def import_data(context: Context,
spark: SparkSession,
aggregator: AggregationContext,
data_source: str,
limit: int = 50000):
# Store in HBase for further batch processing
print("Start: " + str(datetime.now()))
csv = load_newest(context, spark)
context.save_hbase(csv)
print("End: " + str(datetime.now()))
# Update ingestion times for Flume
latest = datetime.fromtimestamp(csv.first()["opened"])
update_ingestion_times(data_source, latest)
# Batch process 15 minute intervals
aggregated = get_batch_processed(csv)
aggregator.save_hbase(aggregated)
def receive(self, from_node, contexts, timestamp=0):
"""receive_data
1. Stores the information who sent what
2. Increase the hopcount when the context is a single context
>>> d = ContextAggregator()
>>> # two contexts are received
>>> r = d.receive(1, {Context(value=1.0, cohorts=[0,1,2]), Context(value=1.0, cohorts=[0,1,3])})
>>> same(d.get_received_data(1), [[0,1,2],[0,1,3]])
True
>>>
"""
contexts = Context.increase_hop_count(contexts)
self.input[from_node] = contexts
received_info = contexts_to_standard(contexts)
self.context_history.add_to_history(node_number=from_node, value=received_info, timestamp=timestamp)
# -*- coding: utf-8 -*-
import re
from context.context import Context
extract_key = Context().get("utils.extract_key")
_CHAR2NUM = {
u"0": 0,
u"1": 1,
u"2": 2,
u"3": 3,
u"4": 4,
u"5": 5,
u"6": 6,
u"7": 7,
u"8": 8,
u"9": 9,
u"零": 0,
u"一": 1,
u"壹": 1,
u"二": 2,
u"贰": 2,
u"两": 2,
u"三": 3,
u"叁": 3,
u"四": 4,
u"肆": 4,
u"五": 5,
u"伍": 5,
u"六": 6,
# -*- coding: utf-8 -*-
from uuid import uuid1
from django.conf import settings
from context.context import Context
ContentModel = Context().get("zjld.ContentModel")
CassandraQueryApi = Context().get("CassandraQueryApi")
class ZjldArticleModel(ContentModel):
"""docstring for ZjldArticleModel"""
TYPE = "zjld.article"
FIELDS = {
"type": u"文章",
"author": u"",
"publisher": u"",
"title": u"",
"content": u"",
"url": u"",
}
def __init__(self, dct={}):
super(ZjldArticleModel, self).__init__(dct)
def find_dup(self):
dup = []
if self.get('url'):
cql = """SELECT * FROM %s WHERE url='%s' LIMIT 1""" \
# -*- coding: utf-8 -*-
import time
import os
import signal
import logging
from django.conf import settings
from context.context import Context
Daemon = Context().get("utils.Daemon")
RedisQueryApi = Context().get("RedisQueryApi")
Handler = Context().get("Handler")
_CRAWLER_TYPES = {}
_TERMINATING = False
inject_logger = logging.getLogger("crawler.inject")
class CrawlerDaemon(Daemon):
"""
注入任务服务的类，继承了Daemon类。
"""
def __init__(self, CRAWLER_PID):
super(CrawlerDaemon, self).__init__(pidfile=CRAWLER_PID)
def run(self):
signal.signal(signal.SIGTERM, self.term_handler) #将正常终止信号绑定自定义方法。
print "jobtracker pid=%s start done." % os.getpid()
inject_logger.info("jobtracker pid=%s START !" % os.getpid())
#!/usr/bin/python
# -*- coding: utf-8 -*-
import re
import requests
import datetime
import json
#from datetime import datetime
import time
from bs4 import BeautifulSoup
from lxml import etree
from context.context import Context
fmt_time = Context().get("datetimeutil.fmt_time")
def get_urls_re(homepage, time = 10, cookie=''):
html_stream = None
count = 0
while count < 2:
try:
html_stream = requests.get(homepage ,cookies=cookie ,\
timeout = time)
except:
count += 1
else:
break
return html_stream
def test_deserialize(self):
c = Context(value=1.0, cohorts={0,1,2})
s = c.serialize(zipped=True)
c2 = Context.deserialize(s,zipped=True)
c == c2
#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time, random, re
from bs4 import BeautifulSoup
from urllib import quote, unquote
from context.context import Context
WeiboArticleModel = Context().get("WeiboArticleModel")
WeiboHotModel = Context().get("WeiboHotModel")
SearchArticleModel = Context().get("SearchArticleModel")
Crawler = Context().get("Crawler")
export = Context().get("export")
from crawlerimpl.weixin.processdata import HandleUrl, new_time, clear_label, \
HandleContent, get_urls_re, get_charset, change_to_json, clear_space
def _get_url(url):
html_stream = get_urls_re(url, time=6)
if True:
html_stream.encoding = "utf-8"
else:
html_stream.encoding = get_charset(html_stream.text)
return html_stream
class FirstCrawler(Crawler):
# -*- coding: utf-8 -*-
from uuid import uuid1
import time
from datetime import datetime
from context.context import Context]
ContentModel = Context().get("weibo.ContentModel")
CassandraQueryApi = Context().get("CassandraQueryApi")
RedisQueryApi = Context().get("RedisQueryApi")
class WeiboArticleModel(ContentModel):
"""docstring for WeiboArticleModel"""
TYPE = "zjld.weibo"
FIELDS = {
"type": u"微博",
"id": uuid1(),
"author": u"",
"title": u"",
"subtitle": [],
"content": u"",
"url": u"",
"imgurl":[],
"source": u"",
"origin_source": u"",
"pubtime": datetime.utcfromtimestamp(0),
"crtime": datetime.now(),
"publisher": u"",
# -*- coding: utf-8 -*-
import re
from context.context import Context
join_path = Context().get("pathutil.join_path")
Field = Context().get("Field")
Url = Context().get("Url")
ArticleContentCrawler = Context().get("ArticleContentCrawler")
FatherCrawler = Context().get("FatherCrawler")
is_url = Context().get("htmlutil.is_url")
class AqsiqCrawler(FatherCrawler):
type = "aqsiq.news"
item = Field(name="item",
path=r"(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')")
url = Field(name="key", path=r".*", type=Url)
province = Field(name="province", value=u"全国")
publisher = Field(name="publisher", value=u"国家质量监督检验检疫总局")
xpath = {
'title': "//tr/td[@align='center']/h1",
'pubtime':
"//tr/td[@align='center']/h1/../../following-sibling::tr[1]/td/text()",
'content': "//div[@class='TRS_Editor']",
}
child = ArticleContentCrawler
export_fields = [province, publisher]
level=env.LOGGING_LEVEL,
format='%(asctime)s %(message)s')
else:
# otherwise, log to terminal
logging.basicConfig(level=env.LOGGING_LEVEL,
format='%(asctime)s %(message)s')
_LOGGER = logging.getLogger(__name__)
if __name__ == '__main__':
# init context
_LOGGER.info('initializing context')
from context.context import Context
Context.initialize(CONFIG_FILE_PATH)
# init endpoints
_LOGGER.info('initializing endpoints')
from endpoints import Endpoints
Endpoints.initialize()
# Endpoints.post_transaction(
# accountID='88efgiTlszS1z2TqSlPj',
# counterParty='suntrust',
# transactionType='debit',
# description='ATM Withdrawal',
# amount='20'
# )
# Endpoints.post_transaction(
# -*- coding: utf-8 -*-
from datetime import datetime
from uuid import uuid1
from context.context import Context
ContentModel = Context().get("ecommerce.ContentModel")
CassandraQueryApi = Context().get("CassandraQueryApi")
class EcBasicModel(ContentModel):
TYPE = "ecommerce.basic"
FIELDS = {
"source_id": u"",
"title": u"",
"adword": u"",
"version": u"",
"original_price": 0.0,
"history_price": {},
"price": 0.0,
"score": 0,
"summary": {},
"address": u"",
"status": 0,
}
INDEXES = [
{
"key": [("source", 1), ("source_id", 1)],
"unique": True
# -*- coding: utf-8 -*-
import os
import signal
import time
import logging
from threading import Timer
from django.conf import settings
from context.context import Context
Crawler = Context().get("Crawler")
Handler = Context().get("Handler")
get_exception_info = Context().get("get_exception_info")
fetch_logger = logging.getLogger("crawler.fetch")
_RUNNING_CRAWLER = None
_TERMINATING = False
def procedure():
"""
一个执行任务服务进程所需要做的事。
"""
signal.signal(signal.SIGTERM, service_term_handler) #将正常终止信号与自定义方法绑定。
signal.signal(signal.SIGALRM, task_term_handler) #将闹钟信号与自定义方法绑定。
start_time = time.time()
print "tasktracker pid=%s start done." % os.getpid()
fetch_logger.info("tasktracker pid=%s START !" % os.getpid())
while (True if settings.PROCESS_TIMEOUT > 0 else
# -*- coding: utf-8 -*-
import sys
import os
import signal
from django.conf import settings
from context.context import Context
_create_child = Context().get("processutil._create_child")
procedure = Context().get("procedure")
def start():
pid_file = file(settings.CRAWLER_TASK_PID, "w+")
for i in range(settings.TASKTRACKER_COUNT):
pid = _create_child(procedure, [], {}).keys()[0]
pid_file.write(str(pid) + "\n")
pid_file.close()
def stop():
pid_file = file(settings.CRAWLER_TASK_PID, "r")
pids = pid_file.readlines()
pid_file.close()
for i in range(len(pids)):
pids[i] = int(pids[i].strip())
try:
os.kill(pids[i], signal.SIGTERM)
except:
self.pids.pop(pid)
#coding=utf-8
from django.contrib import admin
from context.context import Context
Task = Context().get("Task")
class TaskAdmin(admin.ModelAdmin):
list_display = ('crawler', 'key', 'update_time', 'status', 'interval')
list_editable = ('crawler', 'key', 'status', 'interval')
list_filter = ('crawler', 'status', 'category', 'application', 'interval',
'timeout')
fields = ('key', 'data', 'producer_id', 'category', 'application', 'crawler', \
'status', 'interval', 'timeout', 'last_run', 'next_run', 'update_time', 'create_time')
readonly_fields = ('last_run', 'update_time', 'create_time')
ordering = ('update_time', '-key')
search_fields = ('key', )
admin.site.register(Task, TaskAdmin)
# standard
import json
import logging
# packages
import requests
from firebase_admin import messaging
# internal
from context.context import Context
from utility import const
_LOGGER = logging.getLogger(__name__)
token = Context.data()[const.FIREBASE][const.TOKEN]
def generate_message(data):
# send message to firebase
message = messaging.Message(
data=json.dumps(data),
token=token
)
resp = messaging.send(message)
return resp
raise PreventUpdate
storage._update_transactions()
transaction = storage.tables()[const.TRANSACTIONS_DATA][log_id]
amount = transaction[const.T_LOG][const.TOTALS][const.GRAND_AMOUNT]
day = transaction[const.BUSINESS_DAY][const.DATE_TIME]
return f'Amount: {amount}, Time: {day}'
if __name__ == '__main__':
# init context
_LOGGER.info('initializing context')
from context.context import Context
Context.initialize(CONFIG_FILE_PATH)
# init endpoints
_LOGGER.info('initializing endpoints')
from endpoints import Endpoints
Endpoints.initialize()
# init firebase
_LOGGER.info('initializing firebase')
import firebase_admin
from firebase_admin import credentials
from firebase_admin import db
with FIREBASE_CRED_PATH.open() as file:
FIREBASE_DATA = json.loads(file.read())
cred = credentials.Certificate(FIREBASE_DATA)
# -*- coding: utf-8 -*-
import sys
root_mod = '/Users/liujiasheng/workspace/crawler/crawler'
sys.path.append(root_mod)
import django, os
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "settings.development")
django.setup()
import re
from datetime import datetime
from apps.base.models import ScarletOnsell
from context.context import Context
htmlutil = Context().get("htmlutil")
Url = Context().get("Url")
SearchContentCrawler = Context().get("SearchContentCrawler")
FatherCrawler = Context().get("FatherCrawler")
Field = Context().get("Field")
Crawler = Context().get("Crawler")
class BuffOnsellCrawler(Crawler):
type = "buff.onsell"
def __init__(self, task):
pass
# super(BuffOnsellCrawler, self).__init__(task)
def crawl(self):
# -*- coding: utf-8 -*-
import json
import time
import logging
from datetime import datetime, timedelta
from django.conf import settings
from django.db import transaction
from context.context import Context
CrawlerConf = Context().get("CrawlerConf")
Task = Context().get("Task")
RedisQueryApi = Context().get("RedisQueryApi")
time2str = Context().get("datetimeutil.time2str")
inject_logger = logging.getLogger("crawler.inject")
fetch_logger = logging.getLogger("crawler.fetch")
_CRAWLER_CONF = CrawlerConf()
class Status:
"""
任务状态。
"""
NotStart = 0
Running = 1
Succeed = 2
Failed = -1
Canceling = -2
'''
@author: Yu
'''
import time
import sys
import traceback
import mailutil
from context.context import Context
Daemon = Context().get("utils.Daemon")
class ServiceDefinition(object):
def __init__(self,
check_func,
name="Service",
check_interval=180,
retries=3):
if not callable(check_func):
raise TypeError
self.check_func = check_func
self.name = name
self.check_interval = check_interval
self.retries = retries
self.failures = 0
self.last_check = None
def check(self):
self.check_func()
# -*- coding: utf-8 -*-
import os
import socket
import signal
import time
import logging
import json
import re
from datetime import datetime, timedelta
from context.context import Context
ModelBase = Context().get("ModelBase")
str2time = Context().get("datetimeutil.str2time")
class Crawler(object):
"""
业务爬虫的超类，所有业务爬虫都是该类的子类。
每个业务爬虫都必须有一个唯一标识符，该标识符为名为type的成员属性。
同时要重写crawl()方法。
"""
type = "base.crawler"
def __init__(self, task):
self.task = task
self.key = None
self.data = None
def test_big_number(self):
c = Context(value=1.0, cohorts={40000})
s = c.serialize(zipped=True)
c2 = Context.deserialize(s,zipped=True)
c == c2
# -*- coding: utf-8 -*-
import sys
root_mod = '/home/jshliu/Project/zjld/fix/common/crawler'
sys.path.append(root_mod)
import django, os
os.environ.setdefault("DJANGO_SETTINGS_MODULE", "settings.development");
django.setup()
import re
from datetime import datetime
from context.context import Context
Url = Context().get("Url")
SearchContentCrawler = Context().get("SearchContentCrawler")
FatherCrawler = Context().get("FatherCrawler")
Field = Context().get("Field")
class BaiduCrawler(FatherCrawler):
"""
百度新闻搜索爬虫，继承了通用一级爬虫类。
"""
type = "baidu.news" #该爬虫的唯一标识符。
child = SearchContentCrawler #指定生成的任务由哪一爬虫执行。
item = Field(name="item", path="//div[@id='content_left']/div/div[@class='result']") #需要解析的字段，name为‘item’为特殊含义，不能被占用。
pubtime = Field(name="pubtime", path="div//p[@class='c-author']/text()", type=datetime)
def __init__(self):
sc = Context()
self.__session = SparkSession.builder.getOrCreate()
def load(self):
sc = Context()
return sc.get_context().textFile(self.__config.get_source_path())
# -*- coding: utf-8 -*-
import copy
from context.context import Context
convert = Context().get("typeutil.convert")
class ModelMeta(type):
def __init__(self, name, bases, dct):
fields = dct.get('FIELDS', {})
base = bases[0]
while base != object:
for k, v in base.__dict__.get('FIELDS', {}).iteritems():
fields[k] = v
base = base.__base__
dct['FIELDS'] = fields
indexes = dct.get('INDEXES', [])
base = bases[0]
while base != object:
indexes.extend(base.__dict__.get('INDEXES', []))
base = base.__base__
dct['INDEXES'] = indexes
type.__init__(self, name, bases, dct)
class ModelBase(dict):
__metaclass__ = ModelMeta
# standard
import json
import logging
# packages
import requests
# internal
from context.context import Context
from utility import const
_LOGGER = logging.getLogger(__name__)
base_url = Context.data()[const.SILVER][const.BASE_URL]
headers = Context.data()[const.SILVER][const.HEADERS]
def get_store():
# get store data from the silver api
# build request url
req_url = base_url + '/v2/stores'
res = requests.get(url=req_url, headers=headers)
if res.status_code == 200:
# there is only one store in our data, so we only return that
return res.json()[const.RESULT][0]
else:
_LOGGER.error('Request error')
return None
# -*- coding: utf-8 -*-
import logging
import copy
import time
from uuid import uuid1
from datetime import datetime
from context.context import Context
unix_time = Context().get("datetimeutil.unix_time")
ModelBase = Context().get("ModelBase")
CassandraQueryApi = Context().get("CassandraQueryApi")
import_logger = logging.getLogger("crawler.import")
class ContentModel(ModelBase):
TYPE = "base.content"
FIELDS = {
"id": uuid1(),
"source": u"",
"origin_source": u"",
"pubtime": datetime.utcfromtimestamp(0),
"crtime": datetime.now(),
"crtime_int": int(time.time() * 1000000),
"province": u"",
"city": u"",
"district": u"",
"tag": "",
"comment": {},
# -*- coding: utf-8 -*-
import sys
from django.conf import settings
from context.context import Context
CrawlerDaemon = Context().get("CrawlerDaemon")
def run(*args):
"""
注入任务服务进程的执行入口。
"""
jobtracker = CrawlerDaemon(settings.CRAWLER_JOB_PID)
if args[0] == 'start':
jobtracker.start()
elif args[0] == 'stop':
jobtracker.stop()
# standard
import json
import logging
# packages
import requests
# internal
from context.context import Context
from utility import const
_LOGGER = logging.getLogger(__name__)
base_url = Context.data()[const.TRANSACTIONS][const.BASE_URL]
headers = Context.data()[const.TRANSACTIONS][const.HEADERS]
def transaction_details(transaction_id:str):
# get transaction data from the silver api
# build request url
req_url = base_url + '/transaction-document/transaction-documents/' + transaction_id
res = requests.get(
url=req_url,
headers=headers
)
if res.status_code == 200:
data = res.json()
del data[const.ID]
# -*- coding: utf-8 -*-
import logging
import copy
from uuid import uuid1
from datetime import datetime
from context.context import Context
unix_time = Context().get("datetimeutil.unix_time")
ModelBase = Context().get("ModelBase")
_LOGGER = logging.getLogger("ecommerceimport")
class ContentModel(ModelBase):
TYPE = "base.content"
FIELDS = {
"id": uuid1(),
"source": u"",
"source_level": {},
"first_level": u"",
"second_level": u"",
"third_level": u"",
"fourth_level": u"",
"fifth_level": u"",
"province": u"",
"city": u"",
"district": u"",
"comment": {}
}
# standard
import logging
# packages
import requests
# internal
from utility import const
from context.context import Context
_LOGGER = logging.getLogger(__name__)
BASE_URL = Context.data()[const.BASE_URL]
HEADERS = Context.data()[const.HEADERS]
def inspect_account(accountID: str,
base_url: str = BASE_URL,
headers: dict = HEADERS):
'''
'''
# build request url
req_url = base_url + f'/accounts/{accountID}'
# make request
inspect_account_request = requests.get(url=req_url, headers=headers)
# if request was successful
if inspect_account_request.status_code == 200:
inspect_account_response = {
const.STATUS: inspect_account_request.status_code,
# -*- coding: utf-8 -*-
from uuid import uuid1
from django.conf import settings
from context.context import Context
ContentModel = Context().get("search.ContentModel")
CassandraQueryApi = Context().get("CassandraQueryApi")
class SearchArticleModel(ContentModel):
"""docstring for SearchArticleModel"""
#TYPE = "zjld.article"
TYPE = "zjld.search"
FIELDS = {
"type": u"元搜索",
"author": u"",
"publisher": u"",
"title": u"",
"content": u"",
"url": u"",
"key": u"",
}
def __init__(self, dct={}):
super(SearchArticleModel, self).__init__(dct)
def find_dup(self):
dup = []
