def start_requests(self):
permins = 0
print(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, 60)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.carrier, 1)
if not result:
time.sleep(3)
continue
for data in result:
(dt_st, dep, arr, days) = vyUtil.analysisData(data)
for i in range(int(days)):
dt = vyUtil.get_real_date(dt_st, i)
data = dict(beginCity=dep, endCity=arr, beginDate=dt)
data.update(self.custom_settings.get('DEFAULT_DATA'))
yield scrapy.Request(
url=self.start_urls,
method="POST",
body=json.dumps(data),
meta=dict(data=data),
dont_filter=True,
callback=self.parse,
errback=self.errback,
)
def start_requests(self):
permins = 0
logging.info(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=1)
result = next(result_iter)
else:
result = pubUtil.getUrl('aq', 1)
if not result:
logging.info('get task error')
time.sleep(20)
continue
for data in result:
# logging.info("###input data: " + data)
(dt, dep, to) = pubUtil.analysisData(data)
# dt,dep,to='2019-03-28','PVG','TPE'
# ua = UserAgent()
# self.headers['user-agent'] = ua.random
post_data = 'B_LOCATION_1=' + dep + '&E_LOCATION_1=' + to + '&B_DATE_1=' + dt.replace(
'-', ''
) + '0000&B_ANY_TIME_1=True&EMBEDDED_TRANSACTION=FlexPricerAvailability&ARRANGE_BY=D&DISPLAY_TYPE=2&PRICING_TYPE=O&SO_SITE_MATRIX_CALENDAR=FALSE&SO_SITE_RUI_CAL_AVAI_NO_RECO=TRUE&SO_SITE_RUI_FP_AVAI_PRESEL=FALSE&COMMERCIAL_FARE_FAMILY_1=NEWECOOW&COMMERCIAL_FARE_FAMILY_2=NEWDELOW&COMMERCIAL_FARE_FAMILY_3=NEWBIZOW&SO_SITE_RUI_AX_CAL_ENABLED=TRUE&SO_SITE_CAL_CHANGE_WEEK=TRUE&SO_SITE_RUI_HIDE_MDF_SRC=FALSE&EXTERNAL_ID%236=OW&TRAVELLER_TYPE_1=ADT&TRIP_TYPE=O&TRIP_FLOW=YES&SO_SITE_EXPORT_CONFIRM=TRUE&SO_SITE_EXPORT_CONF_URL=https%3A%2F%2Fbooking.evaair.com%2Fexporttripplan%2Fwebservice.aspx&SO_SITE_THREEDS_USE=N&SO_SITE_BILLING_NOT_REQUIRED=Y&SO_SITE_BILL_ADD_OPTIONS=BILL_ADD_HIDDEN&SO_SITE_PREBOOK_CANCELLATION=TRUE&SO_GL=%3C%3Fxml+version%3D%221.0%22+encoding%3D%22iso-8859-1%22%3F%3E%0D%0A%3CSO_GL%3E%0D%0A%3CGLOBAL_LIST+mode%3D%22partial%22%3E%0D%0A%3CNAME%3ESL_AIR_MOP%3C%2FNAME%3E%0D%0A%3CLIST_ELEMENT%3E%0D%0A%3CCODE%3ECC%3C%2FCODE%3E%0D%0A%3CLIST_VALUE%3ECredit+Card%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EY%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3ECC%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3ECryptic%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3ECC%25T%25I%2F%25E%2F%25C%25F%2FN%25A%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%2F%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3ECC%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3CLIST_VALUE%3EN%3C%2FLIST_VALUE%3E%0D%0A%3C%2FLIST_ELEMENT%3E%0D%0A%3C%2FGLOBAL_LIST%3E%0D%0A%3C%2FSO_GL%3E&SO_SITE_FD_DISPLAY_MODE=1&SO_SITE_CURRENCY_FORMAT_JAVA=0&SO_SITE_ENABLE_SRV_POLICY=BAG%2CCOA&SO_SITE_ALLOW_SPEC_REQ_SERV=FALSE&SO_SITE_SD_TRUE_OP_CARRIER=TRUE&SO_SITE_BARCODE_ENABLE=TRUE&SO_SITE_ALLOW_CS_CODE_SHARE=FALSE&SO_SITE_USE_PAYMENT_ACTION=TRUE&EXTERNAL_ID=AIBS&EXTERNAL_ID%232=&EXTERNAL_ID%233=&EXTERNAL_ID%234=NEWECOOW&EXTERNAL_ID%235=&EXTERNAL_ID%2314=N&EXTERNAL_ID%2312=&EXTERNAL_ID%2313=zh_CN&EXTERNAL_ID%2399=C5WBKT102%23%23flyeva&DIRECT_LOGIN=NO&SO_SITE_RUI_MULTIDEV_ENABLED=TRUE&SO_SITE_RUI_TABLET_PG_LIST=ALL&SO_SITE_RUI_MOBILE_PG_LIST=ALL&SO_SITE_RUI_DISP_FF_TABLE=TRUE&SO_SITE_RUI_UPSLL_T_MDL=TRUE&SO_SITE_RUI_UPSLL_T_MDL_ATC=TRUE&SO_SITE_RUI_DPICKER_NATIVE=TABLET%2CMOBILE&MC_FORCE_DEVICE_TYPE=MOBILE&SO_SITE_RUI_MOBILE_FLOW=ALL&SO_SITE_RUI_TABLET_FLOW=ALL&SO_SITE_RUI_COLLAPSE_BOUND_T=TWO_STEPS&SO_SITE_RUI_UPSLL_HIDE_BTNS=FALSE&SO_SITE_OFFICE_ID=SHABR08AA&LANGUAGE=CN&SITE=CAWXCNEW'
url_data = {
"ENCT": "1",
"ENC":
"990572D723A7BC83F77B4C6C03C696340674137066140FF11D721B8765E55FF8DC0562E080CE4BD1CD01272028CBBA89",
# 传入当前查询时间
"ENC_TIME": time.strftime("%Y%m%d%H%M%S", time.localtime())
}
# 设置无效
invalid = {
'date': dt.replace('-', ''),
'depAirport': dep,
'arrAirport': to,
'mins': self.custom_settings.get('INVALID_TIME')
}
url_data = urllib.urlencode(url_data)
self.url = self.start_urls[0] + '?' + url_data
# print '# url: ', url
# print '# url_data: ', url_data
# ip = '127.0.0.1:8888'
# ip = '127.0.0.1:1080'
yield scrapy.Request(
self.url,
headers=self.headers,
body=post_data,
callback=self.parse,
dont_filter=True,
# meta={'invalid': invalid, 'proxy': ip},
meta={'invalid': invalid},
method='POST',
errback=self.errback)
def start_requests(self):
permins = 0
print(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.carrier, 1)
if not result:
time.sleep(6)
continue
for data in result:
(_dt, dep, to, days) = vyUtil.analysisData(data)
for i in range(int(days)):
dt = (datetime.strptime(_dt, '%Y%m%d') +
timedelta(days=i)).strftime('%Y-%m-%d')
# dt, dep, to = '2019-02-28', 'BLR', 'BKK'
post_data = self.custom_settings.get(
'POST_DATA_FORMAT').copy()
post_data['query'] = post_data.get('query') % (self.seats,
to, dep, dt)
yield scrapy.Request(
url=self.start_urls,
method="POST",
body=json.dumps(post_data),
meta={'post_data': post_data},
dont_filter=True,
)
def heart_task(self):
result_iter = None
# 需要加查询判断
while True:
try:
if self.local:
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=10)
result = next(result_iter)
else:
result = json.loads(
requests.get(settings.GET_TASK_URL + 'carrier=' +
self.name,
timeout=60).text).get('data')
except Exception as e:
logging.error(e)
result = None
if result is None:
logging.info('Date is None!')
logging.info('Waiting...')
time.sleep(16)
continue
for data in result:
# 开始请求
self.start_requests(data)
def start_requests(self):
permins = 0
print(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.carrier, 1)
if not result:
time.sleep(3)
continue
for data in result:
(dt_st, dep, arr, days) = vyUtil.analysisData(data)
for i in range(int(days)):
dt = vyUtil.get_real_date(dt_st, i)
pay_load = dict(
depCity1=dep,
arrCity1=arr,
depDate1=dt,
)
pay_load.update(self.custom_settings.get('PAY_LOAD'))
yield scrapy.FormRequest(
self.start_url,
formdata=pay_load,
meta={'payload': pay_load},
callback=self.parse,
dont_filter=True,
errback=self.err_back,
)
def start_requests(self):
permins = 0
print(pubUtil.heartbeat(self.host_name, self.name, self.num, permins, self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.carrier, 1)
if not result:
time.sleep(3)
continue
for data in result:
(dt_st, dep, arr, days) = vyUtil.analysisData(data)
for i in range(int(days)):
dt = vyUtil.get_real_date(dt_st, i)
params = {
'origination-airport': dep,
'destination-airport': arr,
'departure-date': dt,
'number-adult-passengers': self.custom_settings.get('SEAT_SEARCH'),
'number-senior-passengers': 0,
'currency': 'USD',
}
total_url = self.start_urls + parse.urlencode(params)
yield scrapy.Request(
url=total_url,
method="GET",
dont_filter=True,
callback=self.parse,
errback=self.errback,
)
def start_requests(self):
permins = 0
print(
LamudatechDevPipeline.heartbeat(self.host_name, self.spider_name,
self.num, permins, self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, step=7, st=2)
result = next(result_iter)
else:
try:
data_api = settings.GET_TASK_URL + 'carrier=VJ'
result = json.loads(
requests.get(data_api, timeout=180).text).get('data')
except Exception as e:
self.log(e)
result = None
if not result:
logging.info('Date is None!')
logging.info('Waiting...')
continue
airports, _day, _num = result[0].split(':')
FROM, TO = airports.split('-')
_day = re.sub(r'(\d{4})(\d{2})(\d{2})', r'\1-\2-\3', _day)
# for airports in get_airports(u'越捷航空.csv'):
# FROM = airports.get('DepartureAirportCode')
# TO = airports.get('ArrivalAirportCode')
#
# _day = "{:%Y-%m-%d}".format(datetime.today())
for _day in self._get_dates(_day, int(_num)):
data = {
'OutboundDate': _day,
'DaysBefore': '0',
'DaysAfter': '0',
'AdultCount': '1',
'ChildCount': '0',
'InfantCount': '0',
'DepartureAirportCode': FROM,
'ArrivalAirportCode': TO,
'CurrencyCode': 'VND',
'PromoCode': ''
}
yield scrapy.FormRequest(
self.start_urls,
formdata=data,
meta={
'FROM': FROM,
'TO': TO
},
callback=self.parse,
dont_filter=True,
# errback=lambda x: self.download_errback(x, FROM, TO)
errback=self.errback,
)
def start_requests(self):
permins = 0
print(LamudatechDevPipeline.heartbeat(self.host_name, self.spider_name, self.num, permins, self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, step=1)
result = next(result_iter)
else:
try:
data_api = settings.GET_TASK_URL + 'carrier=DY'
result = json.loads(requests.get(data_api, timeout=180).text).get('data')
except Exception as e:
self.log(e)
result = None
if not result:
self.log('Date is None!', 40)
self.log('Waiting...', 40)
time.sleep(16)
continue
airports, _day, _num = result[0].split(':')
FROM, TO = airports.split('-')
currency_market = self.currency_info.get(FROM)
if currency_market:
currencyCode = currency_market.get('currency')
marketCode = currency_market.get('marketCode')
else:
currencyCode = 'EUR'
marketCode = 'en'
for _day in self._get_dates(_day, int(_num)):
params = parse.urlencode(dict(
adultCount=3,
childCount=0,
infantCount=0,
# culture='en-GB',
currencyCode=currencyCode,
marketCode=marketCode,
origin=FROM,
destination=TO,
inboundDate=_day,
outboundDate=_day,
includeTransit='true',
isRoundTrip='false',
isSsrNeeded='false',
))
total_url = self.start_urls + params
yield scrapy.Request(total_url,
meta={'FROM': FROM, 'TO': TO, '_day': _day},
callback=self.parse,
errback=None,
dont_filter=True)
def start_requests(self):
permins = 0
print(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=30)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name)
if not result:
time.sleep(6)
continue
for data in result:
# 处理任务 [u'TLN-CFE:20181110:1']
task_data_list = data.split(':')
count = int(task_data_list[2])
(dt, dep, arr) = pubUtil.analysisData(task_data_list[0] + ':' +
task_data_list[1])
_date = datetime.strptime(dt, '%Y-%m-%d')
for i in range(count):
date = _date + timedelta(days=i)
date = date.strftime('%Y%m%d0000')
dep = self.port_city.get(dep, dep)
arr = self.port_city.get(arr, arr)
# logging.info('# input data: ' + dep + '' + arr + '' + date)
# 设置无效
invalid = {
'date': date.replace('-', ''),
'depAirport': dep,
'arrAirport': arr,
'mins': self.custom_settings.get('INVALID_TIME')
}
post_data = urllib.urlencode(
ly_post_data.second_post_data(dep, arr, date,
self.ADT))
yield scrapy.Request(self.start_urls[0],
body=post_data,
callback=self.parse,
dont_filter=True,
meta={'invalid': invalid},
errback=self.errback,
method='POST')
def start_requests(self):
permins = 0
print(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.carrier, 1)
if not result:
time.sleep(6)
continue
hour = datetime.now().hour + 2
self.cookie = self.cookies[hour % len(self.cookies)]
installid = self.InstallationID[hour % len(self.InstallationID)]
for data in result:
(dt_st, dep, to,
days) = vyUtil.analysisData(data) # 把获取到的data格式化
# dep, to = 'CDG', 'VIE'
for i in range(int(days)):
dt = vyUtil.get_real_date(dt_st, i)
# dt = '2018-11-01'
self.task.append({
'date': dt.replace('-', ''),
'depAirport': dep,
'arrAirport': to,
'mins': settings.INVALID_TIME
})
dt = dt + 'T00:00:00'
data_list = {
'InstallationID':
installid,
'AirportDateTimeList': [{
'MarketDateDeparture': dt,
'DepartureStation': dep,
'ArrivalStation': to,
}]
}
data_list.update(self.custom_settings.get('DEFAULT_DATA'))
yield scrapy.Request(
method='POST',
url=self.start_url,
headers={'Cookie': self.cookie},
body=json.dumps(data_list),
meta={'data_list': data_list},
callback=self.parse,
dont_filter=True,
errback=lambda x: self.download_errback(x, data_list))
def start_requests(self):
permins = 0
logging.info(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=30)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name, 1)
if not result:
logging.info('get task error')
time.sleep(20)
continue
for data in result:
(dt, dep, to) = pubUtil.analysisData(data)
# dep, to, dt = 'FUK', 'YNT', '2019-03-27'
post_data = {
"tripType": "OW",
"orgCode": dep,
"dstCode": to,
"takeoffdate1": dt,
}
# 随机UA
ua = UserAgent()
self.headers['User-Agent'] = ua.random
# post_data = urllib.urlencode(post_data)
# logging.info("###input data: " + dep + to + dt)
# 设置无效
invalid = {
'date': dt.replace('-', ''),
'depAirport': dep,
'arrAirport': to,
'mins': self.custom_settings.get('INVALID_TIME')
}
yield scrapy.Request(
self.start_urls[0],
headers=self.headers,
body=json.dumps(post_data),
# body=post_data,
callback=self.parse,
dont_filter=True,
# meta={'invalid': invalid, 'proxy': 'http://127.0.0.1:8888'},
meta={'invalid': invalid},
method='POST',
errback=self.errback)
def start_requests(self):
permins = 0
logging.info(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, step=7)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name, 1)
if not result:
logging.info('get task error')
time.sleep(10)
continue
# 循环多个任务，现在默认一个
for data in result:
# 处理任务 BVE-LYS-201812030000-15
count = int(data.split(':')[-1])
(date, dep, arr) = pubUtil.analysisData(data[:-2])
date = date.replace('-', '') + '0000'
# logging.info('# input data: ' + dep + '-' + arr + '-' + date + '-' + str(count))
task_data = {
'dep': dep,
'arr': arr,
'date': date,
'count': count
}
post_data = urllib.urlencode(
a5_post_data.first_post_data(dep, arr, date, self.ADT))
# 获取session
yield scrapy.Request(
self.get_session_url[0],
body=post_data,
callback=self.get_session,
dont_filter=True,
meta={
'post_data': post_data,
'task_data': task_data
},
method='POST',
errback=self.errback,
)
def start_requests(self):
permins = 0
logging.info(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=30)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name, 1)
if not result:
logging.info('get task error')
time.sleep(20)
continue
self.session_data['tck'] = random.choice(self.id_pool)
for data in result:
# logging.info("###input data: " + data)
(dt, dep, to) = pubUtil.analysisData(data)
# dt,dep,to='2019-02-28','CAN','RGN'
post_data = {
'traveldate': dt,
'ori': dep,
'currency': 'CNY',
'dest': to
}
# 设置无效
invalid = {
'date': dt.replace('-', ''),
'depAirport': dep,
'arrAirport': to,
'mins': self.custom_settings.get('INVALID_TIME')
}
post_data = urllib.urlencode(post_data)
yield scrapy.Request(self.start_urls[0],
headers=self.headers,
body=post_data,
callback=self.parse,
dont_filter=True,
meta={'invalid': invalid},
method='POST',
errback=self.errback)
def start_requests(self):
permins = 0
self.proxy = True
print(
LamudatechDevPipeline.heartbeat(self.host_name, self.spider_name,
self.num, permins, self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, step=7)
result = next(result_iter)
else:
try:
data_api = settings.GET_TASK_URL + 'carrier=U2'
result = json.loads(
requests.get(data_api, timeout=180).text).get('data')
except Exception as e:
self.log(e)
result = None
if not result:
self.log('Date is None!', level=20)
self.log('Waiting...', level=20)
time.sleep(16)
continue
airports, _day, _num = result[0].split(':')
FROM, TO = airports.split('-')
# FROM, TO = 'TXL', 'ARN'
lowfares_url = 'https://www.easyjet.com/ejcms/cache15m/api/routedates/get/?'
lowfares_total_url = lowfares_url + parse.urlencode(
{
'originIata': FROM,
'destinationIata': TO
})
yield scrapy.Request(lowfares_total_url,
meta={
'FROM': FROM,
'TO': TO
},
callback=self.date_parse,
errback=self.errback,
dont_filter=True)
def start_requests(self):
permins = 0
print(pubUtil.heartbeat(self.host_name, self.name, self.num, permins, self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=30)
result = next(result_iter)
else:
result = pubUtil.getUrl('TW', 5)
if not result:
logging.info('get task error')
time.sleep(10)
continue
today = datetime.now().strftime('%Y%m%d')
for data in result:
(dt, dep, to) = pubUtil.analysisData(data) # 把获取到的data格式化
# dt, dep, to = '20180722', 'ICN', 'KIX' # 测试某条数据
params = urllib.urlencode(dict(
origin=dep,
destination=to,
onwardDateStr=dt.replace('-', ''),
# pointOfPurchase='KR',
paxTypeCountStr='3,0,0',
today=today,
travelType='OW',
searchType='byDate',
# domesticYn='Y',
bundleAmountOW=0,
bundleAmountRT=0,
routeCls='AS',
_=int(time.time() * 1000)
))
total_url = self.start_urls[0] + params
yield scrapy.Request(url=total_url,
callback=self.transit,
meta={'params': params, 'flag': 1},
dont_filter=True)
def start_requests(self):
permins = 0
print(
LamudatechDevPipeline.heartbeat(self.host_name, self.spider_name,
self.num, permins, self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter or not result:
result_iter = pubUtil.get_task(self.name)
result = next(result_iter)
else:
try:
data_api = settings.GET_TASK_URL + 'carrier=EW'
result = json.loads(
requests.get(data_api, timeout=180).text).get('data')
except Exception as e:
self.log(e)
result = None
if not result:
self.log('Date is None!', level=20)
self.log('Waiting...', level=20)
time.sleep(16)
continue
airports, _day, _num = result[0].split(':')
FROM, TO = airports.split('-')
# FROM, TO = 'HAM', 'CDG'
# 请求最低价获得有价格的日期
for record in self.get_data(FROM, TO):
# 日期排序
order_list = [
x.get('date')
for x in sorted(record, key=lambda x: x.get('date'))
]
# 筛选临近日期,减少爬取数量
lowfares = [
x for x in record
if x.get('date') in self.get_list(order_list)
]
for data in lowfares:
_from = data.get('origin')
_to = data.get('destination')
# currency = data.get('currency')
# currency = self.currency_cache.get(currency, currency)
_date = data.get('date')
# _date = '2018-11-06'
params = urllib.urlencode(
dict(
o=_from,
d=_to,
t='o',
od=_date,
adt='5',
lng='en-GB',
appvi='2D53F50C85034ECF-6000119C00002033',
adobe_mc=
'TS=%s|MCAID=2D791936852A6702-40000129C00FCFCA' %
int(time.time()),
screen='Search',
culture='en-GB',
))
total_url = self.start_urls + params
yield scrapy.Request(
total_url,
meta={
'FROM': _from,
'TO': _to,
'_day': _date,
# 'currency': currency
},
dont_filter=True,
callback=self.parse,
errback=self.download_errback)
def start_requests(self):
permins = 0
logging.info(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=30)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name, 1)
if not result:
logging.info('get task error')
time.sleep(5)
continue
for data in result:
# logging.info("## input data: " + data)
# 处理任务 [u'TLN-CFE:20181110:1']
count = int(data.split(':')[-1])
(date, dep, arr) = pubUtil.analysisData(data[:-2])
_date = datetime.strptime(date, '%Y-%m-%d')
for i in range(count):
_date = _date + timedelta(days=i)
date = _date.strftime('%Y%m%d')
# dep = 'KIX'
# arr = 'ICN'
# logging.info('# input data: ' + dep + '-' + arr + '-' + date)
city_code = self.city_dict.get(dep)
if city_code is None:
logging.info('# not found city: ' + dep)
body = json.dumps(
ze_post_data.get_data(dep, arr, date, self.ADT,
city_code))
# 设置无效
invalid = {
'date': date.replace('-', ''),
'depAirport': dep,
'arrAirport': arr,
'mins': self.custom_settings.get('INVALID_TIME')
}
task_data = {
'dep': dep,
'arr': arr,
'date': date,
'city_code': city_code,
'body': body
}
yield scrapy.Request(self.start_urls[0],
headers=self.headers,
body=body,
callback=self.parse,
dont_filter=True,
meta={
'invalid': invalid,
'task_data': task_data
},
errback=self.errback,
method='POST')
def start_request(self):
result_iter = None
# 需要加查询判断
while True:
# if not timeUtil.time_is_valid(self.st_time, self.en_time):
# logging.info('Waiting to 07:30:00.....')
# time.sleep(5 * 60)
# continue
# data_api = 'http://dx.redis.jiaoan100.com/buddha/gettask?carrier=JX'
data_api = 'http://task.jiaoan100.com/buddha/gettask?carrier=jx'
try:
if self.local:
if not result_iter:
result_iter = pubUtil.get_task('JQ', days=10)
result = next(result_iter)
else:
result = json.loads(
requests.get(data_api, timeout=60).text).get('data')
except Exception as e:
logging.error(e)
result = None
if result is None:
logging.info('Date is None!')
logging.info('Waiting...')
time.sleep(16)
continue
airports, _day, day_num = result[0].split(':')
# day_num='1'
# print('airports, _day, day_num',airports, _day, day_num)
FROM, TO = airports.split('-')
# FROM, TO = ('DAD', 'HKG')
_day = re.sub(r'(\d{4})(\d{2})(\d{2})', r'\1-\2-\3', _day)
days = self._get_dates(_day, day_num)
# print(days)
# days = ['2019-01-11', '2019-01-12', '2019-01-13']
for day in days:
# FROM, TO, day = 'RGN', 'SIN', '2019-01-17'
query = urlencode({
'origin1': FROM,
'destination1': TO,
# 'flight-type': '1',
'departuredate1': day,
'adults': str(settings.ADULT_NUM),
'children': '0',
'infants': '0',
})
print(query)
# set_invalid('JX', FROM, TO, day)
total_url = self.start_url + query
# 设置无效
invalid = {
'date': day.replace('-', ''),
'depAirport': FROM,
'arrAirport': TO,
'mins': settings.INVALID_TIME
}
# total_url = 'https://www.jetstar.com/au/en/home?origin=CBR&destination=HNL&flight-type=1&selected-departure-date=02-02-2019&adult=1&flexible=1¤cy=AUD'
# yield total_url,invalid
yield [total_url, invalid]
def start_requests(self):
permins = 0
logging.info(
pubUtil.heartbeat(self.host_name, self.name, self.num, permins,
self.version))
result_iter = None
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=30)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name, 1)
if not result:
logging.info('get task error')
time.sleep(5)
continue
for data in result:
# logging.info("## input data: " + data)
# 处理任务 [u'TLN-CFE:20181110:1']
count = int(data.split(':')[-1])
(date, dep, arr) = pubUtil.analysisData(data[:-2])
_date = datetime.strptime(date, '%Y-%m-%d')
for i in range(count):
temp_date = _date + timedelta(days=i)
date = temp_date.strftime('%Y-%m-%d')
# logging.info('# input data: ' + dep + '-' + arr + '-' + date)
# dep, arr, date = 'MNL', 'SIN', '2019-01-04'
post_data = {
"originIata": dep,
"destinationIata": arr,
"departureDate": date + "T00:00:00+08:00",
"passengerComposition": {
"adult": self.ADT,
"children": 0,
"infant": 0
}
}
body = json.dumps(post_data)
# 设置无效
invalid = {
'date': date[:10].replace('-', ''),
'depAirport': dep,
'arrAirport': arr,
'mins': self.custom_settings.get('INVALID_TIME')
}
task_data = {
'dep': dep,
'arr': arr,
'date': date,
'body': body
}
yield scrapy.Request(url=self.start_urls[0],
body=body,
callback=self.parse,
dont_filter=True,
meta={
'invalid': invalid,
'task_data': task_data
},
errback=self.errback,
method='POST')
def start_requests(self):
permins = 0
logging.info(pubUtil.heartbeat(self.host_name, self.name, self.num, permins, self.version))
result_iter = None
# IP使用时长计时器
# start_time = time.time()
while True:
if hasattr(self, 'local'):
if not result_iter:
result_iter = pubUtil.get_task(self.name, days=10)
result = next(result_iter)
else:
result = pubUtil.getUrl(self.name, 1)
if not result:
logging.info('get task error')
time.sleep(20)
continue
for data in result:
# logging.info("## input data: " + data)
# 处理任务 [u'TLN-CFE:20181110:1']
count = int(data.split(':')[-1])
(date, dep, arr) = pubUtil.analysisData(data[:-2])
_date = datetime.strptime(date, '%Y-%m-%d')
for i in range(count):
temp_date = _date + timedelta(days=i)
date = temp_date.strftime('%m/%d/%Y')
invalid_date = temp_date.strftime('%Y%m%d')
# logging.info('# input data: ' + dep + '-' + arr + '-' + date)
# dep, arr, date = 'FLL', 'LAS', '2019-01-13'
# IP超过使用时长，强制更换
# logging.info('ip used time: ' + str(time.time() - start_time))
# if time.time() - start_time > self.use_time:
# self.proxy_flag = True
# logging.info('### ip invalid:' + self.proxy)
if self.proxy_flag:
while True:
# 俄罗斯代理
# self.proxy = pubUtil.nk_get_ip()
# 小池子代理
self.proxy = pubUtil.get_proxy(self.name)
if self.proxy is None:
logging.info('# no get proxy, continue')
# time.sleep(60)
continue
logging.info('# get a new ip: ' + self.proxy)
ip_proxies = {"https": "https://" + self.proxy}
# 获取session
try:
response = requests.get(self.get_session_url, proxies=ip_proxies, timeout=15)
self.cookies_str = json.dumps(requests.utils.dict_from_cookiejar(response.cookies))[
1:-1].replace(
'\"',
'').replace(
':', '=').replace(' ', '').replace(',', '; ')
except Exception as e:
logging.info(e)
self.proxy_flag = True
logging.info('# get session error')
continue
# IP正常使用，开始计时
# start_time = time.time()
self.proxy_flag = False
break
headers = {
'Content-Type': 'application/x-www-form-urlencoded',
'Cookie': self.cookies_str
}
post_data = {
'from': dep,
'to': arr,
# 'from': 'AXM',
# 'to': 'ATL',
'departDate': date,
'departDateDisplay': date,
'ADT': self.ADT
}
post_data.update(self.custom_settings.get('POST_DATA'))
post_data = urllib.urlencode(post_data)
# 设置无效
invalid = {
'date': invalid_date,
'depAirport': dep,
'arrAirport': arr,
'mins': self.custom_settings.get('INVALID_TIME')
}
yield scrapy.Request(url=self.start_urls[0],
body=post_data,
headers=headers,
callback=self.parse,
dont_filter=True,
meta={'invalid': invalid, 'proxy': self.proxy},
errback=self.errback,
method='POST')
