fix job type search (#106)

* fix(ziprecruiter): pagination

* chore: version

README.md

@@ -29,18 +29,20 @@ _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/)
 ### Usage
 
 ```python
+import csv
 from jobspy import scrape_jobs
 
 jobs = scrape_jobs(
     site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor"],
     search_term="software engineer",
     location="Dallas, TX",
-    results_wanted=10,
+    results_wanted=20,
+    hours_old=72, # (only linkedin is hour specific, others round up to days old)
     country_indeed='USA'  # only needed for indeed / glassdoor
 )
 print(f"Found {len(jobs)} jobs")
 print(jobs.head())
-jobs.to_csv("jobs.csv", index=False) # to_xlsx
+jobs.to_csv("jobs.csv", quoting=csv.QUOTE_NONNUMERIC, escapechar="\\", index=False) # to_xlsx
 ```
 
 ### Output
@@ -67,11 +69,13 @@ Optional
 ├── job_type (enum): fulltime, parttime, internship, contract
 ├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
 ├── is_remote (bool)
-├── full_description (bool): fetches full description for Indeed / LinkedIn (much slower)
+├── full_description (bool): fetches full description for LinkedIn (slower)
 ├── results_wanted (int): number of job results to retrieve for each site specified in 'site_type'
 ├── easy_apply (bool): filters for jobs that are hosted on the job board site
+├── linkedin_company_ids (list[int): searches for linkedin jobs with specific company ids
 ├── country_indeed (enum): filters the country on Indeed (see below for correct spelling)
 ├── offset (num): starts the search from an offset (e.g. 25 will start the search from the 25th result)
+├── hours_old (int): filters jobs by the number of hours since the job was posted (all but LinkedIn rounds up to next day)
 ```
 
 ### JobPost Schema

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.39"
+version = "1.1.44"
 description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/JobSpy"

src/jobspy/__init__.py

@@ -1,7 +1,6 @@
 import pandas as pd
-import concurrent.futures
+from typing import Tuple
-from concurrent.futures import ThreadPoolExecutor
+from concurrent.futures import ThreadPoolExecutor, as_completed
-from typing import Tuple, Optional
 
 from .jobs import JobType, Location
 from .scrapers.indeed import IndeedScraper
@@ -29,19 +28,22 @@ def _map_str_to_site(site_name: str) -> Site:
 
 
 def scrape_jobs(
-    site_name: str | list[str] | Site | list[Site],
+    site_name: str | list[str] | Site | list[Site] | None = None,
-    search_term: str,
+    search_term: str | None = None,
-    location: str = "",
+    location: str | None = None,
-    distance: int = None,
+    distance: int | None = None,
     is_remote: bool = False,
-    job_type: str = None,
+    job_type: str | None = None,
-    easy_apply: bool = False,  # linkedin
+    easy_apply: bool | None = None,
     results_wanted: int = 15,
     country_indeed: str = "usa",
     hyperlinks: bool = False,
-    proxy: Optional[str] = None,
+    proxy: str | None = None,
-    full_description: Optional[bool] = False,
+    full_description: bool | None = False,
-    offset: Optional[int] = 0,
+    linkedin_company_ids: list[int] | None = None,
+    offset: int | None = 0,
+    hours_old: int = None,
+    **kwargs,
 ) -> pd.DataFrame:
     """
     Simultaneously scrapes job data from multiple job sites.
@@ -56,18 +58,23 @@ def scrape_jobs(
 
     job_type = get_enum_from_value(job_type) if job_type else None
 
-    if type(site_name) == str:
+    def get_site_type():
-        site_type = [_map_str_to_site(site_name)]
+        site_types = list(Site)
-    else:  #: if type(site_name) == list
+        if isinstance(site_name, str):
-        site_type = [
+            site_types = [_map_str_to_site(site_name)]
-            _map_str_to_site(site) if type(site) == str else site_name
+        elif isinstance(site_name, Site):
-            for site in site_name
+            site_types = [site_name]
-        ]
+        elif isinstance(site_name, list):
+            site_types = [
+                _map_str_to_site(site) if isinstance(site, str) else site
+                for site in site_name
+            ]
+        return site_types
 
     country_enum = Country.from_string(country_indeed)
 
     scraper_input = ScraperInput(
-        site_type=site_type,
+        site_type=get_site_type(),
         country=country_enum,
         search_term=search_term,
         location=location,
@@ -77,7 +84,9 @@ def scrape_jobs(
         easy_apply=easy_apply,
         full_description=full_description,
         results_wanted=results_wanted,
+        linkedin_company_ids=linkedin_company_ids,
         offset=offset,
+        hours_old=hours_old
     )
 
     def scrape_site(site: Site) -> Tuple[str, JobResponse]:
@@ -112,7 +121,7 @@ def scrape_jobs(
             executor.submit(worker, site): site for site in scraper_input.site_type
         }
 
-        for future in concurrent.futures.as_completed(future_to_site):
+        for future in as_completed(future_to_site):
             site_value, scraped_data = future.result()
             site_to_jobs_dict[site_value] = scraped_data
 
@@ -183,4 +192,4 @@ def scrape_jobs(
     else:
         jobs_formatted_df = pd.DataFrame()
 
-    return jobs_formatted_df
+    return jobs_formatted_df.sort_values(by=['site', 'date_posted'], ascending=[True, False])

src/jobspy/jobs/__init__.py

@@ -193,13 +193,20 @@ class CompensationInterval(Enum):
 
     @classmethod
     def get_interval(cls, pay_period):
-        return cls[pay_period].value if pay_period in cls.__members__ else None
+        interval_mapping = {
+            "YEAR": cls.YEARLY,
+            "HOUR": cls.HOURLY,
+        }
+        if pay_period in interval_mapping:
+            return interval_mapping[pay_period].value
+        else:
+            return cls[pay_period].value if pay_period in cls.__members__ else None
 
 
 class Compensation(BaseModel):
     interval: Optional[CompensationInterval] = None
-    min_amount: int | None = None
+    min_amount: float | None = None
-    max_amount: int | None = None
+    max_amount: float | None = None
     currency: Optional[str] = "USD"
 
 

src/jobspy/scrapers/__init__.py

@@ -1,5 +1,4 @@
 from ..jobs import Enum, BaseModel, JobType, JobResponse, Country
-from typing import List, Optional, Any
 
 
 class Site(Enum):
@@ -10,25 +9,26 @@ class Site(Enum):
 
 
 class ScraperInput(BaseModel):
-    site_type: List[Site]
+    site_type: list[Site]
-    search_term: str
+    search_term: str | None = None
 
-    location: str = None
+    location: str | None = None
-    country: Optional[Country] = Country.USA
+    country: Country | None = Country.USA
-    distance: Optional[int] = None
+    distance: int | None = None
     is_remote: bool = False
-    job_type: Optional[JobType] = None
+    job_type: JobType | None = None
-    easy_apply: bool = None  # linkedin
+    easy_apply: bool | None = None
     full_description: bool = False
     offset: int = 0
+    linkedin_company_ids: list[int] | None = None
 
     results_wanted: int = 15
+    hours_old: int | None = None
 
 
 class Scraper:
-    def __init__(self, site: Site, proxy: Optional[List[str]] = None):
+    def __init__(self, site: Site, proxy: list[str] | None = None):
         self.site = site
         self.proxy = (lambda p: {"http": p, "https": p} if p else None)(proxy)
 
-    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse: ...
-        ...

src/jobspy/scrapers/glassdoor/__init__.py

@@ -6,7 +6,6 @@ This module contains routines to scrape Glassdoor.
 """
 import json
 import requests
-from bs4 import BeautifulSoup
 from typing import Optional
 from datetime import datetime, timedelta
 from concurrent.futures import ThreadPoolExecutor, as_completed
@@ -14,7 +13,7 @@ from ..utils import count_urgent_words, extract_emails_from_text
 
 from .. import Scraper, ScraperInput, Site
 from ..exceptions import GlassdoorException
-from ..utils import create_session, modify_and_get_description
+from ..utils import create_session
 from ...jobs import (
     JobPost,
     Compensation,
@@ -35,6 +34,7 @@ class GlassdoorScraper(Scraper):
 
         self.url = None
         self.country = None
+        self.session = None
         self.jobs_per_page = 30
         self.seen_urls = set()
 
@@ -53,8 +53,7 @@ class GlassdoorScraper(Scraper):
             payload = self.add_payload(
                 scraper_input, location_id, location_type, page_num, cursor
             )
-            session = create_session(self.proxy, is_tls=False, has_retry=True)
+            response = self.session.post(
-            response = session.post(
                 f"{self.url}/graph", headers=self.headers(), timeout=10, data=payload
             )
             if response.status_code != 200:
@@ -73,7 +72,6 @@ class GlassdoorScraper(Scraper):
         with ThreadPoolExecutor(max_workers=self.jobs_per_page) as executor:
             future_to_job_data = {executor.submit(self.process_job, job): job for job in jobs_data}
             for future in as_completed(future_to_job_data):
-                job_data = future_to_job_data[future]
                 try:
                     job_post = future.result()
                     if job_post:
@@ -100,7 +98,7 @@ class GlassdoorScraper(Scraper):
         location_type = job["header"].get("locationType", "")
         age_in_days = job["header"].get("ageInDays")
         is_remote, location = False, None
-        date_posted = (datetime.now() - timedelta(days=age_in_days)).date() if age_in_days else None
+        date_posted = (datetime.now() - timedelta(days=age_in_days)).date() if age_in_days is not None else None
 
         if location_type == "S":
             is_remote = True
@@ -111,7 +109,7 @@ class GlassdoorScraper(Scraper):
 
         try:
             description = self.fetch_job_description(job_id)
-        except Exception as e :
+        except:
             description = None
 
         job_post = JobPost(
@@ -145,6 +143,8 @@ class GlassdoorScraper(Scraper):
         all_jobs: list[JobPost] = []
         cursor = None
         max_pages = 30
+        self.session = create_session(self.proxy, is_tls=False, has_retry=True)
+        self.session.get(self.url)
 
         try:
             for page in range(
@@ -201,8 +201,7 @@ class GlassdoorScraper(Scraper):
             return None
         data = response.json()[0]
         desc = data['data']['jobview']['job']['description']
-        soup = BeautifulSoup(desc, 'html.parser')
+        return desc
-        return modify_and_get_description(soup)
 
     @staticmethod
     def parse_compensation(data: dict) -> Optional[Compensation]:
@@ -246,6 +245,8 @@ class GlassdoorScraper(Scraper):
             location_type = "CITY"
         elif location_type == "S":
             location_type = "STATE"
+        elif location_type == 'N':
+            location_type = "COUNTRY"
         return int(items[0]["locationId"]), location_type
 
     @staticmethod
@@ -256,11 +257,18 @@ class GlassdoorScraper(Scraper):
         page_num: int,
         cursor: str | None = None,
     ) -> str:
+        # `fromage` is the posting time filter in days
+        fromage = max(scraper_input.hours_old // 24, 1) if scraper_input.hours_old else None
+        filter_params = []
+        if scraper_input.easy_apply:
+            filter_params.append({"filterKey": "applicationType", "values": "1"})
+        if fromage:
+            filter_params.append({"filterKey": "fromAge", "values": str(fromage)})
         payload = {
             "operationName": "JobSearchResultsQuery",
             "variables": {
                 "excludeJobListingIds": [],
-                "filterParams": [{"filterKey": "applicationType", "values": "1"}] if scraper_input.easy_apply else [],
+                "filterParams": filter_params,
                 "keyword": scraper_input.search_term,
                 "numJobsToShow": 30,
                 "locationType": location_type,
@@ -268,22 +276,180 @@ class GlassdoorScraper(Scraper):
                 "parameterUrlInput": f"IL.0,12_I{location_type}{location_id}",
                 "pageNumber": page_num,
                 "pageCursor": cursor,
+                "fromage": fromage,
+                "sort": "date"
             },
-            "query": "query JobSearchResultsQuery($excludeJobListingIds: [Long!], $keyword: String, $locationId: Int, $locationType: LocationTypeEnum, $numJobsToShow: Int!, $pageCursor: String, $pageNumber: Int, $filterParams: [FilterParams], $originalPageUrl: String, $seoFriendlyUrlInput: String, $parameterUrlInput: String, $seoUrl: Boolean) {\n  jobListings(\n    contextHolder: {searchParams: {excludeJobListingIds: $excludeJobListingIds, keyword: $keyword, locationId: $locationId, locationType: $locationType, numPerPage: $numJobsToShow, pageCursor: $pageCursor, pageNumber: $pageNumber, filterParams: $filterParams, originalPageUrl: $originalPageUrl, seoFriendlyUrlInput: $seoFriendlyUrlInput, parameterUrlInput: $parameterUrlInput, seoUrl: $seoUrl, searchType: SR}}\n  ) {\n    companyFilterOptions {\n      id\n      shortName\n      __typename\n    }\n    filterOptions\n    indeedCtk\n    jobListings {\n      ...JobView\n      __typename\n    }\n    jobListingSeoLinks {\n      linkItems {\n        position\n        url\n        __typename\n      }\n      __typename\n    }\n    jobSearchTrackingKey\n    jobsPageSeoData {\n      pageMetaDescription\n      pageTitle\n      __typename\n    }\n    paginationCursors {\n      cursor\n      pageNumber\n      __typename\n    }\n    indexablePageForSeo\n    searchResultsMetadata {\n      searchCriteria {\n        implicitLocation {\n          id\n          localizedDisplayName\n          type\n          __typename\n        }\n        keyword\n        location {\n          id\n          shortName\n          localizedShortName\n          localizedDisplayName\n          type\n          __typename\n        }\n        __typename\n      }\n      footerVO {\n        countryMenu {\n          childNavigationLinks {\n            id\n            link\n            textKey\n            __typename\n          }\n          __typename\n        }\n        __typename\n      }\n      helpCenterDomain\n      helpCenterLocale\n      jobAlert {\n        jobAlertExists\n        __typename\n      }\n      jobSerpFaq {\n        questions {\n          answer\n          question\n          __typename\n        }\n        __typename\n      }\n      jobSerpJobOutlook {\n        occupation\n        paragraph\n        __typename\n      }\n      showMachineReadableJobs\n      __typename\n    }\n    serpSeoLinksVO {\n      relatedJobTitlesResults\n      searchedJobTitle\n      searchedKeyword\n      searchedLocationIdAsString\n      searchedLocationSeoName\n      searchedLocationType\n      topCityIdsToNameResults {\n        key\n        value\n        __typename\n      }\n      topEmployerIdsToNameResults {\n        key\n        value\n        __typename\n      }\n      topEmployerNameResults\n      topOccupationResults\n      __typename\n    }\n    totalJobsCount\n    __typename\n  }\n}\n\nfragment JobView on JobListingSearchResult {\n  jobview {\n    header {\n      adOrderId\n      advertiserType\n      adOrderSponsorshipLevel\n      ageInDays\n      divisionEmployerName\n      easyApply\n      employer {\n        id\n        name\n        shortName\n        __typename\n      }\n      employerNameFromSearch\n      goc\n      gocConfidence\n      gocId\n      jobCountryId\n      jobLink\n      jobResultTrackingKey\n      jobTitleText\n      locationName\n      locationType\n      locId\n      needsCommission\n      payCurrency\n      payPeriod\n      payPeriodAdjustedPay {\n        p10\n        p50\n        p90\n        __typename\n      }\n      rating\n      salarySource\n      savedJobId\n      sponsored\n      __typename\n    }\n    job {\n      descriptionFragments\n      importConfigId\n      jobTitleId\n      jobTitleText\n      listingId\n      __typename\n    }\n    jobListingAdminDetails {\n      cpcVal\n      importConfigId\n      jobListingId\n      jobSourceId\n      userEligibleForAdminJobDetails\n      __typename\n    }\n    overview {\n      shortName\n      squareLogoUrl\n      __typename\n    }\n    __typename\n  }\n  __typename\n}\n",
+            "query": """
+            query JobSearchResultsQuery(
+                $excludeJobListingIds: [Long!], 
+                $keyword: String, 
+                $locationId: Int, 
+                $locationType: LocationTypeEnum, 
+                $numJobsToShow: Int!, 
+                $pageCursor: String, 
+                $pageNumber: Int, 
+                $filterParams: [FilterParams], 
+                $originalPageUrl: String, 
+                $seoFriendlyUrlInput: String, 
+                $parameterUrlInput: String, 
+                $seoUrl: Boolean
+            ) {
+                jobListings(
+                    contextHolder: {
+                        searchParams: {
+                            excludeJobListingIds: $excludeJobListingIds, 
+                            keyword: $keyword, 
+                            locationId: $locationId, 
+                            locationType: $locationType, 
+                            numPerPage: $numJobsToShow, 
+                            pageCursor: $pageCursor, 
+                            pageNumber: $pageNumber, 
+                            filterParams: $filterParams, 
+                            originalPageUrl: $originalPageUrl, 
+                            seoFriendlyUrlInput: $seoFriendlyUrlInput, 
+                            parameterUrlInput: $parameterUrlInput, 
+                            seoUrl: $seoUrl, 
+                            searchType: SR
+                        }
+                    }
+                ) {
+                    companyFilterOptions {
+                        id
+                        shortName
+                        __typename
+                    }
+                    filterOptions
+                    indeedCtk
+                    jobListings {
+                        ...JobView
+                        __typename
+                    }
+                    jobListingSeoLinks {
+                        linkItems {
+                            position
+                            url
+                            __typename
+                        }
+                        __typename
+                    }
+                    jobSearchTrackingKey
+                    jobsPageSeoData {
+                        pageMetaDescription
+                        pageTitle
+                        __typename
+                    }
+                    paginationCursors {
+                        cursor
+                        pageNumber
+                        __typename
+                    }
+                    indexablePageForSeo
+                    searchResultsMetadata {
+                        searchCriteria {
+                            implicitLocation {
+                                id
+                                localizedDisplayName
+                                type
+                                __typename
+                            }
+                            keyword
+                            location {
+                                id
+                                shortName
+                                localizedShortName
+                                localizedDisplayName
+                                type
+                                __typename
+                            }
+                            __typename
+                        }
+                        helpCenterDomain
+                        helpCenterLocale
+                        jobSerpJobOutlook {
+                            occupation
+                            paragraph
+                            __typename
+                        }
+                        showMachineReadableJobs
+                        __typename
+                    }
+                    totalJobsCount
+                    __typename
+                }
+            }
+
+            fragment JobView on JobListingSearchResult {
+                jobview {
+                    header {
+                        adOrderId
+                        advertiserType
+                        adOrderSponsorshipLevel
+                        ageInDays
+                        divisionEmployerName
+                        easyApply
+                        employer {
+                            id
+                            name
+                            shortName
+                            __typename
+                        }
+                        employerNameFromSearch
+                        goc
+                        gocConfidence
+                        gocId
+                        jobCountryId
+                        jobLink
+                        jobResultTrackingKey
+                        jobTitleText
+                        locationName
+                        locationType
+                        locId
+                        needsCommission
+                        payCurrency
+                        payPeriod
+                        payPeriodAdjustedPay {
+                            p10
+                            p50
+                            p90
+                            __typename
+                        }
+                        rating
+                        salarySource
+                        savedJobId
+                        sponsored
+                        __typename
+                    }
+                    job {
+                        description
+                        importConfigId
+                        jobTitleId
+                        jobTitleText
+                        listingId
+                        __typename
+                    }
+                    jobListingAdminDetails {
+                        cpcVal
+                        importConfigId
+                        jobListingId
+                        jobSourceId
+                        userEligibleForAdminJobDetails
+                        __typename
+                    }
+                    overview {
+                        shortName
+                        squareLogoUrl
+                        __typename
+                    }
+                    __typename
+                }
+                __typename
+            }
+            """
         }
 
-        job_type_filters = {
+        if scraper_input.job_type:
-            JobType.FULL_TIME: "fulltime",
-            JobType.PART_TIME: "parttime",
-            JobType.CONTRACT: "contract",
-            JobType.INTERNSHIP: "internship",
-            JobType.TEMPORARY: "temporary",
-        }
-
-        if scraper_input.job_type in job_type_filters:
-            filter_value = job_type_filters[scraper_input.job_type]
             payload["variables"]["filterParams"].append(
-                {"filterKey": "jobType", "values": filter_value}
+                {"filterKey": "jobType", "values": scraper_input.job_type.value[0]}
             )
         return json.dumps([payload])
 
@@ -319,7 +485,6 @@ class GlassdoorScraper(Scraper):
             "apollographql-client-name": "job-search-next",
             "apollographql-client-version": "4.65.5",
             "content-type": "application/json",
-            "cookie": 'gdId=91e2dfc4-c8b5-4fa7-83d0-11512b80262c; G_ENABLED_IDPS=google; trs=https%3A%2F%2Fwww.redhat.com%2F:referral:referral:2023-07-05+09%3A50%3A14.862:undefined:undefined; g_state={"i_p":1688587331651,"i_l":1}; _cfuvid=.7llazxhYFZWi6EISSPdVjtqF0NMVwzxr_E.cB1jgLs-1697828392979-0-604800000; GSESSIONID=undefined; JSESSIONID=F03DD1B5EE02DB6D842FE42B142F88F3; cass=1; jobsClicked=true; indeedCtk=1hd77b301k79i801; asst=1697829114.2; G_AUTHUSER_H=0; uc=8013A8318C98C517FE6DD0024636DFDEF978FC33266D93A2FAFEF364EACA608949D8B8FA2DC243D62DE271D733EB189D809ABE5B08D7B1AE865D217BD4EEBB97C282F5DA5FEFE79C937E3F6110B2A3A0ADBBA3B4B6DF5A996FEE00516100A65FCB11DA26817BE8D1C1BF6CFE36B5B68A3FDC2CFEC83AB797F7841FBB157C202332FC7E077B56BD39B167BDF3D9866E3B; AWSALB=zxc/Yk1nbWXXT6HjNyn3H4h4950ckVsFV/zOrq5LSoChYLE1qV+hDI8Axi3fUa9rlskndcO0M+Fw+ZnJ+AQ2afBFpyOd1acouLMYgkbEpqpQaWhY6/Gv4QH1zBcJ; AWSALBCORS=zxc/Yk1nbWXXT6HjNyn3H4h4950ckVsFV/zOrq5LSoChYLE1qV+hDI8Axi3fUa9rlskndcO0M+Fw+ZnJ+AQ2afBFpyOd1acouLMYgkbEpqpQaWhY6/Gv4QH1zBcJ; gdsid=1697828393025:1697830776351:668396EDB9E6A832022D34414128093D; at=HkH8Hnqi9uaMC7eu0okqyIwqp07ht9hBvE1_St7E_hRqPvkO9pUeJ1Jcpds4F3g6LL5ADaCNlxrPn0o6DumGMfog8qI1-zxaV_jpiFs3pugntw6WpVyYWdfioIZ1IDKupyteeLQEM1AO4zhGjY_rPZynpsiZBPO_B1au94sKv64rv23yvP56OiWKKfI-8_9hhLACEwWvM-Az7X-4aE2QdFt93VJbXbbGVf07bdDZfimsIkTtgJCLSRhU1V0kEM1Efyu66vo3m77gFFaMW7lxyYnb36I5PdDtEXBm3aL-zR7-qa5ywd94ISEivgqQOA4FPItNhqIlX4XrfD1lxVz6rfPaoTIDi4DI6UMCUjwyPsuv8mn0rYqDfRnmJpZ97fJ5AnhrknAd_6ZWN5v1OrxJczHzcXd8LO820QPoqxzzG13bmSTXLwGSxMUCtSrVsq05hicimQ3jpRt0c1dA4OkTNqF7_770B9JfcHcM8cr8-C4IL56dnOjr9KBGfN1Q2IvZM2cOBRbV7okiNOzKVZ3qJ24AE34WA2F3U6Whiu6H8nIuGG5hSNkVygY6CtglNZfFF9p8pJAZm79PngrrBv-CXFBZmhYLFo46lmFetDkiJ6mirtez4tKpzTIYjIp4_JAkiZFwbLJ2QGH4mK8kyyW0lZiX1DTuQec50N_5wvRo0Gt7nlKxzLsApMnaNhuQeH5ygh_pa381ORo9mQGi0EYF9zk00pa2--z4PtjfQ8KFq36GgpxKy5-o4qgqygZj8F01L8r-FiX2G4C7PREMIpAyHX2A4-_JxA1IS2j12EyqKTLqE9VcP06qm2Z-YuIW3ctmpMxy5G9_KiEiGv17weizhSFnl6SbpAEY-2VSmQ5V6jm3hoMp2jemkuGCRkZeFstLDEPxlzFN7WM; __cf_bm=zGaVjIJw4irf40_7UVw54B6Ohm271RUX4Tc8KVScrbs-1697830777-0-AYv2GnKTnnCU+cY9xHbJunO0DwlLDO6SIBnC/s/qldpKsGK0rRAjD6y8lbyATT/KlS7g29OZaN4fbd0lrJg0KmWbIybZIzfWVLHSYePVuOhu; asst=1697829114.2; at=dFhXf64wsf2TlnWy41xLs7skJkuxgKToEGcjGtDfUvW4oEAJ4tTIR5dKQ8wbwT75aIaGgdCfvcb-da7vwrCGWscCncmfLFQpJ9l-LLwoRfk-pMsxHhd77wvf-W7I0HSm7-Q5lQJqI9WyNGRxOa-RpzBTf4L8_Et4-3FzjPaAoYY5pY1FhuwXbN5asGOAMW-p8cjpbfn3PumlIYuckguWnjrcY2F31YJ_1noeoHM9tCGpymANbqGXRkG6aXY7yCfVXtdgZU1K5SMeaSPZIuF_iLUxjc_corzpNiH6qq7BIAmh-e5Aa-g7cwpZcln1fmwTVw4uTMZf1eLIMTa9WzgqZNkvG-sGaq_XxKA_Wai6xTTkOHfRgm4632Ba2963wdJvkGmUUa3tb_L4_wTgk3eFnHp5JhghLfT2Pe3KidP-yX__vx8JOsqe3fndCkKXgVz7xQKe1Dur-sMNlGwi4LXfguTT2YUI8C5Miq3pj2IHc7dC97eyyAiAM4HvyGWfaXWZcei6oIGrOwMvYgy0AcwFry6SIP2SxLT5TrxinRRuem1r1IcOTJsMJyUPp1QsZ7bOyq9G_0060B4CPyovw5523hEuqLTM-R5e5yavY6C_1DHUyE15C3mrh7kdvmlGZeflnHqkFTEKwwOftm-Mv-CKD5Db9ABFGNxKB2FH7nDH67hfOvm4tGNMzceBPKYJ3wciTt9jK3wy39_7cOYVywfrZ-oLhw_XtsbGSSeGn3HytrfgSADAh2sT0Gg6eCC9Xy1vh-Za337SVLUDXZ73W2xJxxUHBkFzZs8L_Xndo5DsbpWhVs9IYUGyraJdqB3SLgDbAppIBCJl4fx6_DG8-xOQPBvuFMlTROe1JVdHOzXI1GElwFDTuH1pjkg4I2G0NhAbE06Y-1illQE; gdsid=1697828393025:1697831731408:99C30D94108AC3030D61C736DDCDF11C',
             "gd-csrf-token": "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok",
             "origin": "https://www.glassdoor.com",
             "referer": "https://www.glassdoor.com/",

src/jobspy/scrapers/indeed/__init__.py

@@ -6,12 +6,11 @@ This module contains routines to scrape Indeed.
 """
 import re
 import math
-import io
 import json
+import requests
 from typing import Any
 from datetime import datetime
 
-import urllib.parse
 from bs4 import BeautifulSoup
 from bs4.element import Tag
 from concurrent.futures import ThreadPoolExecutor, Future
@@ -22,7 +21,7 @@ from ..utils import (
     extract_emails_from_text,
     create_session,
     get_enum_from_job_type,
-    modify_and_get_description
+    logger
 )
 from ...jobs import (
     JobPost,
@@ -50,13 +49,14 @@ class IndeedScraper(Scraper):
 
     def scrape_page(
         self, scraper_input: ScraperInput, page: int
-    ) -> tuple[list[JobPost], int]:
+    ) -> list[JobPost]:
         """
         Scrapes a page of Indeed for jobs with scraper_input criteria
         :param scraper_input:
         :param page:
         :return: jobs found on page, total number of jobs found for search
         """
+        job_list = []
         self.country = scraper_input.country
         domain = self.country.indeed_domain_value
         self.url = f"https://{domain}.indeed.com"
@@ -76,17 +76,18 @@ class IndeedScraper(Scraper):
                 )
         except Exception as e:
             if "Proxy responded with" in str(e):
-                raise IndeedException("bad proxy")
+                logger.error(f'Indeed: Bad proxy')
-            raise IndeedException(str(e))
+            else:
+                logger.error(f'Indeed: {str(e)}')
+            return job_list
 
         soup = BeautifulSoup(response.content, "html.parser")
         if "did not match any jobs" in response.text:
-            raise IndeedException("Parsing exception: Search did not match any jobs")
+            return job_list
 
         jobs = IndeedScraper.parse_jobs(
             soup
         )  #: can raise exception, handled by main scrape function
-        total_num_jobs = IndeedScraper.total_jobs(soup)
 
         if (
             not jobs.get("metaData", {})
@@ -95,75 +96,56 @@ class IndeedScraper(Scraper):
         ):
             raise IndeedException("No jobs found.")
 
-        def process_job(job: dict) -> JobPost | None:
+        def process_job(job: dict, job_detailed: dict) -> JobPost | None:
             job_url = f'{self.url}/m/jobs/viewjob?jk={job["jobkey"]}'
             job_url_client = f'{self.url}/viewjob?jk={job["jobkey"]}'
             if job_url in self.seen_urls:
                 return None
+            self.seen_urls.add(job_url)
+            description = job_detailed['description']['html']
 
-            extracted_salary = job.get("extractedSalary")
-            compensation = None
-            if extracted_salary:
-                salary_snippet = job.get("salarySnippet")
-                currency = salary_snippet.get("currency") if salary_snippet else None
-                interval = (extracted_salary.get("type"),)
-                if isinstance(interval, tuple):
-                    interval = interval[0]
-
-                interval = interval.upper()
-                if interval in CompensationInterval.__members__:
-                    compensation = Compensation(
-                        interval=CompensationInterval[interval],
-                        min_amount=int(extracted_salary.get("min")),
-                        max_amount=int(extracted_salary.get("max")),
-                        currency=currency,
-                    )
 
             job_type = IndeedScraper.get_job_type(job)
             timestamp_seconds = job["pubDate"] / 1000
             date_posted = datetime.fromtimestamp(timestamp_seconds)
             date_posted = date_posted.strftime("%Y-%m-%d")
 
-            description = self.get_description(job_url) if scraper_input.full_description else None
-
-            with io.StringIO(job["snippet"]) as f:
-                soup_io = BeautifulSoup(f, "html.parser")
-                li_elements = soup_io.find_all("li")
-                if description is None and li_elements:
-                    description = " ".join(li.text for li in li_elements)
-
             job_post = JobPost(
                 title=job["normTitle"],
                 description=description,
                 company_name=job["company"],
-                company_url=self.url + job["companyOverviewLink"] if "companyOverviewLink" in job else None,
+                company_url=f"{self.url}{job_detailed['employer']['relativeCompanyPageUrl']}" if job_detailed['employer'] else None,
                 location=Location(
                     city=job.get("jobLocationCity"),
                     state=job.get("jobLocationState"),
                     country=self.country,
                 ),
                 job_type=job_type,
-                compensation=compensation,
+                compensation=self.get_compensation(job, job_detailed),
                 date_posted=date_posted,
                 job_url=job_url_client,
                 emails=extract_emails_from_text(description) if description else None,
                 num_urgent_words=count_urgent_words(description)
                 if description
                 else None,
-                is_remote=self.is_remote_job(job),
+                is_remote=IndeedScraper.is_job_remote(job, job_detailed, description)
+
             )
             return job_post
 
-        workers = 10 if scraper_input.full_description else 10  # possibly lessen 10 when fetching desc based on feedback
+        workers = 10
         jobs = jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]
+        job_keys = [job['jobkey'] for job in jobs]
+        jobs_detailed = self.get_job_details(job_keys)
+
         with ThreadPoolExecutor(max_workers=workers) as executor:
             job_results: list[Future] = [
-                executor.submit(process_job, job) for job in jobs
+                executor.submit(process_job, job, job_detailed['job']) for job, job_detailed in zip(jobs, jobs_detailed)
             ]
 
         job_list = [result.result() for result in job_results if result.result()]
 
-        return job_list, total_num_jobs
+        return job_list
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
         """
@@ -171,76 +153,36 @@ class IndeedScraper(Scraper):
         :param scraper_input:
         :return: job_response
         """
-        pages_to_process = (
+        job_list = self.scrape_page(scraper_input, 0)
-            math.ceil(scraper_input.results_wanted / self.jobs_per_page) - 1
+        pages_processed = 1
-        )
 
-        #: get first page to initialize session
+        while len(self.seen_urls) < scraper_input.results_wanted:
-        job_list, total_results = self.scrape_page(scraper_input, 0)
+            pages_to_process = math.ceil((scraper_input.results_wanted - len(self.seen_urls)) / self.jobs_per_page)
+            new_jobs = False
 
-        with ThreadPoolExecutor(max_workers=10) as executor:
+            with ThreadPoolExecutor(max_workers=10) as executor:
-            futures: list[Future] = [
+                futures: list[Future] = [
-                executor.submit(self.scrape_page, scraper_input, page)
+                    executor.submit(self.scrape_page, scraper_input, page + pages_processed)
-                for page in range(1, pages_to_process + 1)
+                    for page in range(pages_to_process)
-            ]
+                ]
 
-            for future in futures:
+                for future in futures:
-                jobs, _ = future.result()
+                    jobs = future.result()
+                    if jobs:
+                        job_list += jobs
+                        new_jobs = True
+                    if len(self.seen_urls) >= scraper_input.results_wanted:
+                        break
 
-                job_list += jobs
+            pages_processed += pages_to_process
+            if not new_jobs:
+                break
 
-        if len(job_list) > scraper_input.results_wanted:
-            job_list = job_list[: scraper_input.results_wanted]
 
-        job_response = JobResponse(
+        if len(self.seen_urls) > scraper_input.results_wanted:
-            jobs=job_list,
+            job_list = job_list[:scraper_input.results_wanted]
-            total_results=total_results,
-        )
-        return job_response
 
-    def get_description(self, job_page_url: str) -> str | None:
+        return JobResponse(jobs=job_list)
-        """
-        Retrieves job description by going to the job page url
-        :param job_page_url:
-        :return: description
-        """
-        parsed_url = urllib.parse.urlparse(job_page_url)
-        params = urllib.parse.parse_qs(parsed_url.query)
-        jk_value = params.get("jk", [None])[0]
-        formatted_url = f"{self.url}/m/viewjob?jk={jk_value}&spa=1"
-        session = create_session(self.proxy)
-
-        try:
-            response = session.get(
-                formatted_url,
-                headers=self.get_headers(),
-                allow_redirects=True,
-                timeout_seconds=5,
-            )
-        except Exception as e:
-            return None
-
-        if response.status_code not in range(200, 400):
-            return None
-
-        try:
-            soup = BeautifulSoup(response.text, 'html.parser')
-            script_tags = soup.find_all('script')
-
-            job_description = ''
-            for tag in script_tags:
-                if 'window._initialData' in tag.text:
-                    json_str = tag.text
-                    json_str = json_str.split('window._initialData=')[1]
-                    json_str = json_str.rsplit(';', 1)[0]
-                    data = json.loads(json_str)
-                    job_description = data["jobInfoWrapperModel"]["jobInfoModel"]["sanitizedJobDescription"]
-                    break
-        except (KeyError, TypeError, IndexError):
-            return None
-
-        soup = BeautifulSoup(job_description, "html.parser")
-        return modify_and_get_description(soup)
 
     @staticmethod
     def get_job_type(job: dict) -> list[JobType] | None:
@@ -261,6 +203,44 @@ class IndeedScraper(Scraper):
                             job_types.append(job_type)
         return job_types
 
+    @staticmethod
+    def get_compensation(job: dict, job_detailed: dict) -> Compensation:
+        """
+        Parses the job to get
+        :param job:
+        :param job_detailed:
+        :return: compensation object
+        """
+        comp = job_detailed['compensation']['baseSalary']
+        if comp:
+            interval = IndeedScraper.get_correct_interval(comp['unitOfWork'])
+            if interval:
+                return Compensation(
+                    interval=interval,
+                    min_amount=round(comp['range'].get('min'), 2) if comp['range'].get('min') is not None else None,
+                    max_amount=round(comp['range'].get('max'), 2) if comp['range'].get('max') is not None else None,
+                    currency=job_detailed['compensation']['currencyCode']
+                )
+
+        extracted_salary = job.get("extractedSalary")
+        compensation = None
+        if extracted_salary:
+            salary_snippet = job.get("salarySnippet")
+            currency = salary_snippet.get("currency") if salary_snippet else None
+            interval = (extracted_salary.get("type"),)
+            if isinstance(interval, tuple):
+                interval = interval[0]
+
+            interval = interval.upper()
+            if interval in CompensationInterval.__members__:
+                compensation = Compensation(
+                    interval=CompensationInterval[interval],
+                    min_amount=int(extracted_salary.get("min")),
+                    max_amount=int(extracted_salary.get("max")),
+                    currency=currency,
+                )
+        return compensation
+
     @staticmethod
     def parse_jobs(soup: BeautifulSoup) -> dict:
         """
@@ -302,24 +282,6 @@ class IndeedScraper(Scraper):
                 "Could not find any results for the search"
             )
 
-    @staticmethod
-    def total_jobs(soup: BeautifulSoup) -> int:
-        """
-        Parses the total jobs for that search from soup object
-        :param soup:
-        :return: total_num_jobs
-        """
-        script = soup.find("script", string=lambda t: t and "window._initialData" in t)
-
-        pattern = re.compile(r"window._initialData\s*=\s*({.*})\s*;", re.DOTALL)
-        match = pattern.search(script.string)
-        total_num_jobs = 0
-        if match:
-            json_str = match.group(1)
-            data = json.loads(json_str)
-            total_num_jobs = int(data["searchTitleBarModel"]["totalNumResults"])
-        return total_num_jobs
-
     @staticmethod
     def get_headers():
         return {
@@ -333,25 +295,17 @@ class IndeedScraper(Scraper):
           'referer': 'https://www.indeed.com/m/jobs?q=software%20intern&l=Dallas%2C%20TX&from=serpso&rq=1&rsIdx=3',
         }
 
-    @staticmethod
-    def is_remote_job(job: dict) -> bool:
-        """
-        :param job:
-        :return: bool
-        """
-        for taxonomy in job.get("taxonomyAttributes", []):
-            if taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0:
-                return True
-        return False
-
     @staticmethod
     def add_params(scraper_input: ScraperInput, page: int) -> dict[str, str | Any]:
+        # `fromage` is the posting time filter in days
+        fromage = max(scraper_input.hours_old // 24, 1) if scraper_input.hours_old else None
         params = {
             "q": scraper_input.search_term,
-            "l": scraper_input.location,
+            "l": scraper_input.location if scraper_input.location else scraper_input.country.value[0].split(',')[-1],
             "filter": 0,
             "start": scraper_input.offset + page * 10,
-            "sort": "date"
+            "sort": "date",
+            "fromage": fromage,
         }
         if scraper_input.distance:
             params["radius"] = scraper_input.distance
@@ -360,7 +314,7 @@ class IndeedScraper(Scraper):
         if scraper_input.is_remote:
             sc_values.append("attr(DSQF7)")
         if scraper_input.job_type:
-            sc_values.append("jt({})".format(scraper_input.job_type.value))
+            sc_values.append("jt({})".format(scraper_input.job_type.value[0]))
 
         if sc_values:
             params["sc"] = "0kf:" + "".join(sc_values) + ";"
@@ -369,3 +323,114 @@ class IndeedScraper(Scraper):
             params['iafilter'] = 1
 
         return params
+
+    @staticmethod
+    def is_job_remote(job: dict, job_detailed: dict, description: str) -> bool:
+        remote_keywords = ['remote', 'work from home', 'wfh']
+        is_remote_in_attributes = any(
+            any(keyword in attr['label'].lower() for keyword in remote_keywords)
+            for attr in job_detailed['attributes']
+        )
+        is_remote_in_description = any(keyword in description.lower() for keyword in remote_keywords)
+        is_remote_in_location = any(
+            keyword in job_detailed['location']['formatted']['long'].lower()
+            for keyword in remote_keywords
+        )
+        is_remote_in_taxonomy = any(
+            taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0
+            for taxonomy in job.get("taxonomyAttributes", [])
+        )
+        return is_remote_in_attributes or is_remote_in_description or is_remote_in_location or is_remote_in_taxonomy
+
+    def get_job_details(self, job_keys: list[str]) -> dict:
+        """
+        Queries the GraphQL endpoint for detailed job information for the given job keys.
+        """
+        url = "https://apis.indeed.com/graphql"
+        headers = {
+            'Host': 'apis.indeed.com',
+            'content-type': 'application/json',
+            'indeed-api-key': '161092c2017b5bbab13edb12461a62d5a833871e7cad6d9d475304573de67ac8',
+            'accept': 'application/json',
+            'indeed-locale': 'en-US',
+            'accept-language': 'en-US,en;q=0.9',
+            'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 16_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 Indeed App 193.1',
+            'indeed-app-info': 'appv=193.1; appid=com.indeed.jobsearch; osv=16.6.1; os=ios; dtype=phone',
+            'indeed-co': 'US',
+        }
+
+        job_keys_gql = '[' + ', '.join(f'"{key}"' for key in job_keys) + ']'
+
+        payload = {
+            "query": f"""
+            query GetJobData {{
+              jobData(input: {{
+                jobKeys: {job_keys_gql}
+              }}) {{
+                results {{
+                  job {{
+                    key
+                    title
+                    description {{
+                      html
+                    }}
+                    location {{
+                      countryName
+                      countryCode
+                      city
+                      postalCode
+                      streetAddress
+                      formatted {{
+                        short
+                        long
+                      }}
+                    }}
+                    compensation {{
+                      baseSalary {{
+                        unitOfWork
+                        range {{
+                          ... on Range {{
+                            min
+                            max
+                          }}
+                        }}
+                      }}
+                      currencyCode
+                    }}
+                    attributes {{
+                      label
+                    }}
+                    employer {{
+                      relativeCompanyPageUrl
+                    }}
+                    recruit {{
+                      viewJobUrl
+                      detailedSalary
+                      workSchedule
+                    }}
+                  }}
+                }}
+              }}
+            }}
+            """
+        }
+        response = requests.post(url, headers=headers, json=payload, proxies=self.proxy)
+        if response.status_code == 200:
+            return response.json()['data']['jobData']['results']
+        else:
+            return {}
+
+    @staticmethod
+    def get_correct_interval(interval: str) -> CompensationInterval:
+        interval_mapping = {
+            "DAY": "DAILY",
+            "YEAR": "YEARLY",
+            "HOUR": "HOURLY",
+            "WEEK": "WEEKLY",
+            "MONTH": "MONTHLY"
+        }
+        mapped_interval = interval_mapping.get(interval.upper(), None)
+        if mapped_interval and mapped_interval in CompensationInterval.__members__:
+            return CompensationInterval[mapped_interval]
+        else:
+            raise ValueError(f"Unsupported interval: {interval}")

src/jobspy/scrapers/linkedin/__init__.py

@@ -31,8 +31,7 @@ from ..utils import (
     count_urgent_words,
     extract_emails_from_text,
     get_enum_from_job_type,
-    currency_parser,
+    currency_parser
-    modify_and_get_description
 )
 
 
@@ -59,6 +58,12 @@ class LinkedInScraper(Scraper):
         url_lock = Lock()
         page = scraper_input.offset // 25 + 25 if scraper_input.offset else 0
 
+        seconds_old = (
+            scraper_input.hours_old * 3600
+            if scraper_input.hours_old
+            else None
+        )
+
         def job_type_code(job_type_enum):
             mapping = {
                 JobType.FULL_TIME: "F",
@@ -70,7 +75,9 @@ class LinkedInScraper(Scraper):
 
             return mapping.get(job_type_enum, "")
 
-        while len(job_list) < scraper_input.results_wanted and page < 1000:
+        continue_search = lambda: len(job_list) < scraper_input.results_wanted and page < 1000
+
+        while continue_search():
             session = create_session(is_tls=False, has_retry=True, delay=5)
             params = {
                 "keywords": scraper_input.search_term,
@@ -83,6 +90,8 @@ class LinkedInScraper(Scraper):
                 "pageNum": 0,
                 "start": page + scraper_input.offset,
                 "f_AL": "true" if scraper_input.easy_apply else None,
+                "f_C": ','.join(map(str, scraper_input.linkedin_company_ids)) if scraper_input.linkedin_company_ids else None,
+                "f_TPR": f"r{seconds_old}",
             }
 
             params = {k: v for k, v in params.items() if v is not None}
@@ -98,7 +107,9 @@ class LinkedInScraper(Scraper):
                 response.raise_for_status()
 
             except requests.HTTPError as e:
-                raise LinkedInException(f"bad response status code: {e.response.status_code}")
+                raise LinkedInException(
+                    f"bad response status code: {e.response.status_code}"
+                )
             except ProxyError as e:
                 raise LinkedInException("bad proxy")
             except Exception as e:
@@ -130,8 +141,9 @@ class LinkedInScraper(Scraper):
                 except Exception as e:
                     raise LinkedInException("Exception occurred while processing jobs")
 
-            page += 25
+            if continue_search():
-            time.sleep(random.uniform(LinkedInScraper.DELAY, LinkedInScraper.DELAY + 2))
+                time.sleep(random.uniform(LinkedInScraper.DELAY, LinkedInScraper.DELAY + 2))
+                page += 25
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
@@ -141,11 +153,11 @@ class LinkedInScraper(Scraper):
 
         compensation = None
         if salary_tag:
-            salary_text = salary_tag.get_text(separator=' ').strip()
+            salary_text = salary_tag.get_text(separator=" ").strip()
-            salary_values = [currency_parser(value) for value in salary_text.split('-')]
+            salary_values = [currency_parser(value) for value in salary_text.split("-")]
             salary_min = salary_values[0]
             salary_max = salary_values[1]
-            currency = salary_text[0] if salary_text[0] != '$' else 'USD'
+            currency = salary_text[0] if salary_text[0] != "$" else "USD"
 
             compensation = Compensation(
                 min_amount=int(salary_min),
@@ -223,10 +235,15 @@ class LinkedInScraper(Scraper):
         div_content = soup.find(
             "div", class_=lambda x: x and "show-more-less-html__markup" in x
         )
-
         description = None
-        if div_content:
+        if div_content is not None:
-            description = modify_and_get_description(div_content)
+            def remove_attributes(tag):
+                for attr in list(tag.attrs):
+                    del tag[attr]
+                return tag
+
+            div_content = remove_attributes(div_content)
+            description = div_content.prettify(formatter="html")
 
         def get_job_type(
             soup_job_type: BeautifulSoup,
@@ -290,17 +307,17 @@ class LinkedInScraper(Scraper):
     @staticmethod
     def headers() -> dict:
         return {
-            'authority': 'www.linkedin.com',
+            "authority": "www.linkedin.com",
-            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-            'accept-language': 'en-US,en;q=0.9',
+            "accept-language": "en-US,en;q=0.9",
-            'cache-control': 'max-age=0',
+            "cache-control": "max-age=0",
-            'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
+            "sec-ch-ua": '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
             # 'sec-ch-ua-mobile': '?0',
             # 'sec-ch-ua-platform': '"macOS"',
             # 'sec-fetch-dest': 'document',
             # 'sec-fetch-mode': 'navigate',
             # 'sec-fetch-site': 'none',
             # 'sec-fetch-user': '?1',
-            'upgrade-insecure-requests': '1',
+            "upgrade-insecure-requests": "1",
-            'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+            "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
         }

src/jobspy/scrapers/utils.py

@@ -1,4 +1,5 @@
 import re
+import logging
 import numpy as np
 
 import tls_client
@@ -7,14 +8,14 @@ from requests.adapters import HTTPAdapter, Retry
 
 from ..jobs import JobType
 
-
+logger = logging.getLogger("JobSpy")
-def modify_and_get_description(soup):
+if not logger.handlers:
-    for li in soup.find_all('li'):
+    logger.setLevel(logging.ERROR)
-        li.string = "- " + li.get_text()
+    console_handler = logging.StreamHandler()
-
+    console_handler.setLevel(logging.ERROR)
-    description = soup.get_text(separator='\n').strip()
+    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-    description = re.sub(r'\n+', '\n', description)
+    console_handler.setFormatter(formatter)
-    return description
+    logger.addHandler(console_handler)
 
 
 def count_urgent_words(description: str) -> int:
@@ -79,6 +80,7 @@ def get_enum_from_job_type(job_type_str: str) -> JobType | None:
             res = job_type
     return res
 
+
 def currency_parser(cur_str):
     # Remove any non-numerical characters
     # except for ',' '.' or '-' (e.g. EUR)
@@ -94,3 +96,5 @@ def currency_parser(cur_str):
         num = float(cur_str)
 
     return np.round(num, 2)
+
+

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -6,17 +6,15 @@ This module contains routines to scrape ZipRecruiter.
 """
 import math
 import time
-import re
+from datetime import datetime, timezone
-from datetime import datetime, date
 from typing import Optional, Tuple, Any
 
-from bs4 import BeautifulSoup
 from concurrent.futures import ThreadPoolExecutor
 
 from .. import Scraper, ScraperInput, Site
 from ..exceptions import ZipRecruiterException
 from ...jobs import JobPost, Compensation, Location, JobResponse, JobType, Country
-from ..utils import count_urgent_words, extract_emails_from_text, create_session, modify_and_get_description
+from ..utils import count_urgent_words, extract_emails_from_text, create_session
 
 
 class ZipRecruiterScraper(Scraper):
@@ -32,6 +30,7 @@ class ZipRecruiterScraper(Scraper):
 
         self.jobs_per_page = 20
         self.seen_urls = set()
+        self.delay = 5
 
     def find_jobs_in_page(
         self, scraper_input: ScraperInput, continue_token: str | None = None
@@ -44,12 +43,12 @@ class ZipRecruiterScraper(Scraper):
         """
         params = self.add_params(scraper_input)
         if continue_token:
-            params["continue"] = continue_token
+            params["continue_from"] = continue_token
         try:
             response = self.session.get(
                 f"https://api.ziprecruiter.com/jobs-app/jobs",
                 headers=self.headers(),
-                params=self.add_params(scraper_input),
+                params=params
             )
             if response.status_code != 200:
                 raise ZipRecruiterException(
@@ -60,7 +59,6 @@ class ZipRecruiterScraper(Scraper):
                 raise ZipRecruiterException("bad proxy")
             raise ZipRecruiterException(str(e))
 
-        time.sleep(5)
         response_data = response.json()
         jobs_list = response_data.get("jobs", [])
         next_continue_token = response_data.get("continue", None)
@@ -68,7 +66,7 @@ class ZipRecruiterScraper(Scraper):
         with ThreadPoolExecutor(max_workers=self.jobs_per_page) as executor:
             job_results = [executor.submit(self.process_job, job) for job in jobs_list]
 
-        job_list = [result.result() for result in job_results if result.result()]
+        job_list = list(filter(None, (result.result() for result in job_results)))
         return job_list, next_continue_token
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
@@ -86,6 +84,9 @@ class ZipRecruiterScraper(Scraper):
             if len(job_list) >= scraper_input.results_wanted:
                 break
 
+            if page > 1:
+                time.sleep(self.delay)
+
             jobs_on_page, continue_token = self.find_jobs_in_page(
                 scraper_input, continue_token
             )
@@ -95,22 +96,19 @@ class ZipRecruiterScraper(Scraper):
             if not continue_token:
                 break
 
-        if len(job_list) > scraper_input.results_wanted:
+        return JobResponse(jobs=job_list[: scraper_input.results_wanted])
-            job_list = job_list[: scraper_input.results_wanted]
 
-        return JobResponse(jobs=job_list)
+    def process_job(self, job: dict) -> JobPost | None:
-
-    @staticmethod
-    def process_job(job: dict) -> JobPost:
         """Processes an individual job dict from the response"""
         title = job.get("name")
-        job_url = job.get("job_url")
+        job_url = f"https://www.ziprecruiter.com/jobs//j?lvk={job['listing_key']}"
+        if job_url in self.seen_urls:
+            return
+        self.seen_urls.add(job_url)
 
-        job_description_html = job.get("job_description", "").strip()
+        description = job.get("job_description", "").strip()
-        description_soup = BeautifulSoup(job_description_html, "html.parser")
-        description = modify_and_get_description(description_soup)
 
-        company = job["hiring_company"].get("name") if "hiring_company" in job else None
+        company = job.get("hiring_company", {}).get("name")
         country_value = "usa" if job.get("job_country") == "US" else "canada"
         country_enum = Country.from_string(country_value)
 
@@ -120,17 +118,7 @@ class ZipRecruiterScraper(Scraper):
         job_type = ZipRecruiterScraper.get_job_type_enum(
             job.get("employment_type", "").replace("_", "").lower()
         )
-
+        date_posted = datetime.fromisoformat(job['posted_time'].rstrip("Z")).date()
-        save_job_url = job.get("SaveJobURL", "")
-        posted_time_match = re.search(
-            r"posted_time=(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z)", save_job_url
-        )
-        if posted_time_match:
-            date_time_str = posted_time_match.group(1)
-            date_posted_obj = datetime.strptime(date_time_str, "%Y-%m-%dT%H:%M:%SZ")
-            date_posted = date_posted_obj.date()
-        else:
-            date_posted = date.today()
 
         return JobPost(
             title=title,
@@ -173,30 +161,25 @@ class ZipRecruiterScraper(Scraper):
         params = {
             "search": scraper_input.search_term,
             "location": scraper_input.location,
-            "form": "jobs-landing",
         }
-        job_type_value = None
+        if scraper_input.hours_old:
+            fromage = max(scraper_input.hours_old // 24, 1) if scraper_input.hours_old else None
+            params['days'] = fromage
+        job_type_map = {
+            JobType.FULL_TIME: 'full_time',
+            JobType.PART_TIME: 'part_time'
+        }
         if scraper_input.job_type:
-            if scraper_input.job_type.value == "fulltime":
+            params['employment_type'] = job_type_map[scraper_input.job_type] if scraper_input.job_type in job_type_map else scraper_input.job_type.value[0]
-                job_type_value = "full_time"
-            elif scraper_input.job_type.value == "parttime":
-                job_type_value = "part_time"
-            else:
-                job_type_value = scraper_input.job_type.value
         if scraper_input.easy_apply:
             params['zipapply'] = 1
-
-        if job_type_value:
-            params[
-                "refine_by_employment"
-            ] = f"employment_type:employment_type:{job_type_value}"
-
         if scraper_input.is_remote:
-            params["refine_by_location_type"] = "only_remote"
+            params["remote"] = 1
-
         if scraper_input.distance:
             params["radius"] = scraper_input.distance
 
+        params = {k: v for k, v in params.items() if v is not None}
+
         return params
 
     @staticmethod