maped to job post object

fix the location by goozali ids

src/jobspy/jobs/__init__.py

@@ -185,6 +185,7 @@ class Location(BaseModel):
     country: Country | str | None = None
     city: Optional[str] = None
     state: Optional[str] = None
+    text: str = None
 
     def display_location(self) -> str:
         location_parts = []
@@ -253,6 +254,12 @@ class DescriptionFormat(Enum):
 
 
 class JobPost(BaseModel):
+
+    # def __init__(self, obj):
+    #     super().__init__()
+    #     for key, value in obj.items():
+    #         setattr(self, key, value)
+
     id: str | None = None
     title: str
     company_name: str | None
@@ -271,6 +278,7 @@ class JobPost(BaseModel):
     emails: list[str] | None = None
     is_remote: bool | None = None
     listing_type: str | None = None
+    field: str | None = None
 
     # linkedin specific
     job_level: str | None = None

src/jobspy/scrapers/goozali/GoozaliMapper.py

@@ -1,10 +1,12 @@
+from datetime import datetime
 import json
 
-from jobspy.jobs import JobPost
+from jobspy.jobs import JobPost, Location
 from jobspy.scrapers.goozali.model import GoozaliColumnTypeOptions, GoozaliResponse, GoozaliRow
 from jobspy.scrapers.goozali.model.GoozaliColumn import GoozaliColumn
 from jobspy.scrapers.goozali.model.GoozaliColumnChoice import GoozaliColumnChoice
 from jobspy.scrapers.goozali.model.GozaaliResponseData import GoozaliResponseData
+from .constants import job_post_column_to_goozali_column, job_post_column_names
 
 # Mapping function to convert parsed dictionary into GoozaliResponseData
 
@@ -77,6 +79,24 @@ class GoozaliMapper:
         # Return a new GoozaliResponse with msg and the converted data
         return GoozaliResponse(msg=data['msg'], data=data_obj)
 
-    def map_goozali_response_to_job_post(self, row: GoozaliRow, columns: dict[str, GoozaliColumn]) -> JobPost:
+    def get_value_by_job_post_Id(self, job_post_column: str, row: GoozaliRow, dict_column_name_to_columnZ):
+        goozali_column_name = job_post_column_to_goozali_column[job_post_column]
+        column = dict_column_name_to_columnZ[goozali_column_name]
+        value = row.cellValuesByColumnId[column.id]
+        if (job_post_column == "location"):
+            # todo: fix it
+            return Location(text="tel aviv")
 
-        return JobPost()
+        if (job_post_column == "date_posted"):
+            return datetime.fromisoformat(value.replace("Z", "")).date()
+
+        return str(value)
+
+    def map_goozali_response_to_job_post(self, row: GoozaliRow, dict_column_name_to_column) -> JobPost:
+        temp = {}
+        for col in job_post_column_names:
+            value = self.get_value_by_job_post_Id(
+                col, row, dict_column_name_to_column)
+            temp[col] = value
+
+        return JobPost.model_validate(temp)

src/jobspy/scrapers/goozali/__init__.py

@@ -18,7 +18,6 @@ from jobspy.scrapers.goozali.model.GoozaliColumnChoice import GoozaliColumnChoic
 from jobspy.scrapers.site import Site
 
 from ..utils import create_session, create_logger
-from .constants import headers
 from ...jobs import (
     JobPost,
     JobResponse,

src/jobspy/scrapers/goozali/constants.py

@@ -1,59 +1,21 @@
-import json
+job_post_column_to_goozali_column = {
-
+    "date_posted": "Discovered",
-
+    "field": "Field",
-view_ids = ["viwIOzPYaUGxlA0Jd"]
+    "title": "Job Title",
-
+    "job_url": "Position Link",
-headers = {
+    "company_name": "Company",
-    'accept': '*/*',
+    "description": "Requirements",
-    'accept-language': 'en-US,en;q=0.9,he-IL;q=0.8,he;q=0.7',
+    "location": "Location",
-    'priority': 'u=1, i',
+    "company_industry": "Company Industry",
-    'sec-ch-ua': '"Google Chrome";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
+    "id": "Job ID"
-    'sec-ch-ua-mobile': '?0',
-    'sec-ch-ua-platform': '"Windows"',
-    'sec-fetch-dest': 'empty',
-    'sec-fetch-mode': 'cors',
-    'sec-fetch-site': 'same-origin',
-    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
-    'x-airtable-accept-msgpack': 'true',
-    'x-airtable-application-id': 'appwewqLk7iUY4azc',
-    'x-airtable-inter-service-client': 'webClient',
-    'x-airtable-page-load-id': 'pglqAAzFDZEWCEC7s',
-    'x-early-prefetch': 'true',
-    'x-requested-with': 'XMLHttpRequest',
-    'x-time-zone': 'Asia/Jerusalem',
-    'x-user-locale': 'en'
 }
 
-session_id = "lWt/xRLIQas/blkys/2YBYl0priNI7gv85sXXtmkrW+TzbLHR8Vm6iY5RDialmLUYsQgLab8uWZyahWRw0HizxdOXhJxd5FB66H85GpUAX8zZbAZPZdUHvzxjaVa130w14QSXDa8OmsNlpKtiUtZ/DXMTOZ1wYDWC4tVJTKJ171wyKA7C9E="
+job_post_column_names = ["id",
-
+                         "date_posted",
-cookies = {}
+                         "field",
-
+                         "title",
-request_id = "req4q4tKw3woEEWxw&"
+                         "job_url",
-share_id = "shrQBuWjXd0YgPqV6"
+                         "company_name",
-application_id = "appwewqLk7iUY4azc"
+                         "description",
-signature = "be8bd40c133f051f929ebab311c416013f5af0d5acae4264575b88ccf051ee59"
+                         "location",
-
+                         "company_industry"]
-
-def get_access_policy(view_id: str) -> dict[str, str]:
-    access_policy = {
-        "allowedActions": [
-            {"modelClassName": "view", "modelIdSelector": view_id,
-                "action": "readSharedViewData"},
-            {"modelClassName": "view", "modelIdSelector": view_id,
-                "action": "getMetadataForPrinting"},
-            {"modelClassName": "view", "modelIdSelector": view_id,
-                "action": "readSignedAttachmentUrls"},
-            {"modelClassName": "row", "modelIdSelector": f"rows *[displayedInView={view_id}]",
-             "action": "createDocumentPreviewSession"}
-        ],
-        "shareId": share_id,
-        "applicationId": application_id,
-        "generationNumber": 0,
-        "expires": "2025-01-02T00:00:00.000Z",
-        "signature": signature
-    }
-    # Convert to a JSON string
-    return json.dumps(access_policy)
-
-
-stringifiedObjectParams = {"shouldUseNestedResponseFormat": "true"}

src/tests/test_goozali.py

@@ -3,6 +3,7 @@ import os
 from jobspy import scrape_jobs
 import pandas as pd
 
+from jobspy.jobs import JobPost
 from jobspy.scrapers.goozali.GoozaliMapper import GoozaliMapper
 from jobspy.scrapers.goozali.GoozaliScrapperComponent import GoozaliScrapperComponent
 from jobspy.scrapers.goozali.model import GoozaliColumn
@@ -35,13 +36,18 @@ try:
     filtered_rows_by_age_and_column_choice = component.filter_rows_by_hours(
         filtered_rows_by_column_choice, hours_old)
 
-    # Key mapper: Extract 'id' as the key
+    # Key mapper: Extract 'name' as the key
-    def extract_goozali_column_id(column): return column.id if isinstance(
+    def extract_goozali_column_name(column): return column.name if isinstance(
         column, GoozaliColumn) else None
-    dict_column_id_to_column = create_dict_by_key_and_value(
+    dict_column_name_to_column = create_dict_by_key_and_value(
-        response_data.columns, extract_goozali_column_id)
+        response_data.columns, extract_goozali_column_name)
+    response: list[JobPost] = []
+    for row in filtered_rows_by_age_and_column_choice:
+        job_post = mapper.map_goozali_response_to_job_post(
+            row, dict_column_name_to_column)
+        response.append(job_post)
 
-    print("hello heloo")
+    print("kingggggg")
 except FileNotFoundError:
     print("The file was not found.")
 except json.JSONDecodeError: