location filter in search_jobs doesn't work

[tonorgguillamon]

Hi,
when using search_jobs, it seems that the location filter is ignored.

Notice in the example, location: Berlin

/voyagerJobsDashJobCards?decorationId=com.linkedin.voyager.dash.deco.jobs.search.JobSearchCardsCollection-174&count=10&q=jobSearch&query=(origin:JOB_SEARCH_PAGE_QUERY_EXPANSION,keywords:engineer,locationFallback:Berlin,selectedFilters:(timePostedRange:List(r86400)),spellCorrectionEnabled:true)&start=0

The search returns only results from my current country, not even an accurate location such as the city, (i guess taken from the browser cookies).

Anybody knows how this filter actually works?

[space192]

I'm having the same issue did you find any solution ?

[salvatorenitopi]

I found a workaround, locationUnion can be used instead of locationFallback,

I added to the function the location_id parameter and commented out location_name

then I added a new query parameter: query["locationUnion"] = f"(geoId:{location_id})" and commented out the locationFallback one.

You can find a list of IDs here: https://support.captaindata.co/hc/en-us/articles/18071222083485-List-of-GeocodeURN-to-use-in-your-Geography-Parameter

Below in detail what I changed in the function:

def search_jobs(
    self,
    keywords: Optional[str] = None,
    companies: Optional[List[str]] = None,
    experience: Optional[
        List[
            Union[
                Literal["1"],
                Literal["2"],
                Literal["3"],
                Literal["4"],
                Literal["5"],
                Literal["6"],
            ]
        ]
    ] = None,
    job_type: Optional[
        List[
            Union[
                Literal["F"],
                Literal["C"],
                Literal["P"],
                Literal["T"],
                Literal["I"],
                Literal["V"],
                Literal["O"],
            ]
        ]
    ] = None,
    job_title: Optional[List[str]] = None,
    industries: Optional[List[str]] = None,
    # location_name: Optional[str] = None,
    remote: Optional[List[Union[Literal["1"], Literal["2"], Literal["3"]]]] = None,
    listed_at=24 * 60 * 60,
    distance: Optional[int] = None,
    limit=-1,
    offset=0,
    location_id="102299470",
    **kwargs,
) -> List[Dict]:

    count = Linkedin._MAX_SEARCH_COUNT
    if limit is None:
        limit = -1

    query: Dict[str, Union[str, Dict[str, str]]] = {
        "origin": "JOB_SEARCH_PAGE_QUERY_EXPANSION"
    }
    if keywords:
        query["keywords"] = "KEYWORD_PLACEHOLDER"
    # if location_name:
    #    query["locationFallback"] = "LOCATION_PLACEHOLDER"

    # In selectedFilters()
    query["selectedFilters"] = {}
    if companies:
        query["selectedFilters"]["company"] = f"List({','.join(companies)})"
    if experience:
        query["selectedFilters"]["experience"] = f"List({','.join(experience)})"
    if job_type:
        query["selectedFilters"]["jobType"] = f"List({','.join(job_type)})"
    if job_title:
        query["selectedFilters"]["title"] = f"List({','.join(job_title)})"
    if industries:
        query["selectedFilters"]["industry"] = f"List({','.join(industries)})"
    if distance:
        query["selectedFilters"]["distance"] = f"List({distance})"
    if remote:
        query["selectedFilters"]["workplaceType"] = f"List({','.join(remote)})"

    query["selectedFilters"]["timePostedRange"] = f"List(r{listed_at})"
    query["spellCorrectionEnabled"] = "true"
    query["locationUnion"] = f"(geoId:{location_id})"

Then you call the function as follows:

response = linkedin_client.search_jobs(
    keywords="myjob".replace(" ", "%20"),
    location_id="102299470",
    remote="2",
    listed_at=24*60*60,
    limit=-1,
    offset=0
)

It ended up generating this query:

(origin:JOB_SEARCH_PAGE_QUERY_EXPANSION,keywords:myjob,selectedFilters:(workplaceType:List(2),timePostedRange:List(r86400)),spellCorrectionEnabled:true,locationUnion:(geoId:102299470))

I hope this can help you

[tonorgguillamon]

yep, that´s the workaround I found. It is just very painful to go id by id mapping the location. By countries might be feasible, but if you wanna go more detailed, like cities,..give it up.

i tried to figure out which function Linkedin is using to relate location with geoId, but no success