update 定时抓取改为定时匹配

This commit is contained in:
timerzz 2025-03-28 14:30:33 +08:00
parent 895b86e38a
commit bee82026fd
13 changed files with 496 additions and 37 deletions

View File

@ -8,7 +8,7 @@ jobs:
env:
HTTPS_PROXY: http://192.168.31.55:10809
with:
go-version: '1.22.x'
go-version: '1.24.x'
- uses: http://192.168.31.55:13000/timerzz/checkout@v4
- uses: http://192.168.31.55:13000/timerzz/setup-ko@v0.6
with:

13
build/build-chart.sh Normal file
View File

@ -0,0 +1,13 @@
#!/usr/bin/bash
# 打包 Helm Chart
helm package chart/
# 获取最新生成的包名
chart_package=$(ls -t *.tgz | head -n 1)
# 推送 Helm Chart 到 OCI 仓库
helm push $chart_package oci://registry.timerzz.com:20443/helm-charts
# 删除生成的包
rm -f $chart_package

23
build/chart/.helmignore Normal file
View File

@ -0,0 +1,23 @@
# Patterns to ignore when building packages.
# This supports shell glob matching, relative path matching, and
# negation (prefixed with !). Only one pattern per line.
.DS_Store
# Common VCS dirs
.git/
.gitignore
.bzr/
.bzrignore
.hg/
.hgignore
.svn/
# Common backup files
*.swp
*.bak
*.tmp
*.orig
*~
# Various IDEs
.project
.idea/
*.tmproj
.vscode/

24
build/chart/Chart.yaml Normal file
View File

@ -0,0 +1,24 @@
apiVersion: v2
name: dw-spider
description: 抓取得物价格
# A chart can be either an 'application' or a 'library' chart.
#
# Application charts are a collection of templates that can be packaged into versioned archives
# to be deployed.
#
# Library charts provide useful utilities or functions for the chart developer. They're included as
# a dependency of application charts to inject those utilities and functions into the rendering
# pipeline. Library charts do not define any templates and therefore cannot be deployed.
type: application
# This is the chart version. This version number should be incremented each time you make changes
# to the chart and its templates, including the app version.
# Versions are expected to follow Semantic Versioning (https://semver.org/)
version: 1.0.1
# This is the version number of the application being deployed. This version number should be
# incremented each time you make changes to the application. Versions are not expected to
# follow Semantic Versioning. They should reflect the version the application is using.
# It is recommended to use it with quotes.
appVersion: "v1.0.1"

View File

@ -0,0 +1,22 @@
1. Get the application URL by running these commands:
{{- if .Values.ingress.enabled }}
{{- range $host := .Values.ingress.hosts }}
{{- range .paths }}
http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
{{- end }}
{{- end }}
{{- else if contains "NodePort" .Values.service.type }}
export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "chart.fullname" . }})
export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
echo http://$NODE_IP:$NODE_PORT
{{- else if contains "LoadBalancer" .Values.service.type }}
NOTE: It may take a few minutes for the LoadBalancer IP to be available.
You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "chart.fullname" . }}'
export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "chart.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
echo http://$SERVICE_IP:{{ .Values.service.port }}
{{- else if contains "ClusterIP" .Values.service.type }}
export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "chart.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
echo "Visit http://127.0.0.1:8080 to use your application"
kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
{{- end }}

View File

@ -0,0 +1,62 @@
{{/*
Expand the name of the chart.
*/}}
{{- define "chart.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Create a default fully qualified app name.
We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
If release name contains chart name it will be used as a full name.
*/}}
{{- define "chart.fullname" -}}
{{- if .Values.fullnameOverride }}
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- if contains $name .Release.Name }}
{{- .Release.Name | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- end }}
{{- end }}
{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "chart.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Common labels
*/}}
{{- define "chart.labels" -}}
helm.sh/chart: {{ include "chart.chart" . }}
{{ include "chart.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{/*
Selector labels
*/}}
{{- define "chart.selectorLabels" -}}
app.kubernetes.io/name: {{ include "chart.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{/*
Create the name of the service account to use
*/}}
{{- define "chart.serviceAccountName" -}}
{{- if .Values.serviceAccount.create }}
{{- default (include "chart.fullname" .) .Values.serviceAccount.name }}
{{- else }}
{{- default "default" .Values.serviceAccount.name }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,83 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "chart.fullname" . }}
labels:
{{- include "chart.labels" . | nindent 4 }}
spec:
{{- if not .Values.autoscaling.enabled }}
replicas: {{ .Values.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "chart.selectorLabels" . | nindent 6 }}
template:
metadata:
{{- with .Values.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "chart.labels" . | nindent 8 }}
{{- with .Values.podLabels }}
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "chart.serviceAccountName" . }}
{{- with .Values.podSecurityContext }}
securityContext:
{{- toYaml . | nindent 8 }}
{{- end }}
containers:
- name: {{ .Chart.Name }}
{{- with .Values.securityContext }}
securityContext:
{{- toYaml . | nindent 12 }}
{{- end }}
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
ports:
- name: http
containerPort: {{ .Values.service.port }}
protocol: TCP
env:
- name: BID_TYPE
value: '{{ .Values.env.bid }}'
- name: SELLER_ID
value: {{ .Values.env.sellerID }}
{{- with .Values.livenessProbe }}
livenessProbe:
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.readinessProbe }}
readinessProbe:
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.resources }}
resources:
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.volumeMounts }}
volumeMounts:
{{- toYaml . | nindent 12 }}
{{- end }}
{{- with .Values.volumes }}
volumes:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}

View File

@ -0,0 +1,32 @@
{{- if .Values.autoscaling.enabled }}
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: {{ include "chart.fullname" . }}
labels:
{{- include "chart.labels" . | nindent 4 }}
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: {{ include "chart.fullname" . }}
minReplicas: {{ .Values.autoscaling.minReplicas }}
maxReplicas: {{ .Values.autoscaling.maxReplicas }}
metrics:
{{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
{{- end }}
{{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
- type: Resource
resource:
name: memory
target:
type: Utilization
averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,43 @@
{{- if .Values.ingress.enabled -}}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: {{ include "chart.fullname" . }}
labels:
{{- include "chart.labels" . | nindent 4 }}
{{- with .Values.ingress.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
{{- with .Values.ingress.className }}
ingressClassName: {{ . }}
{{- end }}
{{- if .Values.ingress.tls }}
tls:
{{- range .Values.ingress.tls }}
- hosts:
{{- range .hosts }}
- {{ . | quote }}
{{- end }}
secretName: {{ .secretName }}
{{- end }}
{{- end }}
rules:
{{- range .Values.ingress.hosts }}
- host: {{ .host | quote }}
http:
paths:
{{- range .paths }}
- path: {{ .path }}
{{- with .pathType }}
pathType: {{ . }}
{{- end }}
backend:
service:
name: {{ $.Values.env.sellerID }}
port:
number: {{ $.Values.service.port }}
{{- end }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,15 @@
apiVersion: v1
kind: Service
metadata:
name: {{ .Values.env.sellerID }}
labels:
{{- include "chart.labels" . | nindent 4 }}
spec:
type: {{ .Values.service.type }}
ports:
- port: {{ .Values.service.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "chart.selectorLabels" . | nindent 4 }}

View File

@ -0,0 +1,13 @@
{{- if .Values.serviceAccount.create -}}
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "chart.serviceAccountName" . }}
labels:
{{- include "chart.labels" . | nindent 4 }}
{{- with .Values.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
automountServiceAccountToken: {{ .Values.serviceAccount.automount }}
{{- end }}

155
build/chart/values.yaml Normal file
View File

@ -0,0 +1,155 @@
# Default values for chart.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
# This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
replicaCount: 1
# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
repository: registry.timerzz.com:20443/kedaya/dw-spider
# This sets the pull policy for images.
pullPolicy: Always
# Overrides the image tag whose default is the chart appVersion.
tag: "latest"
# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets: []
# This is to override the chart name.
nameOverride: ""
fullnameOverride: ""
# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
serviceAccount:
# Specifies whether a service account should be created
create: false
# Automatically mount a ServiceAccount's API credentials?
automount: true
# Annotations to add to the service account
annotations: {}
# The name of the service account to use.
# If not set and create is true, a name is generated using the fullname template
name: ""
# This is for setting Kubernetes Annotations to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
podAnnotations: {}
# This is for setting Kubernetes Labels to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
podLabels: {}
podSecurityContext: {}
# fsGroup: 2000
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
# This is for setting up a service more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/
service:
# This sets the service type more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
type: ClusterIP
# This sets the ports more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports
port: 80
# This block is for setting up the ingress for more information can be found here: https://kubernetes.io/docs/concepts/services-networking/ingress/
ingress:
enabled: true
className: "kubesphere-router-cluster"
annotations: {}
hosts:
- host: ht.timerzz.com
paths:
- path: /api/v2/seller/dw-normal # 闪电直发 dw-consign 预售 dw-pre-sale 现货 dw-normal
pathType: ImplementationSpecific
tls: []
# - secretName: chart-example-tls
# hosts:
# - chart-example.local
resources: {}
# We usually recommend not to specify default resources and to leave this as a conscious
# choice for the user. This also increases chances charts run on environments with little
# resources, such as Minikube. If you do want to specify resources, uncomment the following
# lines, adjust them as necessary, and remove the curly braces after 'resources:'.
requests:
cpu: 20m
memory: 50Mi
# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
livenessProbe:
httpGet:
path: /living
port: 80
scheme: HTTP
timeoutSeconds: 1
periodSeconds: 3
successThreshold: 1
failureThreshold: 3
readinessProbe:
httpGet:
path: /ready
port: 80
scheme: HTTP
timeoutSeconds: 1
periodSeconds: 3
successThreshold: 1
failureThreshold: 3
# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
autoscaling:
enabled: false
minReplicas: 1
maxReplicas: 100
targetCPUUtilizationPercentage: 80
# targetMemoryUtilizationPercentage: 80
# Additional volumes on the output Deployment definition.
volumes:
- name: host-time
hostPath:
path: /etc/localtime
type: ''
- name: volume-7oavgu
configMap:
name: online
items:
- key: db
path: db.yaml
- key: redis
path: redis.yaml
- key: dw
path: dw.yaml
defaultMode: 420
# - name: foo
# secret:
# secretName: mysecret
# optional: false
# Additional volumeMounts on the output Deployment definition.
volumeMounts:
- name: host-time
readOnly: true
mountPath: /etc/localtime
- name: volume-7oavgu
readOnly: true
mountPath: /cfg
# - name: foo
# mountPath: "/etc/foo"
# readOnly: true
nodeSelector: {}
tolerations: []
affinity: {}
env:
bid: 0 # 预售 1 现货 0 闪电直发: 5
sellerID: dw-normal #闪电直发 dw-consign 预售 dw-pre-sale 现货 dw-normal

View File

@ -155,48 +155,22 @@ func (c *Controller) Crawl() {
var msgs = make([]string, 0)
var results = make([]*v2.Article, 0, 20)
c.storage.DB().Debug().
Preload("Sellers", "seller_id = ?", c.sellerId).Preload("Sellers.CalculateProcess").
Preload("Sellers", "seller_id = ?", c.sellerId).
Joins("LEFT JOIN seller_articles ON seller_articles.article_id=articles.id AND seller_articles.seller_id = ?", c.sellerId).
Where("(seller_articles.exclude is null OR not seller_articles.exclude) AND (articles.exclude is null OR not articles.exclude)").
Where("(seller_articles.exclude is null) AND (articles.exclude is null OR not articles.exclude)").
FindInBatches(&results, 20, func(tx *gorm.DB, batch int) error {
glog.Infof("正在抓取第%d批数据", batch)
for _, article := range results {
var sArticle v2.SellerArticle
if len(article.Sellers) > 0 {
sArticle = article.Sellers[0]
} else {
var err error
sArticle, err = c.MatchDWSluId(v2.SellerArticle{
ArticleID: article.ID,
SellerId: c.sellerId,
Pid: article.Pid,
Brand: article.Brand,
})
if err != nil {
glog.Warning(err)
}
if sArticle.SkuID == "" {
continue
}
sArticle, err = c.storage.SellerArticle().Get(storage.NewGetSellerArticleQuery().SetSellerId(c.sellerId).SetSkuId(sArticle.SkuID))
if err != nil {
glog.Warning(err)
continue
}
}
if err := c.PullArticle(sArticle); err != nil {
msgs = append(msgs, err.Error())
glog.Error(err.Error())
continue
}
// 抓取成功,利润率重新计算
if err := c.subscribeClient.Publish(c.ctx, utils.ProfitRate_Channel, strconv.Itoa(int(article.ID))); err != nil {
glog.Warningf("发布消息失败: %v", err)
if _, err := c.MatchDWSluId(v2.SellerArticle{
ArticleID: article.ID,
SellerId: c.sellerId,
Pid: article.Pid,
Brand: article.Brand,
}); err != nil {
glog.Warning(err)
}
}
glog.Infof("完成抓取第%d批数据", batch)
glog.Infof("完成匹配第%d批数据", batch)
return nil
})