class=\"lf\">(.*?)</p>')
techStatus = pattern.search(res)
bulls = 0
bears = 0
notsure = 0
if techStatus is not None:
pattern = re.compile(r'\d+')
numbers = pattern.findall(techStatus.group())
if numbers is not None:
bulls = numbers[1]
bears = numbers[2]
notsure = numbers[3]
stockTechStatus = StockTechStatus(code, dictStatus, bulls, bears, notsure)
forecastInfo = getGainForecast(stockTechStatus)
return (stockTechInfo, stockTechStatus, forecastInfo)
def getRankPeg(code):
url = "http://www.iwencai.com/diag/block-detail?pid=1559&codes=" + code + "&codeType=stock&info=%7B%22view%22%3A%7B%22nolazy%22%3A1%2C%22parseArr%22%3A%7B%22_v%22%3A%22new%22%2C%22dateRange%22%3A%5B%2220170728%22%2C%2220170728%22%5D%2C%22staying%22%3A%5B%5D%2C%22queryCompare%22%3A%5B%5D%2C%22comparesOfIndex%22%3A%5B%5D%7D%2C%22asyncParams%22%3A%7B%22tid%22%3A659%7D%7D%7D"
res = httpGet(url)
res = res.decode(getEncoding(res))
jo = json.loads(res)
if not bool(jo['success']):
return ['--', '--', '--']
data = jo["data"]["data"]["tableTempl"]
pattern = re.compile(r'<tr[^>]*?>([\s\S]*?)</tr>')
trData = pattern.findall(data)
columnNames = ['rankNo', 'code', 'name', 'peg']
result = []
for j in range(0, len(trData)):
tr = trData[j]
if (j > 3):
break
pattern = re.compile(r'<div.*?>(.*?)</div>')
divData = pattern.findall(tr)
if len(divData) <= 0:
continue
dict = {}
for i in range(0, len(divData) - 1):
if '<a' in divData[i]:
pattern = re.compile(r'<a.*?>(.*?)</a>')
aData = pattern.findall(divData[i])
dict[columnNames[i]] = aData[0]
else:
dict[columnNames[i]] = divData[i]
result.append(
unicode("{0}:{1}:{2}").format(dict.get('code'), dict.get('name'),
dict.get('peg')))
for i in range(0, 3 - len(result)):
result.append('--')
return result
def getStockInfos(code, year):
try:
url = "http://d.10jqka.com.cn/v2/line/hs_{0}/01/{1}.js".format(
code, year)
res = httpGet(url).decode("utf-8")
index = res.find("(")
if (index < 0):
writeErrorLog(
unicode("解析行情失败: code:{0}, year:{1}, res:{2}").format(
code, year, res))
return []
res = res[index + 1:-1]
writeLog(unicode("获取股票历史行情: code: {0}, year:{1}").format(code, year))
jo = json.loads(res)
dataInfo = jo['data'].split(';')
result = {}
for item in dataInfo:
infos = item.split(',')
dic = {}
dic['open'] = infos[1]
dic['high'] = infos[2]
dic['low'] = infos[3]
dic['close'] = infos[4]
dic['volume'] = infos[5]
dic['amount'] = "{0}亿".format(round(
float(infos[6]) / 100000000, 1))
result[datetime.strptime(infos[0],
'%Y%m%d').strftime('%Y-%m-%d')] = dic
return result
except Exception, e:
writeErrorLog(
unicode("解析行情失败: code:{0}, year:{1}, e:{2}").format(
code, year, str(e)))
if "404" in str(e):
return []
else:
return None
def getListData(type, page):
url = "http://q.10jqka.com.cn/index/index/board/" + type + "/field/syl/order/asc/page/" + str(
page) + "/ajax/1/"
res = httpGet(
url, {
"Accept-Encoding": "gzip, deflate, sdch",
"Accept-Language": "zh-CN,zh;q=0.8"
})
try:
res = res.decode(getEncoding(res))
columnNames = [
'number', 'code', 'name', 'price', 'changepercent', 'changeamount',
'changerate', 'turnoverratio', 'QRR', 'zf', 'amount', 'liutonggu',
'liutongshizhi', 'pe'
]
listData = []
pattern = re.compile(r'<tr[^>]*?>([\s\S]*?)</tr>')
trData = pattern.findall(res)
for tr in trData:
pattern = re.compile(r'<td.*?>(.*?)</td>')
tdData = pattern.findall(tr)
if len(tdData) <= 0:
continue
dict = {}
for i in range(1, len(tdData) - 1):
if i <= 2:
pattern = re.compile(r'<a.*?>(.*?)</a>')
aData = pattern.findall(tdData[i])
dict[columnNames[i]] = aData[0]
else:
dict[columnNames[i]] = tdData[i]
listData.append(dict)
return listData
except Exception, e:
print e, res
def getPEG(code):
market = "sh" if code.startswith("6") else "sz"
url = "http://emweb.securities.eastmoney.com/PC_HSF10/IndustryAnalysis/IndustryAnalysisAjax?code=" + market + code + "&icode=" + str(
random.randint(100, 999))
res = httpGet(url).decode("utf-8")
jo = json.loads(res)
print jo
rate = 0
PEG = 0
if (jo is not None and jo["Result"]["gzbj"] is not None
and jo["Result"]["gzbj"]["data"] is not None):
if (jo["Result"]["gzbj"]["data"][0]["dm"] != code):
writeWarningLog("估值比较的股票代码没找到,实际代码：" + code + ",当前代码：" +
jo["Result"]["gzbj"]["data"][0]["dm"])
else:
rate = jo["Result"]["gzbj"]["data"][0]["pm"]
PEG = jo["Result"]["gzbj"]["data"][0]["peg"]
PEG = 0 if '--' in PEG else PEG
if (jo is None or jo["Result"]["czxbj"] is None
or jo["Result"]["czxbj"]["data"] is None
or len(jo["Result"]["czxbj"]["data"]) <= 0):
return (rate, PEG, 0, 0, 0, 0)
e2017 = 0
e2018 = 0
e2019 = 0
mixThree = 0
if (jo["Result"]["czxbj"]["data"][0]["dm"] != code):
writeWarningLog("成长性比较的股票代码没找到,实际代码：" + code + ",当前代码：" +
jo["Result"]["czxbj"]["data"][0]["dm"])
else:
mixThree = jo["Result"]["czxbj"]["data"][0]["jbmgsyzzlfh"]
e2017 = jo["Result"]["czxbj"]["data"][0]["jbmgsyzzl1"]
e2018 = jo["Result"]["czxbj"]["data"][0]["jbmgsyzzl2"]
e2019 = jo["Result"]["czxbj"]["data"][0]["jbmgsyzzl3"]
return (rate, PEG, mixThree, e2017, e2018, e2019)
def getDirectionByLngLat(origin, destination):
url = unicode(
'http://restapi.amap.com/v3/direction/transit/integrated?key={0}&origin={1}&destination={2}&strategy=0&city=天津市'
).format(getKey(), origin, destination)
res = httpGet(url)
try:
jo = json.loads(res)
if (int(jo['status']) == 0):
writeWarningLog(
unicode(
"【高德】公交 路径规划失败, origin:{0},destination:{1},原因：{2}").format(
origin, destination, jo))
return None
transits = jo['route']['transits']
if (len(transits) <= 0):
writeWarningLog(
unicode("【高德】公交规划 没有找到相关路径, origin:{0},destination:{1},原因：{2}"
).format(origin, destination, jo))
return None
transit = transits[0] # 找第一条规划路线
segments = transit['segments'] # 路径信息
if (len(segments) <= 0):
writeWarningLog(
unicode("【高德】公交规划 没有找到路径信息, origin:{0},destination:{1},原因：{2}"
).format(origin, destination, jo))
return None
result = []
for i in range(0, len(segments)):
segment = segments[i]
if i == 0:
walkingDistance = round(
float(segment['walking']['distance']) / 1000, 1)
walkingTime = int(float(segment['walking']['duration']) / 60)
result.append(
unicode("步行{0}公里：约{1}分钟").format(walkingDistance,
walkingTime))
busName = segment['bus']['buslines'][0]['name']
busDepartureStop = segment['bus']['buslines'][0][
'departure_stop']['name']
busArrivalStop = segment['bus']['buslines'][0]['arrival_stop'][
'name']
totalStops = len(
segment['bus']['buslines'][0]['via_stops']) + 1
result.append(
unicode("（{0}） {1} => {2} 共{3}站").format(
busName, busDepartureStop, busArrivalStop, totalStops))
elif i == len(segments) - 1:
if segment['walking'] is not None:
if len(segment['walking']) <= 0:
continue
walkingDistance = round(
float(segment['walking']['distance']) / 1000, 1)
walkingTime = int(
float(segment['walking']['duration']) / 60)
result.append(
unicode("步行{0}公里：约{1}分钟").format(
walkingDistance, walkingTime))
else:
busName = segment['bus']['buslines'][0]['name']
busDepartureStop = segment['bus']['buslines'][0][
'departure_stop']['name']
busArrivalStop = segment['bus']['buslines'][0]['arrival_stop'][
'name']
totalStops = len(
segment['bus']['buslines'][0]['via_stops']) + 1
result.append(
unicode("（{0}） {1} => {2} 共{3}站").format(
busName, busDepartureStop, busArrivalStop, totalStops))
return result
except Exception, e:
traceback.print_exc()
print url
print res
return None
def handleHouseList(houseInfoList, geoCodeHome, geoCodeHerOffice, geoCodeMyOffice, result, i):
for houseInfo in houseInfoList:
print houseInfo
print i
i = i + 1
try:
pattern = re.compile(r'<div class=\"houseInfo\">([\s\S]*?)</div>')
houseInfoDiv = pattern.findall(houseInfo)[0]
pattern = re.compile(r'<a[^>]*?>([\s\S]*?)</a>')
village = pattern.findall(houseInfoDiv)[0].strip() # 小区名称
other = re.subn(r'<[span|a][^>]*?>([\s\S]*?)</[span|a]>', '', houseInfoDiv)[0]
pattern = re.compile(r'<div class=\"positionInfo\">([\s\S]*?)</div>')
positionInfoDiv = pattern.findall(houseInfo)[0]
pattern = re.compile(r'<a[^>]*?>([\s\S]*?)</a>')
street = pattern.findall(positionInfoDiv)[0].strip() # 街道名称
pattern = re.compile(r'<span class=\"subway\">([\s\S]*?)</span>')
subwayInfo = pattern.findall(houseInfo)
subwayInfo = '' if len(subwayInfo) <= 0 else subwayInfo[0].strip() # 地铁信息
lineIndex = subwayInfo.find('线')
stationIndex = subwayInfo.find('站')
subway = ''
if (lineIndex >= 0 and stationIndex >= 0):
subway = subwayInfo[lineIndex + 3:stationIndex]
pattern = re.compile(r'<div class=\"totalPrice\"><span>([\s\S]*?)</span>')
totalPrice = pattern.findall(houseInfo)[0] # 总价
pattern = re.compile(r'<div class=\"unitPrice\".*?><span>([\s\S]*?)</span>')
unitPrice = pattern.findall(houseInfo)[0][6:-10] # 单价
pattern = re.compile(r'<div class=\"followInfo\"><span.*?></span>([\s\S]*?)</div>')
dateInfo = pattern.findall(houseInfo) # 发布时间
dateInfo = dateInfo[0].split('/')[2]
pattern = re.compile(r'<a class=\"img \" href=\"(.*?)\"')
linkUrl = pattern.findall(houseInfo)[0]
linkRes = httpGet(linkUrl, {
'Cookie': 'lianjia_uuid=dfcb3cfc-1367-44d0-ab71-a4371c024f14; _jzqy=1.1497172963.1497172963.1.jzqsr=baidu|jzqct=%E9%93%BE%E5%AE%B6.-; UM_distinctid=15c96766dee1d-02c0d24031f09b-57e1b3c-100200-15c96766def2d0; lianjia_token=2.001caa2ee5666b6ddd0d0707d40582481c; Hm_lvt_efa595b768cc9dc7d7f9823368e795f1=1497173127; select_city=120000; all-lj=6341ae6e32895385b04aae0cf3d794b0; _jzqx=1.1501484606.1501816686.2.jzqsr=tj%2Elianjia%2Ecom|jzqct=/ershoufang/co32sf1ep131/.jzqsr=captcha%2Elianjia%2Ecom|jzqct=/; _jzqckmp=1; Hm_lvt_9152f8221cb6243a53c83b956842be8a=1501566186,1501632151,1501727320,1501816685; Hm_lpvt_9152f8221cb6243a53c83b956842be8a=1501817441; _smt_uid=593d0be2.3137f8c0; CNZZDATA1253477585=1433138464-1497169384-null%7C1501812237; CNZZDATA1254525948=1005085447-1497168099-null%7C1501812362; CNZZDATA1255633284=2082143268-1497171373-null%7C1501817197; CNZZDATA1255604082=911884105-1497168620-null%7C1501813499; _qzja=1.1430239548.1497172962788.1501727321514.1501816685601.1501817428734.1501817441713.0.0.0.87.20; _qzjb=1.1501816685601.6.0.0.0; _qzjc=1; _qzjto=6.1.0; _jzqa=1.3807096351994737700.1497172963.1501727322.1501816686.20; _jzqc=1; _jzqb=1.6.10.1501816686.1; _ga=GA1.2.457334799.1497172965; _gid=GA1.2.1962824039.1501816690; lianjia_ssid=11e953d7-b086-4fcf-a424-b43314c76cca',
'Host': 'tj.lianjia.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'})
pattern = re.compile(r'<div class="areaName">.*?</div>')
areaDiv = pattern.search(linkRes)
pattern = re.compile(r'<a.*?>(.*?)</a>')
aData = pattern.findall(areaDiv.group())
areaData = '' if aData is None or len(aData) <= 0 else aData[0]
geoCodeVillage = getGeoCodes(u'天津市{0}'.format(village))[0] # 小区坐标
distanceAndTime = getDistanceAndTimeByLngLat(geoCodeHome, geoCodeVillage) # 路径规划信息，获取距离和时间（自驾）
babyDirection = getDirectionByLngLat(geoCodeHerOffice, geoCodeVillage)
babyDirectionStr = '\"'
for item in babyDirection:
babyDirectionStr = babyDirectionStr + unicode('{0}\n').format(item)
babyDirectionStr = babyDirectionStr + '\"'
meDirection = getDirectionByLngLat(geoCodeMyOffice, geoCodeVillage)
meDirectionStr = '\"'
for item in meDirection:
meDirectionStr = meDirectionStr + unicode('{0}\n').format(item)
meDirectionStr = meDirectionStr + '\"'
result.append(
unicode("{0},{1},{10},{2},{3},{9},{4},{11},{5},{6},{7},{8}\n").format(village, street, totalPrice,
unitPrice, distanceAndTime[0],
other, subway,
babyDirectionStr,
meDirectionStr, dateInfo,
areaData,
distanceAndTime[1]).encode(
'gbk'))
saveFile("houselist1.csv",
unicode("{0},{1},{10},{2},{3},{9},{4},{11},{5},{6},{7},{8}\n").format(village, street, totalPrice,
unitPrice,
distanceAndTime[0], other,
subway,
babyDirectionStr,
meDirectionStr, dateInfo,
areaData,
distanceAndTime[1]).encode(
'gbk'), 'a')
except Exception, e:
traceback.print_exc()
time.sleep(random.randint(2, 5))
