File tree Expand file tree Collapse file tree 3 files changed +14
-4
lines changed
Expand file tree Collapse file tree 3 files changed +14
-4
lines changed Original file line number Diff line number Diff line change 1- FROM nginx: alpine
1+ FROM alpine:3.7
22WORKDIR /app
33RUN apk add --no-cache --virtual .build-deps g++ python3-dev libffi-dev \
44 openssl-dev libxml2-dev libxslt-dev gcc musl-dev py3-pip && \
Original file line number Diff line number Diff line change 2323 - containerPort : 5555
2424 protocol : TCP
2525 imagePullPolicy : {{ .Values.deployment.imagePullPolicy }}
26+ livenessProbe :
27+ httpGet :
28+ path : /random
29+ port : 5555
30+ initialDelaySeconds : 60
31+ periodSeconds : 5
32+ failureThreshold : 5
33+ timeoutSeconds : 10
2634 resources :
2735 {{- toYaml .Values.deployment.resources | nindent 12 }}
2836 env :
Original file line number Diff line number Diff line change 44from proxypool .setting import GET_TIMEOUT
55from fake_headers import Headers
66import time
7+
8+
79class BaseCrawler (object ):
810 urls = []
9-
11+
1012 @retry (stop_max_attempt_number = 3 , retry_on_result = lambda x : x is None , wait_fixed = 2000 )
1113 def fetch (self , url , ** kwargs ):
1214 try :
1315 headers = Headers (headers = True ).generate ()
1416 kwargs .setdefault ('timeout' , GET_TIMEOUT )
1517 kwargs .setdefault ('verify' , False )
1618 kwargs .setdefault ('headers' , headers )
17- response = requests .get (url , ** kwargs )
19+ response = requests .get (url , ** kwargs )
1820 if response .status_code == 200 :
1921 response .encoding = 'utf-8'
2022 return response .text
2123 except requests .ConnectionError :
2224 return
23-
25+
2426 @logger .catch
2527 def crawl (self ):
2628 """
You can’t perform that action at this time.
0 commit comments