enh: indeed more fields (#126)

README.md

@@ -21,7 +21,7 @@ Updated for release v1.1.3
 ### Installation
 
 ```
-pip install python-jobspy
+pip install -U python-jobspy
 ```
 
 _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
@@ -64,8 +64,8 @@ Required
 ├── site_type (List[enum]): linkedin, zip_recruiter, indeed, glassdoor
 └── search_term (str)
 Optional
-├── location (int)
+├── location (str)
-├── distance (int): in miles
+├── distance (int): in miles, default 50
 ├── job_type (enum): fulltime, parttime, internship, contract
 ├── proxy (str): in format 'http://user:pass@host:port'
 ├── is_remote (bool)
@@ -76,7 +76,7 @@ Optional
 ├── description_format (enum): markdown, html (format type of the job descriptions)
 ├── 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)
+├── hours_old (int): filters jobs by the number of hours since the job was posted (ZipRecruiter and Glassdoor round up to next day. If you use this on Indeed, it will not filter by job_type or is_remote)
 ```
 
 ### JobPost Schema
@@ -100,24 +100,26 @@ JobPost
 │   └── currency (enum)
 └── date_posted (date)
 └── emails (str)
-└── num_urgent_words (int)
 └── is_remote (bool)
+
+Indeed specific
+├── company_country (str)
+└── company_addresses (str)
+└── company_industry (str)
+└── company_employees_label (str)
+└── company_revenue_label (str)
+└── company_description (str)
+└── ceo_name (str)
+└── ceo_photo_url (str)
+└── logo_photo_url (str)
+└── banner_photo_url (str)
 ```
 
-### Exceptions
-
-The following exceptions may be raised when using JobSpy:
-
-* `LinkedInException`
-* `IndeedException`
-* `ZipRecruiterException`
-* `GlassdoorException`
-
 ## Supported Countries for Job Searching
 
 ### **LinkedIn**
 
-LinkedIn searches globally & uses only the `location` parameter. You can only fetch 1000 jobs max from the LinkedIn endpoint we're using
+LinkedIn searches globally & uses only the `location` parameter. You can only fetch 1000 jobs max from the LinkedIn endpoint we are using
 
 ### **ZipRecruiter**
 
@@ -147,10 +149,14 @@ You can specify the following countries when searching on Indeed (use the exact
 | South Korea          | Spain*       | Sweden     | Switzerland*   |
 | Taiwan               | Thailand     | Turkey     | Ukraine        |
 | United Arab Emirates | UK*          | USA*       | Uruguay        |
-| Venezuela            | Vietnam      |            |                |
+| Venezuela            | Vietnam*     |            |                |
 
 
-Glassdoor can only fetch 900 jobs from the endpoint we're using on a given search.
+## Notes
+* Indeed is the best scraper currently with no rate limiting.  
+* Glassdoor can only fetch 900 jobs from the endpoint we're using on a given search.  
+* LinkedIn is the most restrictive and usually rate limits on around the 10th page  
+* ZipRecruiter is okay but has a 5 second delay in between each page to avoid rate limiting.
 ## Frequently Asked Questions
 
 ---
@@ -167,8 +173,4 @@ persist, [submit an issue](https://github.com/Bunsly/JobSpy/issues).
 - Waiting some time between scrapes (site-dependent).
 - Trying a VPN or proxy to change your IP address.
 
----
+---
-
-
-
-  

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand.
 
 [[package]]
 name = "annotated-types"
@@ -524,17 +524,6 @@ files = [
     {file = "fqdn-1.5.1.tar.gz", hash = "sha256:105ed3677e767fb5ca086a0c1f4bb66ebc3c100be518f0e0d755d9eae164d89f"},
 ]
 
-[[package]]
-name = "html2text"
-version = "2020.1.16"
-description = "Turn HTML into equivalent Markdown-structured text."
-optional = false
-python-versions = ">=3.5"
-files = [
-    {file = "html2text-2020.1.16-py3-none-any.whl", hash = "sha256:c7c629882da0cf377d66f073329ccf34a12ed2adf0169b9285ae4e63ef54c82b"},
-    {file = "html2text-2020.1.16.tar.gz", hash = "sha256:e296318e16b059ddb97f7a8a1d6a5c1d7af4544049a01e261731d2d5cc277bbb"},
-]
-
 [[package]]
 name = "idna"
 version = "3.4"
@@ -1037,6 +1026,21 @@ files = [
     {file = "jupyterlab_widgets-3.0.8.tar.gz", hash = "sha256:d428ab97b8d87cc7c54cbf37644d6e0f0e662f23876e05fa460a73ec3257252a"},
 ]
 
+[[package]]
+name = "markdownify"
+version = "0.11.6"
+description = "Convert HTML to markdown."
+optional = false
+python-versions = "*"
+files = [
+    {file = "markdownify-0.11.6-py3-none-any.whl", hash = "sha256:ba35fe289d5e9073bcd7d2cad629278fe25f1a93741fcdc0bfb4f009076d8324"},
+    {file = "markdownify-0.11.6.tar.gz", hash = "sha256:009b240e0c9f4c8eaf1d085625dcd4011e12f0f8cec55dedf9ea6f7655e49bfe"},
+]
+
+[package.dependencies]
+beautifulsoup4 = ">=4.9,<5"
+six = ">=1.15,<2"
+
 [[package]]
 name = "markupsafe"
 version = "2.1.3"
@@ -1064,16 +1068,6 @@ files = [
     {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"},
     {file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"},
     {file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f698de3fd0c4e6972b92290a45bd9b1536bffe8c6759c62471efaa8acb4c37bc"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aa57bd9cf8ae831a362185ee444e15a93ecb2e344c8e52e4d721ea3ab6ef1823"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffcc3f7c66b5f5b7931a5aa68fc9cecc51e685ef90282f4a82f0f5e9b704ad11"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47d4f1c5f80fc62fdd7777d0d40a2e9dda0a05883ab11374334f6c4de38adffd"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1f67c7038d560d92149c060157d623c542173016c4babc0c1913cca0564b9939"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:9aad3c1755095ce347e26488214ef77e0485a3c34a50c5a5e2471dff60b9dd9c"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:14ff806850827afd6b07a5f32bd917fb7f45b046ba40c57abdb636674a8b559c"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8f9293864fe09b8149f0cc42ce56e3f0e54de883a9de90cd427f191c346eb2e1"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-win32.whl", hash = "sha256:715d3562f79d540f251b99ebd6d8baa547118974341db04f5ad06d5ea3eb8007"},
-    {file = "MarkupSafe-2.1.3-cp312-cp312-win_amd64.whl", hash = "sha256:1b8dd8c3fd14349433c79fa8abeb573a55fc0fdd769133baac1f5e07abf54aeb"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"},
     {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"},
@@ -2456,4 +2450,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "eea3694820df164179cdd8312d382eb5b29d6317c4d34c586e8866c69aaee9e9"
+content-hash = "ba7f7cc9b6833a4a6271981f90610395639dd8b9b3db1370cbd1149d70cc9632"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.46"
+version = "1.1.48"
 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"
@@ -17,8 +17,8 @@ beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"
 NUMPY = "1.24.2"
 pydantic = "^2.3.0"
-html2text = "^2020.1.16"
 tls-client = "^1.0.1"
+markdownify = "^0.11.6"
 
 
 [tool.poetry.group.dev.dependencies]

src/jobspy/__init__.py

@@ -3,6 +3,7 @@ from typing import Tuple
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from .jobs import JobType, Location
+from .scrapers.utils import logger
 from .scrapers.indeed import IndeedScraper
 from .scrapers.ziprecruiter import ZipRecruiterScraper
 from .scrapers.glassdoor import GlassdoorScraper
@@ -20,7 +21,7 @@ def scrape_jobs(
     site_name: str | list[str] | Site | list[Site] | None = None,
     search_term: str | None = None,
     location: str | None = None,
-    distance: int | None = None,
+    distance: int | None = 50,
     is_remote: bool = False,
     job_type: str | None = None,
     easy_apply: bool | None = None,
@@ -92,6 +93,8 @@ def scrape_jobs(
         scraper_class = SCRAPER_MAPPING[site]
         scraper = scraper_class(proxy=proxy)
         scraped_data: JobResponse = scraper.scrape(scraper_input)
+        site_name = 'ZipRecruiter' if site.value.capitalize() == 'Zip_recruiter' else site.value.capitalize()
+        logger.info(f"{site_name} finished scraping")
         return site.value, scraped_data
 
     site_to_jobs_dict = {}
@@ -160,11 +163,11 @@ def scrape_jobs(
         
         # Desired column order
         desired_order = [
-            "job_url_hyper" if hyperlinks else "job_url",
             "site",
+            "job_url_hyper" if hyperlinks else "job_url",
+            "job_url_direct",
             "title",
             "company",
-            "company_url",
             "location",
             "job_type",
             "date_posted",
@@ -173,10 +176,20 @@ def scrape_jobs(
             "max_amount",
             "currency",
             "is_remote",
-            "num_urgent_words",
-            "benefits",
             "emails",
             "description",
+
+            "company_url",
+            "company_url_direct",
+            "company_addresses",
+            "company_industry",
+            "company_num_employees",
+            "company_revenue",
+            "company_description",
+            "logo_photo_url",
+            "banner_photo_url",
+            "ceo_name",
+            "ceo_photo_url",
         ]
         
         # Step 3: Ensure all desired columns are present, adding missing ones as empty

src/jobspy/jobs/__init__.py

@@ -57,7 +57,7 @@ class JobType(Enum):
 class Country(Enum):
     """
     Gets the subdomain for Indeed and Glassdoor.
-    The second item in the tuple is the subdomain for Indeed
+    The second item in the tuple is the subdomain (and API country code if there's a ':' separator) for Indeed
     The third item in the tuple is the subdomain (and tld if there's a ':' separator) for Glassdoor
     """
 
@@ -118,11 +118,11 @@ class Country(Enum):
     TURKEY = ("turkey", "tr")
     UKRAINE = ("ukraine", "ua")
     UNITEDARABEMIRATES = ("united arab emirates", "ae")
-    UK = ("uk,united kingdom", "uk", "co.uk")
+    UK = ("uk,united kingdom", "uk:gb", "co.uk")
-    USA = ("usa,us,united states", "www", "com")
+    USA = ("usa,us,united states", "www:us", "com")
     URUGUAY = ("uruguay", "uy")
     VENEZUELA = ("venezuela", "ve")
-    VIETNAM = ("vietnam", "vn")
+    VIETNAM = ("vietnam", "vn", "com")
 
     # internal for ziprecruiter
     US_CANADA = ("usa/ca", "www")
@@ -132,7 +132,10 @@ class Country(Enum):
 
     @property
     def indeed_domain_value(self):
-        return self.value[1]
+        subdomain, _, api_country_code = self.value[1].partition(":")
+        if subdomain and api_country_code:
+            return subdomain, api_country_code.upper()
+        return self.value[1], self.value[1].upper()
 
     @property
     def glassdoor_domain_value(self):
@@ -145,7 +148,7 @@ class Country(Enum):
         else:
             raise Exception(f"Glassdoor is not available for {self.name}")
 
-    def get_url(self):
+    def get_glassdoor_url(self):
         return f"https://{self.glassdoor_domain_value}/"
 
     @classmethod
@@ -163,7 +166,7 @@ class Country(Enum):
 
 
 class Location(BaseModel):
-    country: Country | None = None
+    country: Country | str | None = None
     city: Optional[str] = None
     state: Optional[str] = None
 
@@ -173,7 +176,9 @@ class Location(BaseModel):
             location_parts.append(self.city)
         if self.state:
             location_parts.append(self.state)
-        if self.country and self.country not in (Country.US_CANADA, Country.WORLDWIDE):
+        if isinstance(self.country, str):
+            location_parts.append(self.country)
+        elif self.country and self.country not in (Country.US_CANADA, Country.WORLDWIDE):
             country_name = self.country.value[0]
             if "," in country_name:
                 country_name = country_name.split(",")[0]
@@ -217,21 +222,31 @@ class DescriptionFormat(Enum):
 
 class JobPost(BaseModel):
     title: str
-    company_name: str
+    company_name: str | None
     job_url: str
+    job_url_direct: str | None = None
     location: Optional[Location]
 
     description: str | None = None
     company_url: str | None = None
+    company_url_direct: str | None = None
 
     job_type: list[JobType] | None = None
     compensation: Compensation | None = None
     date_posted: date | None = None
-    benefits: str | None = None
     emails: list[str] | None = None
-    num_urgent_words: int | None = None
     is_remote: bool | None = None
-    # company_industry: str | None = None
+
+    # indeed specific
+    company_addresses: str | None = None
+    company_industry: str | None = None
+    company_num_employees: str | None = None
+    company_revenue: str | None = None
+    company_description: str | None = None
+    ceo_name: str | None = None
+    ceo_photo_url: str | None = None
+    logo_photo_url: str | None = None
+    banner_photo_url: str | None = None
 
 
 class JobResponse(BaseModel):

src/jobspy/scrapers/glassdoor/__init__.py

@@ -5,11 +5,13 @@ jobspy.scrapers.glassdoor
 This module contains routines to scrape Glassdoor.
 """
 import json
+import re
+
 import requests
 from typing import Optional
 from datetime import datetime, timedelta
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from ..utils import count_urgent_words, extract_emails_from_text
+from ..utils import extract_emails_from_text
 
 from .. import Scraper, ScraperInput, Site
 from ..exceptions import GlassdoorException
@@ -42,6 +44,7 @@ class GlassdoorScraper(Scraper):
         self.session = None
         self.scraper_input = None
         self.jobs_per_page = 30
+        self.max_pages = 30
         self.seen_urls = set()
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
@@ -52,39 +55,40 @@ class GlassdoorScraper(Scraper):
         """
         self.scraper_input = scraper_input
         self.scraper_input.results_wanted = min(900, scraper_input.results_wanted)
-        self.base_url = self.scraper_input.country.get_url()
+        self.base_url = self.scraper_input.country.get_glassdoor_url()
+
+        self.session = create_session(self.proxy, is_tls=True, has_retry=True)
+        token = self._get_csrf_token()
+        self.headers['gd-csrf-token'] = token if token else self.fallback_token
 
         location_id, location_type = self._get_location(
             scraper_input.location, scraper_input.is_remote
         )
         if location_type is None:
+            logger.error('Glassdoor: location not parsed')
             return JobResponse(jobs=[])
         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.base_url)
 
-        try:
+        for page in range(
-            for page in range(
+            1 + (scraper_input.offset // self.jobs_per_page),
-                1 + (scraper_input.offset // self.jobs_per_page),
+            min(
-                min(
+                (scraper_input.results_wanted // self.jobs_per_page) + 2,
-                    (scraper_input.results_wanted // self.jobs_per_page) + 2,
+                self.max_pages + 1,
-                    max_pages + 1,
+            ),
-                ),
+        ):
-            ):
+            logger.info(f'Glassdoor search page: {page}')
-                try:
+            try:
-                    jobs, cursor = self._fetch_jobs_page(
+                jobs, cursor = self._fetch_jobs_page(
-                        scraper_input, location_id, location_type, page, cursor
+                    scraper_input, location_id, location_type, page, cursor
-                    )
+                )
-                    all_jobs.extend(jobs)
+                all_jobs.extend(jobs)
-                    if len(all_jobs) >= scraper_input.results_wanted:
+                if not jobs or len(all_jobs) >= scraper_input.results_wanted:
-                        all_jobs = all_jobs[: scraper_input.results_wanted]
+                    all_jobs = all_jobs[: scraper_input.results_wanted]
-                        break
+                    break
-                except Exception as e:
+            except Exception as e:
-                    raise GlassdoorException(str(e))
+                logger.error(f'Glassdoor: {str(e)}')
-        except Exception as e:
+                break
-            raise GlassdoorException(str(e))
         return JobResponse(jobs=all_jobs)
 
     def _fetch_jobs_page(
@@ -98,27 +102,26 @@ class GlassdoorScraper(Scraper):
         """
         Scrapes a page of Glassdoor for jobs with scraper_input criteria
         """
+        jobs = []
         self.scraper_input = scraper_input
         try:
             payload = self._add_payload(
                 location_id, location_type, page_num, cursor
             )
             response = self.session.post(
-                f"{self.base_url}/graph", headers=self.headers, timeout=10, data=payload
+                f"{self.base_url}/graph", headers=self.headers, timeout_seconds=15, data=payload
             )
             if response.status_code != 200:
-                raise GlassdoorException(
+                raise GlassdoorException(f"bad response status code: {response.status_code}")
-                    f"bad response status code: {response.status_code}"
-                )
             res_json = response.json()[0]
             if "errors" in res_json:
                 raise ValueError("Error encountered in API response")
-        except Exception as e:
+        except (requests.exceptions.ReadTimeout, GlassdoorException, ValueError, Exception) as e:
-            raise GlassdoorException(str(e))
+            logger.error(f'Glassdoor: {str(e)}')
+            return jobs, None
 
         jobs_data = res_json["data"]["jobListings"]["jobListings"]
 
-        jobs = []
         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):
@@ -133,6 +136,18 @@ class GlassdoorScraper(Scraper):
             res_json["data"]["jobListings"]["paginationCursors"], page_num + 1
         )
 
+    def _get_csrf_token(self):
+        """
+        Fetches csrf token needed for API by visiting a generic page
+        """
+        res = self.session.get(f'{self.base_url}/Job/computer-science-jobs.htm', headers=self.headers)
+        pattern = r'"token":\s*"([^"]+)"'
+        matches = re.findall(pattern, res.text)
+        token = None
+        if matches:
+            token = matches[0]
+        return token
+
     def _process_job(self, job_data):
         """
         Processes a single job and fetches its description.
@@ -173,7 +188,6 @@ class GlassdoorScraper(Scraper):
             is_remote=is_remote,
             description=description,
             emails=extract_emails_from_text(description) if description else None,
-            num_urgent_words=count_urgent_words(description) if description else None,
         )
 
     def _fetch_job_description(self, job_id):
@@ -217,7 +231,7 @@ class GlassdoorScraper(Scraper):
             return "11047", "STATE"  # remote options
         url = f"{self.base_url}/findPopularLocationAjax.htm?maxLocationsToReturn=10&term={location}"
         session = create_session(self.proxy, has_retry=True)
-        res = session.get(url)
+        res = self.session.get(url, headers=self.headers)
         if res.status_code != 200:
             if res.status_code == 429:
                 logger.error(f'429 Response - Blocked by Glassdoor for too many requests')
@@ -266,7 +280,74 @@ class GlassdoorScraper(Scraper):
                 "fromage": fromage,
                 "sort": "date"
             },
-            "query": """
+            "query": self.query_template
+        }
+        if self.scraper_input.job_type:
+            payload["variables"]["filterParams"].append(
+                {"filterKey": "jobType", "values": self.scraper_input.job_type.value[0]}
+            )
+        return json.dumps([payload])
+
+    @staticmethod
+    def parse_compensation(data: dict) -> Optional[Compensation]:
+        pay_period = data.get("payPeriod")
+        adjusted_pay = data.get("payPeriodAdjustedPay")
+        currency = data.get("payCurrency", "USD")
+        if not pay_period or not adjusted_pay:
+            return None
+
+        interval = None
+        if pay_period == "ANNUAL":
+            interval = CompensationInterval.YEARLY
+        elif pay_period:
+            interval = CompensationInterval.get_interval(pay_period)
+        min_amount = int(adjusted_pay.get("p10") // 1)
+        max_amount = int(adjusted_pay.get("p90") // 1)
+        return Compensation(
+            interval=interval,
+            min_amount=min_amount,
+            max_amount=max_amount,
+            currency=currency,
+        )
+
+    @staticmethod
+    def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
+        for job_type in JobType:
+            if job_type_str in job_type.value:
+                return [job_type]
+
+    @staticmethod
+    def parse_location(location_name: str) -> Location | None:
+        if not location_name or location_name == "Remote":
+            return
+        city, _, state = location_name.partition(", ")
+        return Location(city=city, state=state)
+
+    @staticmethod
+    def get_cursor_for_page(pagination_cursors, page_num):
+        for cursor_data in pagination_cursors:
+            if cursor_data["pageNumber"] == page_num:
+                return cursor_data["cursor"]
+
+    fallback_token = "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok"
+    headers = {
+        "authority": "www.glassdoor.com",
+        "accept": "*/*",
+        "accept-language": "en-US,en;q=0.9",
+        "apollographql-client-name": "job-search-next",
+        "apollographql-client-version": "4.65.5",
+        "content-type": "application/json",
+        "origin": "https://www.glassdoor.com",
+        "referer": "https://www.glassdoor.com/",
+        "sec-ch-ua": '"Chromium";v="118", "Google Chrome";v="118", "Not=A?Brand";v="99"',
+        "sec-ch-ua-mobile": "?0",
+        "sec-ch-ua-platform": '"macOS"',
+        "sec-fetch-dest": "empty",
+        "sec-fetch-mode": "cors",
+        "sec-fetch-site": "same-origin",
+        "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
+    }
+    query_template = """
             query JobSearchResultsQuery(
                 $excludeJobListingIds: [Long!], 
                 $keyword: String, 
@@ -431,70 +512,4 @@ class GlassdoorScraper(Scraper):
                 }
                 __typename
             }
-            """
+    """
-        }
-        if self.scraper_input.job_type:
-            payload["variables"]["filterParams"].append(
-                {"filterKey": "jobType", "values": self.scraper_input.job_type.value[0]}
-            )
-        return json.dumps([payload])
-
-    @staticmethod
-    def parse_compensation(data: dict) -> Optional[Compensation]:
-        pay_period = data.get("payPeriod")
-        adjusted_pay = data.get("payPeriodAdjustedPay")
-        currency = data.get("payCurrency", "USD")
-        if not pay_period or not adjusted_pay:
-            return None
-
-        interval = None
-        if pay_period == "ANNUAL":
-            interval = CompensationInterval.YEARLY
-        elif pay_period:
-            interval = CompensationInterval.get_interval(pay_period)
-        min_amount = int(adjusted_pay.get("p10") // 1)
-        max_amount = int(adjusted_pay.get("p90") // 1)
-        return Compensation(
-            interval=interval,
-            min_amount=min_amount,
-            max_amount=max_amount,
-            currency=currency,
-        )
-
-    @staticmethod
-    def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
-        for job_type in JobType:
-            if job_type_str in job_type.value:
-                return [job_type]
-
-    @staticmethod
-    def parse_location(location_name: str) -> Location | None:
-        if not location_name or location_name == "Remote":
-            return
-        city, _, state = location_name.partition(", ")
-        return Location(city=city, state=state)
-
-    @staticmethod
-    def get_cursor_for_page(pagination_cursors, page_num):
-        for cursor_data in pagination_cursors:
-            if cursor_data["pageNumber"] == page_num:
-                return cursor_data["cursor"]
-
-    headers = {
-        "authority": "www.glassdoor.com",
-        "accept": "*/*",
-        "accept-language": "en-US,en;q=0.9",
-        "apollographql-client-name": "job-search-next",
-        "apollographql-client-version": "4.65.5",
-        "content-type": "application/json",
-        "gd-csrf-token": "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok",
-        "origin": "https://www.glassdoor.com",
-        "referer": "https://www.glassdoor.com/",
-        "sec-ch-ua": '"Chromium";v="118", "Google Chrome";v="118", "Not=A?Brand";v="99"',
-        "sec-ch-ua-mobile": "?0",
-        "sec-ch-ua-platform": '"macOS"',
-        "sec-fetch-dest": "empty",
-        "sec-fetch-mode": "cors",
-        "sec-fetch-site": "same-origin",
-        "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
-    }

src/jobspy/scrapers/indeed/__init__.py

@@ -4,22 +4,15 @@ jobspy.scrapers.indeed
 
 This module contains routines to scrape Indeed.
 """
-import re
 import math
-import json
+from concurrent.futures import ThreadPoolExecutor, Future
-import requests
-from typing import Any
 from datetime import datetime
 
-from bs4 import BeautifulSoup
+import requests
-from bs4.element import Tag
-from concurrent.futures import ThreadPoolExecutor, Future
 
-from ..exceptions import IndeedException
+from .. import Scraper, ScraperInput, Site
 from ..utils import (
-    count_urgent_words,
     extract_emails_from_text,
-    create_session,
     get_enum_from_job_type,
     markdown_converter,
     logger
@@ -33,18 +26,19 @@ from ...jobs import (
     JobType,
     DescriptionFormat
 )
-from .. import Scraper, ScraperInput, Site
 
 
 class IndeedScraper(Scraper):
     def __init__(self, proxy: str | None = None):
         """
-        Initializes IndeedScraper with the Indeed job search url
+        Initializes IndeedScraper with the Indeed API url
         """
         self.scraper_input = None
-        self.jobs_per_page = 25
+        self.jobs_per_page = 100
         self.num_workers = 10
         self.seen_urls = set()
+        self.headers = None
+        self.api_country_code = None
         self.base_url = None
         self.api_url = "https://apis.indeed.com/graphql"
         site = Site(Site.INDEED)
@@ -57,279 +51,220 @@ class IndeedScraper(Scraper):
         :return: job_response
         """
         self.scraper_input = scraper_input
-        job_list = self._scrape_page()
+        domain, self.api_country_code = self.scraper_input.country.indeed_domain_value
-        pages_processed = 1
+        self.base_url = f"https://{domain}.indeed.com"
+        self.headers = self.api_headers.copy()
+        self.headers['indeed-co'] = self.scraper_input.country.indeed_domain_value
+        job_list = []
+        page = 1
 
-        while len(self.seen_urls) < scraper_input.results_wanted:
+        cursor = None
-            pages_to_process = math.ceil((scraper_input.results_wanted - len(self.seen_urls)) / self.jobs_per_page)
+        offset_pages = math.ceil(self.scraper_input.offset / 100)
-            new_jobs = False
+        for _ in range(offset_pages):
-
+            logger.info(f'Indeed skipping search page: {page}')
-            with ThreadPoolExecutor(max_workers=10) as executor:
+            __, cursor = self._scrape_page(cursor)
-                futures: list[Future] = [
+            if not __:
-                    executor.submit(self._scrape_page, page + pages_processed)
+                logger.info(f'Indeed found no jobs on page: {page}')
-                    for page in range(pages_to_process)
-                ]
-
-                for future in futures:
-                    jobs = future.result()
-                    if jobs:
-                        job_list += jobs
-                        new_jobs = True
-                    if len(self.seen_urls) >= scraper_input.results_wanted:
-                        break
-
-            pages_processed += pages_to_process
-            if not new_jobs:
                 break
 
-        if len(self.seen_urls) > scraper_input.results_wanted:
+        while len(self.seen_urls) < scraper_input.results_wanted:
-            job_list = job_list[:scraper_input.results_wanted]
+            logger.info(f'Indeed search page: {page}')
+            jobs, cursor = self._scrape_page(cursor)
+            if not jobs:
+                logger.info(f'Indeed found no jobs on page: {page}')
+                break
+            job_list += jobs
+            page += 1
+        return JobResponse(jobs=job_list[:scraper_input.results_wanted])
 
-        return JobResponse(jobs=job_list)
+    def _scrape_page(self, cursor: str | None) -> (list[JobPost], str | None):
-
-    def _scrape_page(self, page: int=0) -> list[JobPost]:
         """
         Scrapes a page of Indeed for jobs with scraper_input criteria
-        :param page:
+        :param cursor:
-        :return: jobs found on page, total number of jobs found for search
+        :return: jobs found on page, next page cursor
         """
-        job_list = []
+        jobs = []
-        domain = self.scraper_input.country.indeed_domain_value
+        new_cursor = None
-        self.base_url = f"https://{domain}.indeed.com"
+        filters = self._build_filters()
-
+        query = self.job_search_query.format(
-        try:
+            what=self.scraper_input.search_term,
-            session = create_session(self.proxy)
+            location=self.scraper_input.location if self.scraper_input.location else self.scraper_input.country.value[0].split(',')[-1],
-            response = session.get(
+            radius=self.scraper_input.distance,
-                f"{self.base_url}/m/jobs",
+            dateOnIndeed=self.scraper_input.hours_old,
-                headers=self.headers,
+            cursor=f'cursor: "{cursor}"' if cursor else '',
-                params=self._add_params(page),
+            filters=filters
-            )
+        )
-            if response.status_code not in range(200, 400):
+        payload = {
-                if response.status_code == 429:
+            'query': query,
-                    logger.error(f'429 Response - Blocked by Indeed for too many requests')
+        }
-                else:
+        api_headers = self.api_headers.copy()
-                    logger.error(f'Indeed response status code {response.status_code}')
+        api_headers['indeed-co'] = self.api_country_code
-                return job_list
+        response = requests.post(self.api_url, headers=api_headers, json=payload, proxies=self.proxy, timeout=10)
-
+        if response.status_code != 200:
-        except Exception as e:
+            logger.info(f'Indeed responded with status code: {response.status_code} (submit GitHub issue if this appears to be a beg)')
-            if "Proxy responded with" in str(e):
+            return jobs, new_cursor
-                logger.error(f'Indeed: Bad proxy')
+        data = response.json()
-            else:
+        jobs = data['data']['jobSearch']['results']
-                logger.error(f'Indeed: {str(e)}')
+        new_cursor = data['data']['jobSearch']['pageInfo']['nextCursor']
-            return job_list
-
-        soup = BeautifulSoup(response.content, "html.parser")
-        if "did not match any jobs" in response.text:
-            return job_list
-
-        jobs = IndeedScraper._parse_jobs(soup)
-        if not jobs:
-            return []
-        if (
-            not jobs.get("metaData", {})
-            .get("mosaicProviderJobCardsModel", {})
-            .get("results")
-        ):
-            logger.error("Indeed - No jobs found.")
-            return []
-
-        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=self.num_workers) as executor:
             job_results: list[Future] = [
-                executor.submit(self._process_job, job, job_detailed['job']) for job, job_detailed in zip(jobs, jobs_detailed)
+                executor.submit(self._process_job, job['job']) for job in jobs
-            ]
+           ]
-
         job_list = [result.result() for result in job_results if result.result()]
+        return job_list, new_cursor
 
-        return job_list
+    def _build_filters(self):
+        """
+        Builds the filters dict for job type/is_remote. If hours_old is provided, composite filter for job_type/is_remote is not possible.
+        IndeedApply: filters: { keyword: { field: "indeedApplyScope", keys: ["DESKTOP"] } }
+        """
+        filters_str = ""
+        if self.scraper_input.hours_old:
+            filters_str = """
+            filters: {{
+                date: {{
+                  field: "dateOnIndeed",
+                  start: "{start}h"
+                }}
+            }}
+            """.format(start=self.scraper_input.hours_old)
+        elif self.scraper_input.job_type or self.scraper_input.is_remote:
+            job_type_key_mapping = {
+                JobType.FULL_TIME: "CF3CP",
+                JobType.PART_TIME: "75GKK",
+                JobType.CONTRACT: "NJXCK",
+                JobType.INTERNSHIP: "VDTG7",
+            }
 
-    def _process_job(self, job: dict, job_detailed: dict) -> JobPost | None:
+            keys = []
-        job_url = f'{self.base_url}/m/jobs/viewjob?jk={job["jobkey"]}'
+            if self.scraper_input.job_type:
-        job_url_client = f'{self.base_url}/viewjob?jk={job["jobkey"]}'
+                key = job_type_key_mapping[self.scraper_input.job_type]
+                keys.append(key)
+
+            if self.scraper_input.is_remote:
+                keys.append("DSQF7")
+
+            if keys:
+                keys_str = '", "'.join(keys)  # Prepare your keys string
+                filters_str = f"""
+                filters: {{
+                  composite: {{
+                    filters: [{{
+                      keyword: {{
+                        field: "attributes",
+                        keys: ["{keys_str}"]
+                      }}
+                    }}]
+                  }}
+                }}
+                """
+        return filters_str
+
+    def _process_job(self, job: dict) -> JobPost | None:
+        """
+        Parses the job dict into JobPost model
+        :param job: dict to parse
+        :return: JobPost if it's a new job
+        """
+        job_url = f'{self.base_url}/viewjob?jk={job["key"]}'
         if job_url in self.seen_urls:
-            return None
+            return
         self.seen_urls.add(job_url)
-        description = job_detailed['description']['html']
+        description = job['description']['html']
         description = markdown_converter(description) if self.scraper_input.description_format == DescriptionFormat.MARKDOWN else description
-        job_type = self._get_job_type(job)
+
-        timestamp_seconds = job["pubDate"] / 1000
+        job_type = self._get_job_type(job['attributes'])
-        date_posted = datetime.fromtimestamp(timestamp_seconds)
+        timestamp_seconds = job["datePublished"] / 1000
-        date_posted = date_posted.strftime("%Y-%m-%d")
+        date_posted = datetime.fromtimestamp(timestamp_seconds).strftime("%Y-%m-%d")
+        employer = job['employer'].get('dossier') if job['employer'] else None
+        employer_details = employer.get('employerDetails', {}) if employer else {}
         return JobPost(
-            title=job["normTitle"],
+            title=job["title"],
             description=description,
-            company_name=job["company"],
+            company_name=job['employer'].get("name") if job.get('employer') else None,
-            company_url=f"{self.base_url}{job_detailed['employer']['relativeCompanyPageUrl']}" if job_detailed[
+            company_url=f"{self.base_url}{job['employer']['relativeCompanyPageUrl']}" if job[
                 'employer'] else None,
+            company_url_direct=employer['links']['corporateWebsite'] if employer else None,
+
             location=Location(
-                city=job.get("jobLocationCity"),
+                city=job.get("location", {}).get("city"),
-                state=job.get("jobLocationState"),
+                state=job.get("location", {}).get("admin1Code"),
-                country=self.scraper_input.country,
+                country=job.get("location", {}).get("countryCode"),
             ),
             job_type=job_type,
-            compensation=self._get_compensation(job, job_detailed),
+            compensation=self._get_compensation(job),
             date_posted=date_posted,
-            job_url=job_url_client,
+            job_url=job_url,
+            job_url_direct=job['recruit'].get('viewJobUrl') if job.get('recruit') else None,
             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_job_remote(job, description),
-            is_remote=self._is_job_remote(job, job_detailed, description)
+
+            company_addresses=employer_details['addresses'][0] if employer_details.get('addresses') else None,
+            company_industry=employer_details['industry'].replace('Iv1', '').replace('_', ' ').title() if employer_details.get('industry') else None,
+            company_num_employees=employer_details.get('employeesLocalizedLabel'),
+            company_revenue=employer_details.get('revenueLocalizedLabel'),
+            company_description=employer_details.get('briefDescription'),
+            ceo_name=employer_details.get('ceoName'),
+            ceo_photo_url=employer_details.get('ceoPhotoUrl'),
+
+            logo_photo_url=employer['images'].get('squareLogoUrl') if employer and employer.get('images') else None,
+            banner_photo_url=employer['images'].get('headerImageUrl') if employer and employer.get('images') else None,
         )
 
-    def _get_job_details(self, job_keys: list[str]) -> dict:
-        """
-        Queries the GraphQL endpoint for detailed job information for the given job keys.
-        """
-        job_keys_gql = '[' + ', '.join(f'"{key}"' for key in job_keys) + ']'
-        payload = dict(self.api_payload)
-        payload["query"] = self.api_payload["query"].format(job_keys_gql=job_keys_gql)
-        response = requests.post(self.api_url, headers=self.api_headers, json=payload, proxies=self.proxy)
-        if response.status_code == 200:
-            return response.json()['data']['jobData']['results']
-        else:
-            return {}
-
-    def _add_params(self, page: int) -> dict[str, str | Any]:
-        fromage = max(self.scraper_input.hours_old // 24, 1) if self.scraper_input.hours_old else None
-        params = {
-            "q": self.scraper_input.search_term,
-            "l": self.scraper_input.location if self.scraper_input.location else self.scraper_input.country.value[0].split(',')[-1],
-            "filter": 0,
-            "start": self.scraper_input.offset + page * 10,
-            "sort": "date",
-            "fromage": fromage,
-        }
-        if self.scraper_input.distance:
-            params["radius"] = self.scraper_input.distance
-
-        sc_values = []
-        if self.scraper_input.is_remote:
-            sc_values.append("attr(DSQF7)")
-        if self.scraper_input.job_type:
-            sc_values.append("jt({})".format(self.scraper_input.job_type.value[0]))
-
-        if sc_values:
-            params["sc"] = "0kf:" + "".join(sc_values) + ";"
-
-        if self.scraper_input.easy_apply:
-            params['iafilter'] = 1
-
-        return params
-
     @staticmethod
-    def _get_job_type(job: dict) -> list[JobType] | None:
+    def _get_job_type(attributes: list) -> list[JobType]:
         """
-        Parses the job to get list of job types
+        Parses the attributes to get list of job types
-        :param job:
+        :param attributes:
-        :return:
+        :return: list of JobType
         """
         job_types: list[JobType] = []
-        for taxonomy in job["taxonomyAttributes"]:
+        for attribute in attributes:
-            if taxonomy["label"] == "job-types":
+            job_type_str = attribute['label'].replace("-", "").replace(" ", "").lower()
-                for i in range(len(taxonomy["attributes"])):
+            job_type = get_enum_from_job_type(job_type_str)
-                    label = taxonomy["attributes"][i].get("label")
+            if job_type:
-                    if label:
+                job_types.append(job_type)
-                        job_type_str = label.replace("-", "").replace(" ", "").lower()
-                        job_type = get_enum_from_job_type(job_type_str)
-                        if job_type:
-                            job_types.append(job_type)
         return job_types
 
     @staticmethod
-    def _get_compensation(job: dict, job_detailed: dict) -> Compensation:
+    def _get_compensation(job: dict) -> Compensation | None:
         """
-        Parses the job to get
+        Parses the job to get compensation
+        :param job:
         :param job:
-        :param job_detailed:
         :return: compensation object
         """
-        comp = job_detailed['compensation']['baseSalary']
+        comp = job['compensation']['baseSalary']
         if comp:
-            interval = IndeedScraper._get_correct_interval(comp['unitOfWork'])
+            interval = IndeedScraper._get_compensation_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']
+                    currency=job['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:
+    def _is_job_remote(job: dict, description: str) -> bool:
         """
-        Parses the jobs from the soup object
+        Searches the description, location, and attributes to check if job is remote
-        :param soup:
-        :return: jobs
         """
-        def find_mosaic_script() -> Tag | None:
-            script_tags = soup.find_all("script")
-
-            for tag in script_tags:
-                if (
-                    tag.string
-                    and "mosaic.providerData" in tag.string
-                    and "mosaic-provider-jobcards" in tag.string
-                ):
-                    return tag
-            return None
-
-        script_tag = find_mosaic_script()
-        if script_tag:
-            script_str = script_tag.string
-            pattern = r'window.mosaic.providerData\["mosaic-provider-jobcards"\]\s*=\s*({.*?});'
-            p = re.compile(pattern, re.DOTALL)
-            m = p.search(script_str)
-            if m:
-                jobs = json.loads(m.group(1).strip())
-                return jobs
-            else:
-                logger.warning(f'Indeed: Could not find mosaic provider job cards data')
-                return {}
-        else:
-            logger.warning(f"Indeed: Could not parse any jobs on the page")
-            return {}
-
-    @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']
+            for attr in job['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()
+            keyword in job['location']['formatted']['long'].lower()
             for keyword in remote_keywords
         )
-        is_remote_in_taxonomy = any(
+        return is_remote_in_attributes or is_remote_in_description or is_remote_in_location
-            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
 
     @staticmethod
-    def _get_correct_interval(interval: str) -> CompensationInterval:
+    def _get_compensation_interval(interval: str) -> CompensationInterval:
         interval_mapping = {
             "DAY": "DAILY",
             "YEAR": "YEARLY",
@@ -343,16 +278,6 @@ class IndeedScraper(Scraper):
         else:
             raise ValueError(f"Unsupported interval: {interval}")
 
-    headers =  {
-      'Host': 'www.indeed.com',
-      'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
-      'sec-fetch-site': 'same-origin',
-      'sec-fetch-dest': 'document',
-      'accept-language': 'en-US,en;q=0.9',
-      'sec-fetch-mode': 'navigate',
-      '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 192.0',
-      'referer': 'https://www.indeed.com/m/jobs?q=software%20intern&l=Dallas%2C%20TX&from=serpso&rq=1&rsIdx=3',
-    }
     api_headers = {
         'Host': 'apis.indeed.com',
         'content-type': 'application/json',
@@ -362,24 +287,35 @@ class IndeedScraper(Scraper):
         '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',
     }
-    api_payload = {
+    job_search_query = """
-        "query": """
         query GetJobData {{
-          jobData(input: {{
+          jobSearch(
-            jobKeys: {job_keys_gql}
+            what: "{what}"
-          }}) {{
+            location: {{ where: "{location}", radius: {radius}, radiusUnit: MILES }}
+            includeSponsoredResults: NONE
+            limit: 100
+            sort: DATE
+            {cursor}
+            {filters}
+          ) {{
+            pageInfo {{
+              nextCursor
+            }}
             results {{
+              trackingKey
               job {{
                 key
                 title
+                datePublished
+                dateOnIndeed
                 description {{
                   html
                 }}
                 location {{
                   countryName
                   countryCode
+                  admin1Code
                   city
                   postalCode
                   streetAddress
@@ -401,10 +337,30 @@ class IndeedScraper(Scraper):
                   currencyCode
                 }}
                 attributes {{
+                  key
                   label
                 }}
                 employer {{
                   relativeCompanyPageUrl
+                  name
+                  dossier {{
+                      employerDetails {{
+                        addresses
+                        industry
+                        employeesLocalizedLabel
+                        revenueLocalizedLabel
+                        briefDescription
+                        ceoName
+                        ceoPhotoUrl
+                      }}
+                      images {{
+                            headerImageUrl
+                            squareLogoUrl
+                      }}
+                      links {{
+                        corporateWebsite
+                    }}
+                  }}
                 }}
                 recruit {{
                   viewJobUrl
@@ -416,4 +372,3 @@ class IndeedScraper(Scraper):
           }}
         }}
         """
-    }

src/jobspy/scrapers/linkedin/__init__.py

@@ -9,8 +9,6 @@ import random
 from typing import Optional
 from datetime import datetime
 
-import requests
-from requests.exceptions import ProxyError
 from threading import Lock
 from bs4.element import Tag
 from bs4 import BeautifulSoup
@@ -30,7 +28,6 @@ from ...jobs import (
 )
 from ..utils import (
     logger,
-    count_urgent_words,
     extract_emails_from_text,
     get_enum_from_job_type,
     currency_parser,
@@ -41,15 +38,16 @@ from ..utils import (
 class LinkedInScraper(Scraper):
     base_url = "https://www.linkedin.com"
     delay = 3
+    band_delay = 4
+    jobs_per_page = 25
 
     def __init__(self, proxy: Optional[str] = None):
         """
         Initializes LinkedInScraper with the LinkedIn job search url
         """
+        super().__init__(Site(Site.LINKEDIN), proxy=proxy)
         self.scraper_input = None
-        site = Site(Site.LINKEDIN)
         self.country = "worldwide"
-        super().__init__(site, proxy=proxy)
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
         """
@@ -68,8 +66,8 @@ class LinkedInScraper(Scraper):
             else None
         )
         continue_search = lambda: len(job_list) < scraper_input.results_wanted and page < 1000
-
         while continue_search():
+            logger.info(f'LinkedIn search page: {page // 25 + 1}')
             session = create_session(is_tls=False, has_retry=True, delay=5)
             params = {
                 "keywords": scraper_input.search_term,
@@ -83,8 +81,9 @@ class LinkedInScraper(Scraper):
                 "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}",
             }
+            if seconds_old is not None:
+                params["f_TPR"] = f"r{seconds_old}"
 
             params = {k: v for k, v in params.items() if v is not None}
             try:
@@ -101,13 +100,13 @@ class LinkedInScraper(Scraper):
                         logger.error(f'429 Response - Blocked by LinkedIn for too many requests')
                     else:
                         logger.error(f'LinkedIn response status code {response.status_code}')
-                    return JobResponse(job_list=job_list)
+                    return JobResponse(jobs=job_list)
             except Exception as e:
                 if "Proxy responded with" in str(e):
                     logger.error(f'LinkedIn: Bad proxy')
                 else:
                     logger.error(f'LinkedIn: {str(e)}')
-                return JobResponse(job_list=job_list)
+                return JobResponse(jobs=job_list)
 
             soup = BeautifulSoup(response.text, "html.parser")
             job_cards = soup.find_all("div", class_="base-search-card")
@@ -136,8 +135,8 @@ class LinkedInScraper(Scraper):
                     raise LinkedInException(str(e))
 
             if continue_search():
-                time.sleep(random.uniform(self.delay, self.delay + 2))
+                time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
-                page += 25
+                page += self.jobs_per_page
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
@@ -187,7 +186,6 @@ class LinkedInScraper(Scraper):
             except:
                 date_posted = None
         benefits_tag = job_card.find("span", class_="result-benefits__text")
-        benefits = " ".join(benefits_tag.get_text().split()) if benefits_tag else None
         if full_descr:
             description, job_type = self._get_job_description(job_url)
 
@@ -199,11 +197,9 @@ class LinkedInScraper(Scraper):
             date_posted=date_posted,
             job_url=job_url,
             compensation=compensation,
-            benefits=benefits,
             job_type=job_type,
             description=description,
             emails=extract_emails_from_text(description) if description else None,
-            num_urgent_words=count_urgent_words(description) if description else None,
         )
 
     def _get_job_description(

src/jobspy/scrapers/utils.py

@@ -1,49 +1,29 @@
-import re
 import logging
-import numpy as np
+import re
 
-import html2text
+import numpy as np
-import tls_client
 import requests
+import tls_client
+from markdownify import markdownify as md
 from requests.adapters import HTTPAdapter, Retry
 
 from ..jobs import JobType
 
-text_maker = html2text.HTML2Text()
 logger = logging.getLogger("JobSpy")
 logger.propagate = False
 if not logger.handlers:
-    logger.setLevel(logging.ERROR)
+    logger.setLevel(logging.INFO)
     console_handler = logging.StreamHandler()
-    console_handler.setLevel(logging.ERROR)
     formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
     console_handler.setFormatter(formatter)
     logger.addHandler(console_handler)
 
 
-def count_urgent_words(description: str) -> int:
-    """
-    Count the number of urgent words or phrases in a job description.
-    """
-    urgent_patterns = re.compile(
-        r"\burgen(t|cy)|\bimmediate(ly)?\b|start asap|\bhiring (now|immediate(ly)?)\b",
-        re.IGNORECASE,
-    )
-    matches = re.findall(urgent_patterns, description)
-    count = len(matches)
-
-    return count
-
-
 def markdown_converter(description_html: str):
     if description_html is None:
-        return ""
+        return None
-    text_maker.ignore_links = False
+    markdown = md(description_html)
-    try:
+    return markdown.strip()
-        markdown = text_maker.handle(description_html)
-        return markdown.strip()
-    except AssertionError as e:
-        return ""
 
 
 def extract_emails_from_text(text: str) -> list[str] | None:

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -14,7 +14,6 @@ from concurrent.futures import ThreadPoolExecutor
 from .. import Scraper, ScraperInput, Site
 from ..utils import (
     logger,
-    count_urgent_words,
     extract_emails_from_text,
     create_session,
     markdown_converter
@@ -63,7 +62,7 @@ class ZipRecruiterScraper(Scraper):
                 break
             if page > 1:
                 time.sleep(self.delay)
-
+            logger.info(f'ZipRecruiter search page: {page}')
             jobs_on_page, continue_token = self._find_jobs_in_page(
                 scraper_input, continue_token
             )
@@ -161,7 +160,6 @@ class ZipRecruiterScraper(Scraper):
             job_url=job_url,
             description=description,
             emails=extract_emails_from_text(description) if description else None,
-            num_urgent_words=count_urgent_words(description) if description else None,
         )
 
     def _get_cookies(self):