Docker workflow (#24)

.github/workflows/docker-build.yml

@@ -0,0 +1,32 @@
+name: Build and Push Docker Image
+
+on:
+  push:
+    branches:
+      - docker_workflow
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Login to GitHub Docker Registry
+        uses: docker/login-action@v1
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build and Push Image
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ghcr.io/${{ github.repository_owner }}/jobspy:latest

.github/workflows/test.yml

@@ -39,50 +39,51 @@ jobs:
           exit 1
         fi
 
-    - name: Check HTTP status to POST /api/v1/jobs/
+# not checking currently because of bad ip at Github's servers being blocked
-      run: |
+#    - name: Check HTTP status to POST /api/v1/jobs/
-        response=$(curl -L -s -X 'POST' -H 'Content-Type: application/json' -d '{
+#      run: |
-          "site_type": ["indeed", "linkedin"], 
+#        response=$(curl -L -s -X 'POST' -H 'Content-Type: application/json' -d '{
-          "search_term": "software engineer",
+#          "site_type": ["indeed", "linkedin"],
-          "location": "austin, tx",
+#          "search_term": "software engineer",
-          "distance": 10,
+#          "location": "austin, tx",
-          "job_type": "fulltime",
+#          "distance": 10,
-          "results_wanted": 5
+#          "job_type": "fulltime",
-        }' http://0.0.0.0:8000/api/v1/jobs -w "%{http_code}")
+#          "results_wanted": 5
-        
+#        }' http://0.0.0.0:8000/api/v1/jobs -w "%{http_code}")
-        status_code="${response: -3}"
+#
-        echo "Received status code: $status_code"
+#        status_code="${response: -3}"
-        
+#        echo "Received status code: $status_code"
-        if [ "$status_code" != "200" ]; then
+#
-          echo "Error: Expected status code 200, but got $status_code"
+#        if [ "$status_code" != "200" ]; then
-          exit 1
+#          echo "Error: Expected status code 200, but got $status_code"
-        fi
+#          exit 1
-
+#        fi
-        echo "${response::-3}" > response.json
+#
-        cat response.json
+#        echo "${response::-3}" > response.json
-
+#        cat response.json
-    - name: Check error field in response
+#
-      run: |
+#    - name: Check error field in response
-        global_error=$(jq '.error' response.json)
+#      run: |
-        indeed_error=$(jq '.indeed.error' response.json)
+#        global_error=$(jq '.error' response.json)
-        linkedin_error=$(jq '.linkedin.error' response.json)
+#        indeed_error=$(jq '.indeed.error' response.json)
-
+#        linkedin_error=$(jq '.linkedin.error' response.json)
-        if [[ "$indeed_error" != "null" || "$linkedin_error" != "null" ]]; then
+#
-          echo "Error found in response:"
+#        if [[ "$indeed_error" != "null" || "$linkedin_error" != "null" ]]; then
-          echo "Global Error: $global_error"
+#          echo "Error found in response:"
-          echo "Indeed Error: $indeed_error"
+#          echo "Global Error: $global_error"
-          echo "LinkedIn Error: $linkedin_error"
+#          echo "Indeed Error: $indeed_error"
-          exit 1
+#          echo "LinkedIn Error: $linkedin_error"
-        fi
+#          exit 1
-
+#        fi
-    - name: Verify returned_results in response
+#
-      run: |
+#    - name: Verify returned_results in response
-        indeed_results=$(jq '.indeed.returned_results' response.json)
+#      run: |
-        linkedin_results=$(jq '.linkedin.returned_results' response.json)
+#        indeed_results=$(jq '.indeed.returned_results' response.json)
-        
+#        linkedin_results=$(jq '.linkedin.returned_results' response.json)
-        if [[ $indeed_results -ne 5 || $linkedin_results -ne 5 ]]; then
+#
-          echo "Mismatch in results_wanted and returned_results:"
+#        if [[ $indeed_results -ne 5 || $linkedin_results -ne 5 ]]; then
-          echo "Indeed: Expected 5, Got $indeed_results"
+#          echo "Mismatch in results_wanted and returned_results:"
-          echo "LinkedIn: Expected 5, Got $linkedin_results"
+#          echo "Indeed: Expected 5, Got $indeed_results"
-          exit 1
+#          echo "LinkedIn: Expected 5, Got $linkedin_results"
-        fi
+#          exit 1
+#        fi

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY . /app
+
+RUN apt-get update && \
+    apt-get install -y jq && \
+    pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 8000
+
+ENV PORT=8000
+
+CMD sh -c "uvicorn main:app --host 0.0.0.0 --port $PORT"

README.md

@@ -138,13 +138,51 @@ linkedin, Software Engineer 1, Public Partnerships | PPL, https://www.linkedin.c
 ```
 
 ## Installation
-_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_  
-1. Clone this repository `git clone https://github.com/cullenwatson/jobspy`
-2. Install the dependencies with `pip install -r requirements.txt`
-4. Run the server with `uvicorn main:app --reload`
 
-## Usage
+## Docker Image (simple)
-### Google Sheets Integration (Optional)
+_Requires [Docker Desktop](https://www.docker.com/products/docker-desktop/)_
+
+[JobSpy API Image](https://ghcr.io/cullenwatson/jobspy:latest) is continuously updated and available on GitHub Container Registry. You can pull and use the image with:
+
+## Usage Docker
+
+To pull the Docker image:
+
+```bash
+docker pull ghcr.io/cullenwatson/jobspy:latest
+```
+
+### Params
+
+By default, 
+* `client_secret.json` in current directory  (if using Google Sheets, see below to obtain)
+* Listens on port `8000`
+* Places the jobs into a sheet that is named JobSpy
+
+ To run the image with these default settings, use:
+
+Example (Windows):
+```bash
+docker run -v %cd%/client_secret.json:/app/client_secret.json -p 8000:8000 ghcr.io/cullenwatson/jobspy
+```
+
+Example (Unix):
+```bash
+docker run -v $(pwd)/client_secret.json:/app/client_secret.json -p 8000:8000 ghcr.io/cullenwatson/jobspy
+```
+
+### Using custom params
+
+  For example, 
+   * port `8030`,
+   * path `C:\config\client_secret.json`
+   * Google sheet name `JobSheet`
+
+```bash
+docker run -v C:\config\client_secret.json:/app/client_secret.json -e GSHEET_NAME=JobSheet -e PORT=8030 -p 8030:8030 ghcr.io/cullenwatson/jobspy
+```
+
+### Google Sheets Integration
 
 #### Obtaining an Access Key: [Video Guide](https://youtu.be/w533wJuilao?si=5u3m50pRtdhqkg9Z&t=43)
   * Enable the [Google Sheets & Google Drive API](https://console.cloud.google.com/)
@@ -161,8 +199,6 @@ _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/)
 
 ### How to call the API
 
-
-
 #### [Postman](https://www.postman.com/downloads/) (preferred):
 To use Postman:
 1. Locate the files in the `/postman/` directory.
@@ -171,6 +207,12 @@ To use Postman:
 #### Swagger UI:
 Or you can call the API with the interactive documentation at [localhost:8000/docs](http://localhost:8000/docs).
 
+
+## Python installtion (alternative to Docker)
+_Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_  
+1. Clone this repository `git clone https://github.com/cullenwatson/jobspy`
+2. Install the dependencies with `pip install -r requirements.txt`
+4. Run the server with `uvicorn main:app --reload`
 ## FAQ
 
 ### I'm having issues with my queries. What should I do?

api/core/formatters/csv/__init__.py

@@ -20,7 +20,7 @@ class CSVFormatter:
                 "https://www.googleapis.com/auth/drive",
             ]
             credentials = ServiceAccountCredentials.from_json_keyfile_name(
-                GSHEET_JSON_KEY_PATH, scope
+                "client_secret.json", scope
             )
             gc = gspread.authorize(credentials)
             sh = gc.open(GSHEET_NAME)
@@ -43,6 +43,11 @@ class CSVFormatter:
         timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
         return f"JobSpy_results_{timestamp}.csv"
 
+    @staticmethod
+    def generate_filename() -> str:
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        return f"JobSpy_results_{timestamp}.csv"
+
     @staticmethod
     def format(jobs: CommonResponse) -> StringIO:
         """

settings.py

@@ -2,9 +2,8 @@ from dotenv import load_dotenv
 import os
 
 load_dotenv()
-# gsheets (template to copy at https://docs.google.com/spreadsheets/d/1HAnn-aPv-BO4QTEzfIWc-5iw50duyMoTgX8o3RsEOWs/edit?usp=sharing)
+# gsheets (template to copy at https://docs.google.com/spreadsheets/d/1mOgb-ZGZy_YIhnW9OCqIVvkFwiKFvhMBjNcbakW7BLo/edit?usp=sharing)
-GSHEET_JSON_KEY_PATH = "client_secret.json"
+GSHEET_NAME = os.environ.get("GSHEET_NAME", "JobSpy")
-GSHEET_NAME = "JobSpy"
 
 # optional autha
 AUTH_REQUIRED = False