Refactor Dockerfile and Update CI Configuration

- Changed the working directory in the Dockerfile to /app for better organization.
- Removed the iat.yaml configuration file to simplify the container setup and reduce complexity.
- Adjusted the exposed port to 80, aligning with standard HTTP practices for the scraper application.
- Updated the CI configuration in .drone.yml to reflect these changes, ensuring a streamlined build process.

.drone.yml

@@ -18,7 +18,6 @@ steps:
       - APP_VERSION=$(git rev-list HEAD --count --no-merges)-$DRONE_BRANCH
       - echo "APP Version tags $APP_VERSION"
       - echo -n "$APP_VERSION" >> .tags
-
   - name: build web
     image: plugins/docker
     settings:

cmd/scraper/Dockerfile

@@ -3,21 +3,20 @@ ARG BASH_VERSION=5.0
 
 FROM golang:${GO_VERSION} AS go-builder
 
-WORKDIR /go/src/company/tm_back
+WORKDIR /app
 
 COPY . .
-COPY cmd/scraper/iat.yaml /go/bin/config.yaml
 
 RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -v -o scraper-build ./cmd/scraper/main.go
 
 FROM bash:${BASH_VERSION}
 RUN apk --no-cache add busybox-suid curl rsync tzdata tcpdump tree ca-certificates s-nail \
-    && ln -s /usr/bin/mail /usr/bin/s-nail \
+    && ln -s /usr/bin/mail /usr/bin/s-nail
-    && mkdir -p /go/bin/media /go/bin/log /go/bin/config
-WORKDIR /go/bin
 
-COPY --from=go-builder /go/src/company/tm_back/scraper-build .
+WORKDIR /app
 
-EXPOSE 8090
+COPY --from=go-builder /app/scraper-build .
+
+EXPOSE 80
 
 ENTRYPOINT /go/bin/scraper-build

cmd/scraper/iat.yaml

@@ -1,28 +0,0 @@
-database:
-  mongodb:
-    uri: "mongodb://mongo:27017"
-    name: "tender_management"
-    timeout: 10s
-    max_pool_size: 50
-
-logging:
-  level: "info"
-  format: "json"
-  output: "file"  # stdout, stderr, file
-  file:
-    path: "./logs/scraper.log"
-    max_size: 100      # Max size in MB before rotation
-    max_backups: 5     # Number of backup files to keep
-    max_age: 30        # Max age in days to keep log files
-    compress: true     # Compress rotated files
-
-ted:
-  base_url: "https://ted.europa.eu/packages/daily"
-  timeout: 300s  # Increased to 5 minutes for large files
-  max_retries: 5
-  retry_delay: 10s
-  user_agent: "TenderManagement-TED-Scraper/1.0"
-  max_concurrency: 2  # Reduced to avoid overwhelming the server
-  download_dir: "./ted_downloads"
-  cleanup_after: 72h
-  scraping_interval: 12h  # Run scraping every 12 hours