Merge pull request #26 from pestanko/chore/ISS-25-sagram

Chore/iss 25 sagram

.github/workflows/build-and-push.yml

@@ -13,7 +13,7 @@ jobs:
     steps:
       -
         name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
       -
         name: Set up QEMU
         uses: docker/setup-qemu-action@v2

.github/workflows/golangci-lint.yml

@@ -13,13 +13,13 @@ jobs:
     name: lint
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-go@v3
-        with:
-          go-version: 1.19
+      - uses: actions/checkout@v4
 
-      - uses: actions/checkout@v3
+      - uses: actions/setup-go@v4
+        with:
+          go-version-file: go.mod
 
       - name: golangci-lint
-        uses: golangci/golangci-lint-action@v3
+        uses: golangci/golangci-lint-action@v4
         with:
-          args: --timeout 3m0s
+          args: --timeout 3m0s

.github/workflows/unit-test.yml

@@ -14,13 +14,13 @@ jobs:
   unit-tests:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         name: Checkout code
 
       - name: setup golang v1.x
-        uses: actions/setup-go@v3
+        uses: actions/setup-go@v4
         with:
-          go-version: ^1.19
+          go-version-file: go.mod
 
       - name: Install Task
         uses: arduino/setup-task@v1

.pre-commit-config.yaml

@@ -9,8 +9,3 @@ repos:
       - id: check-yaml
         args: ['--unsafe']
       - id: check-added-large-files
-
-  - repo: https://github.com/golangci/golangci-lint
-    rev: v1.50.1
-    hooks:
-      - id: golangci-lint

Dockerfile

@@ -1,4 +1,4 @@
-FROM golang:1.20-alpine AS build
+FROM golang:1.22-alpine AS build
 
 WORKDIR /app
 

README.md

@@ -1,4 +1,4 @@
-# Miniscraper
+# MiniScrape
 
 Simple webpages scrapper written in GO
 
@@ -23,6 +23,7 @@ go get .
 ```
 
 ## Build the scraper
+
 ```shell
 make build
 ```
@@ -33,13 +34,23 @@ make build
 go run main.go scrape
 ```
 
+Scrape the single webpage:
+
+```shell
+# For food category
+go run main.go scrape -C food -N ubaumanu
+```
+
 ### Run the server
+
 ```shell
 make run-serve
 ```
 
 ## Add/Edit available webpages
+
 The webpages list is located in ``./config/default.yml``.
 
 ## License
-Miniscrape is released under the Apache 2.0 license. See LICENSE
+
+Miniscrape is released under the Apache 2.0 license. See LICENSE

Taskfile.yaml

@@ -5,7 +5,7 @@ version: '3'
 vars:
   APPNAME: 'miniscrape'
   GO_VERSION:
-    sh: go version | awk '{print $$3}'
+    sh: go version | awk '{print $3}'
   GO_PATH:
     sh: go env GOPATH
   NC: '\033[0m'

config/categories/food.yml

@@ -264,3 +264,15 @@ pages:
         enabled: true
       html:
         tables: custom
+
+  - codename: sagram
+    name: sagram
+    homepage: https://sargamrestaurace.cz/
+    tags: ["ns", "india", "asia"]
+    url: https://sargamrestaurace.cz/DMenuItems
+    query: "main div.row:nth-child(n+5)"
+    filters:
+      day:
+        enabled: true
+      cut:
+        after: "#Sunday"

internal/scraper/filters/new_line.go

@@ -1,15 +1,16 @@
 package filters
 
 import (
-	"github.com/pestanko/miniscrape/internal/models"
 	"regexp"
+
+	"github.com/pestanko/miniscrape/internal/models"
 )
 
-var normPattern = regexp.MustCompile("\n\n")
+var normPattern = regexp.MustCompile("[\n]+")
 
 // NewNewLineTrimConverter a new instance of the filter that
 // cuts the line of the content
-func NewNewLineTrimConverter(page *models.Page) PageFilter {
+func NewNewLineTrimConverter(_ *models.Page) PageFilter {
 	return &newLineTrimConverter{}
 }