sheets integration

.gitignore

@@ -4,4 +4,5 @@
 /ven/
 **/__pycache__/
 *.pyc
-.env
+.env
+client_secret.json

api/auth/auth_utils.py

@@ -4,11 +4,9 @@
 from fastapi import HTTPException, status, Depends
 from fastapi.security import OAuth2PasswordBearer
 
-from settings import *
 from api.core.users import TokenData
 from api.auth.db_utils import UserInDB, get_user
 
-load_dotenv()
 oauth2_scheme = OAuth2PasswordBearer(tokenUrl="/api/auth/token")
 
 

api/core/formatters/__init__.py

@@ -4,3 +4,4 @@
 class OutputFormat(Enum):
     CSV = "csv"
     JSON = "json"
+    GSHEET = "gsheet"

api/core/formatters/csv/__init__.py

@@ -1,19 +1,50 @@
+import gspread
+from oauth2client.service_account import ServiceAccountCredentials
+
 import csv
 from io import StringIO
 from datetime import datetime
 
 from ...jobs import *
 from ...scrapers import *
+from settings import *
 
 
-def generate_filename() -> str:
-    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-    return f"JobSpy_results_{timestamp}.csv"
+class CSVFormatter:
+    @staticmethod
+    def upload_to_google_sheet(csv_data: str):
+        try:
+            scope = [
+                "https://www.googleapis.com/auth/spreadsheets",
+                "https://www.googleapis.com/auth/drive.file",
+                "https://www.googleapis.com/auth/drive",
+            ]
+            credentials = ServiceAccountCredentials.from_json_keyfile_name(
+                GSHEET_JSON_KEY_PATH, scope
+            )
+            gc = gspread.authorize(credentials)
+            sh = gc.open(GSHEET_NAME)
 
+            worksheet = sh.get_worksheet(0)
+            data_string = csv_data.getvalue()
+            reader = csv.reader(StringIO(data_string))
+
+            rows = list(reader)
+
+            for i, row in enumerate(rows):
+                if i == 0:
+                    continue
+                worksheet.append_row(row)
+        except Exception as e:
+            raise e
+
+    @staticmethod
+    def generate_filename() -> str:
+        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+        return f"JobSpy_results_{timestamp}.csv"
 
-class CSVFormatter:
     @staticmethod
-    def format(jobs: ScraperResponse) -> StringIO:
+    def format(jobs: CommonResponse) -> StringIO:
         """
         Transfomr the jobs objects into csv
         :param jobs:
@@ -41,7 +72,7 @@ def format(jobs: ScraperResponse) -> StringIO:
         writer.writerow(headers)
 
         for site, job_response in jobs.dict().items():
-            if job_response and job_response.get("success"):
+            if isinstance(job_response, dict) and job_response.get("success"):
                 for job in job_response["jobs"]:
                     writer.writerow(
                         [

api/core/scrapers/__init__.py

@@ -1,6 +1,6 @@
 from ..jobs import *
 from ..formatters import OutputFormat
-from typing import List, Dict, Optional
+from typing import List, Dict, Optional, Any
 
 
 class StatusException(Exception):
@@ -28,10 +28,12 @@ class ScraperInput(BaseModel):
     results_wanted: int = 15
 
 
-class ScraperResponse(BaseModel):
-    linkedin: Optional[JobResponse]
-    indeed: Optional[JobResponse]
-    zip_recruiter: Optional[JobResponse]
+class CommonResponse(BaseModel):
+    status: Optional[str]
+    error: Optional[str]
+    linkedin: Optional[Any] = None
+    indeed: Optional[Any] = None
+    zip_recruiter: Optional[Any] = None
 
 
 class Scraper:

api/v1/jobs/__init__.py

@@ -6,13 +6,13 @@
 from api.core.scrapers.indeed import IndeedScraper
 from api.core.scrapers.ziprecruiter import ZipRecruiterScraper
 from api.core.scrapers.linkedin import LinkedInScraper
-from api.core.formatters.csv import CSVFormatter, generate_filename
+from api.core.formatters.csv import CSVFormatter
 from api.core.scrapers import (
     ScraperInput,
     Site,
     JobResponse,
     OutputFormat,
-    ScraperResponse,
+    CommonResponse,
 )
 from typing import List, Dict, Tuple, Union
 
@@ -26,7 +26,7 @@
 
 
 @router.post("/")
-async def scrape_jobs(scraper_input: ScraperInput) -> ScraperResponse:
+async def scrape_jobs(scraper_input: ScraperInput) -> CommonResponse:
     """
     Asynchronously scrapes job data from multiple job sites.
     :param scraper_input:
@@ -42,14 +42,26 @@ def scrape_site(site: Site) -> Tuple[str, JobResponse]:
     with ThreadPoolExecutor() as executor:
         results = dict(executor.map(scrape_site, scraper_input.site_type))
 
-    scraper_response = ScraperResponse(**results)
+    scraper_response = CommonResponse(status="JSON response success", **results)
 
     if scraper_input.output_format == OutputFormat.CSV:
         csv_output = CSVFormatter.format(scraper_response)
         response = StreamingResponse(csv_output, media_type="text/csv")
         response.headers[
             "Content-Disposition"
-        ] = f"attachment; filename={generate_filename()}"
+        ] = f"attachment; filename={CSVFormatter.generate_filename()}"
         return response
 
-    return scraper_response
+    elif scraper_input.output_format == OutputFormat.GSHEET:
+        csv_output = CSVFormatter.format(scraper_response)
+        try:
+            CSVFormatter.upload_to_google_sheet(csv_output)
+            return CommonResponse(status="Successfully uploaded to Google Sheets")
+
+        except Exception as e:
+            return CommonResponse(
+                status="Failed to upload to Google Sheet", error=str(e)
+            )
+
+    else:
+        return scraper_response

settings.py

@@ -2,9 +2,14 @@
 import os
 
 load_dotenv()
+# gsheets (template to copy at https://docs.google.com/spreadsheets/d/1HAnn-aPv-BO4QTEzfIWc-5iw50duyMoTgX8o3RsEOWs/edit?usp=sharing)
+GSHEET_JSON_KEY_PATH = "client_secret.json"
+GSHEET_NAME = "JobSpy"
+
+# optional autha
+AUTH_REQUIRED = False
 SUPABASE_URL = os.environ.get("SUPABASE_URL")
 SUPABASE_KEY = os.environ.get("SUPABASE_KEY")
 JWT_SECRET_KEY = os.environ.get("JWT_SECRET_KEY")
-ALGORITHM = "HS256"
 ACCESS_TOKEN_EXPIRE_MINUTES = 60
-AUTH_REQUIRED = False
+ALGORITHM = "HS256"