Description format (#107)

* fix(ziprecruiter): pagination

* chore: version

README.md

@@ -11,7 +11,7 @@ work with us.*
 
 - Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, & **ZipRecruiter** simultaneously
 - Aggregates the job postings in a Pandas DataFrame
-- Proxy support (HTTP/S, SOCKS)
+- Proxy support
 
 [Video Guide for JobSpy](https://www.youtube.com/watch?v=RuP1HrAZnxs&pp=ygUgam9icyBzY3JhcGVyIGJvdCBsaW5rZWRpbiBpbmRlZWQ%3D) -
 Updated for release v1.1.3
@@ -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
@@ -65,13 +67,16 @@ Optional
 ├── location (int)
 ├── distance (int): in miles
 ├── job_type (enum): fulltime, parttime, internship, contract
-├── proxy (str): in format 'http://user:pass@host:port' or [https, socks]
+├── proxy (str): in format 'http://user:pass@host:port'
 ├── is_remote (bool)
-├── full_description (bool): fetches full description for Indeed / LinkedIn (much slower)
+├── linkedin_fetch_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 LinkedIn, Glassdoor
+├── 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
+├── 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)
 ```
 
 ### JobPost Schema
@@ -80,6 +85,7 @@ Optional
 JobPost
 ├── title (str)
 ├── company (str)
+├── company_url (str)
 ├── job_url (str)
 ├── location (object)
 │   ├── country (str)
@@ -158,16 +164,11 @@ persist, [submit an issue](https://github.com/Bunsly/JobSpy/issues).
 **Q: Received a response code 429?**  
 **A:** This indicates that you have been blocked by the job board site for sending too many requests. All of the job board sites are aggressive with blocking. We recommend:
 
-- Waiting a few seconds between requests.
+- Waiting some time between scrapes (site-dependent).
 - Trying a VPN or proxy to change your IP address.
 
 ---
 
-**Q: Experiencing a "Segmentation fault: 11" on macOS Catalina?**  
-**A:** This is due to `tls_client` dependency not supporting your architecture. Solutions and workarounds include:
-
-- Upgrade to a newer version of MacOS
-- Reach out to the maintainers of [tls_client](https://github.com/bogdanfinn/tls-client) for fixes
 
 
   

poetry.lock

@@ -524,6 +524,17 @@ 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"
@@ -2435,4 +2446,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "404a77d78066cbb2ef71015562baf44aa11d12aac29a191c1ccc7758bfda598a"
+content-hash = "40cdc19a57cba0d21ff4f0fcfa53e14a073fcccd9f2a871440e056ab6e8fade0"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.37"
+version = "1.1.45"
 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"
@@ -18,6 +18,7 @@ beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"
 NUMPY = "1.24.2"
 pydantic = "^2.3.0"
+html2text = "^2020.1.16"
 
 
 [tool.poetry.group.dev.dependencies]

src/jobspy/__init__.py

@@ -1,7 +1,6 @@
 import pandas as pd
-import concurrent.futures
-from concurrent.futures import ThreadPoolExecutor
-from typing import Tuple, Optional
+from typing import Tuple
+from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from .jobs import JobType, Location
 from .scrapers.indeed import IndeedScraper
@@ -16,37 +15,39 @@ from .scrapers.exceptions import (
     GlassdoorException,
 )
 
-SCRAPER_MAPPING = {
-    Site.LINKEDIN: LinkedInScraper,
-    Site.INDEED: IndeedScraper,
-    Site.ZIP_RECRUITER: ZipRecruiterScraper,
-    Site.GLASSDOOR: GlassdoorScraper,
-}
-
-
-def _map_str_to_site(site_name: str) -> Site:
-    return Site[site_name.upper()]
-
 
 def scrape_jobs(
-    site_name: str | list[str] | Site | list[Site],
-    search_term: str,
-    location: str = "",
-    distance: int = None,
+    site_name: str | list[str] | Site | list[Site] | None = None,
+    search_term: str | None = None,
+    location: str | None = None,
+    distance: int | None = None,
     is_remote: bool = False,
-    job_type: str = None,
-    easy_apply: bool = False,  # linkedin
+    job_type: str | None = None,
+    easy_apply: bool | None = None,
     results_wanted: int = 15,
     country_indeed: str = "usa",
     hyperlinks: bool = False,
-    proxy: Optional[str] = None,
-    full_description: Optional[bool] = False,
-    offset: Optional[int] = 0,
+    proxy: str | None = None,
+    description_format: str = "markdown",
+    linkedin_fetch_description: bool | None = False,
+    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.
     :return: results_wanted: pandas dataframe containing job data
     """
+    SCRAPER_MAPPING = {
+        Site.LINKEDIN: LinkedInScraper,
+        Site.INDEED: IndeedScraper,
+        Site.ZIP_RECRUITER: ZipRecruiterScraper,
+        Site.GLASSDOOR: GlassdoorScraper,
+    }
+
+    def map_str_to_site(site_name: str) -> Site:
+        return Site[site_name.upper()]
 
     def get_enum_from_value(value_str):
         for job_type in JobType:
@@ -56,18 +57,22 @@ def scrape_jobs(
 
     job_type = get_enum_from_value(job_type) if job_type else None
 
-    if type(site_name) == str:
-        site_type = [_map_str_to_site(site_name)]
-    else:  #: if type(site_name) == list
-        site_type = [
-            _map_str_to_site(site) if type(site) == str else site_name
-            for site in site_name
-        ]
-
+    def get_site_type():
+        site_types = list(Site)
+        if isinstance(site_name, str):
+            site_types = [map_str_to_site(site_name)]
+        elif isinstance(site_name, Site):
+            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,
@@ -75,30 +80,18 @@ def scrape_jobs(
         is_remote=is_remote,
         job_type=job_type,
         easy_apply=easy_apply,
-        full_description=full_description,
+        description_format=description_format,
+        linkedin_fetch_description=linkedin_fetch_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]:
         scraper_class = SCRAPER_MAPPING[site]
         scraper = scraper_class(proxy=proxy)
-
-        try:
-            scraped_data: JobResponse = scraper.scrape(scraper_input)
-        except (LinkedInException, IndeedException, ZipRecruiterException) as lie:
-            raise lie
-        except Exception as e:
-            if site == Site.LINKEDIN:
-                raise LinkedInException(str(e))
-            if site == Site.INDEED:
-                raise IndeedException(str(e))
-            if site == Site.ZIP_RECRUITER:
-                raise ZipRecruiterException(str(e))
-            if site == Site.GLASSDOOR:
-                raise GlassdoorException(str(e))
-            else:
-                raise e
+        scraped_data: JobResponse = scraper.scrape(scraper_input)
         return site.value, scraped_data
 
     site_to_jobs_dict = {}
@@ -112,7 +105,7 @@ 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
 
@@ -179,8 +172,6 @@ def scrape_jobs(
             "emails",
             "description",
         ]
-        jobs_formatted_df = jobs_df[desired_order]
+        return jobs_df[desired_order].sort_values(by=['site', 'date_posted'], ascending=[True, False])
     else:
-        jobs_formatted_df = pd.DataFrame()
-
-    return jobs_formatted_df
+        return pd.DataFrame()

src/jobspy/jobs/__init__.py

@@ -193,16 +193,28 @@ 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
-    max_amount: int | None = None
+    min_amount: float | None = None
+    max_amount: float | None = None
     currency: Optional[str] = "USD"
 
 
+class DescriptionFormat(Enum):
+    MARKDOWN = "markdown"
+    HTML = "html"
+
+
 class JobPost(BaseModel):
     title: str
     company_name: str

src/jobspy/scrapers/__init__.py

@@ -1,5 +1,11 @@
-from ..jobs import Enum, BaseModel, JobType, JobResponse, Country
-from typing import List, Optional, Any
+from ..jobs import (
+    Enum,
+    BaseModel,
+    JobType,
+    JobResponse,
+    Country,
+    DescriptionFormat
+)
 
 
 class Site(Enum):
@@ -10,25 +16,27 @@ class Site(Enum):
 
 
 class ScraperInput(BaseModel):
-    site_type: List[Site]
-    search_term: str
+    site_type: list[Site]
+    search_term: str | None = None
 
-    location: str = None
-    country: Optional[Country] = Country.USA
-    distance: Optional[int] = None
+    location: str | None = None
+    country: Country | None = Country.USA
+    distance: int | None = None
     is_remote: bool = False
-    job_type: Optional[JobType] = None
-    easy_apply: bool = None  # linkedin
-    full_description: bool = False
+    job_type: JobType | None = None
+    easy_apply: bool | None = None
     offset: int = 0
+    linkedin_fetch_description: bool = False
+    linkedin_company_ids: list[int] | None = None
+    description_format: DescriptionFormat | None = DescriptionFormat.MARKDOWN
 
     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 +13,11 @@ 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,
+    markdown_converter,
+    logger
+)
 from ...jobs import (
     JobPost,
     Compensation,
@@ -22,6 +25,7 @@ from ...jobs import (
     Location,
     JobResponse,
     JobType,
+    DescriptionFormat
 )
 
 
@@ -33,12 +37,57 @@ class GlassdoorScraper(Scraper):
         site = Site(Site.GLASSDOOR)
         super().__init__(site, proxy=proxy)
 
-        self.url = None
+        self.base_url = None
         self.country = None
+        self.session = None
+        self.scraper_input = None
         self.jobs_per_page = 30
         self.seen_urls = set()
 
-    def fetch_jobs_page(
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+        """
+        Scrapes Glassdoor for jobs with scraper_input criteria.
+        :param scraper_input: Information about job search criteria.
+        :return: JobResponse containing a list of jobs.
+        """
+        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()
+
+        location_id, location_type = self._get_location(
+            scraper_input.location, scraper_input.is_remote
+        )
+        if location_type is None:
+            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(
+                1 + (scraper_input.offset // self.jobs_per_page),
+                min(
+                    (scraper_input.results_wanted // self.jobs_per_page) + 2,
+                    max_pages + 1,
+                ),
+            ):
+                try:
+                    jobs, cursor = self._fetch_jobs_page(
+                        scraper_input, location_id, location_type, page, cursor
+                    )
+                    all_jobs.extend(jobs)
+                    if len(all_jobs) >= scraper_input.results_wanted:
+                        all_jobs = all_jobs[: scraper_input.results_wanted]
+                        break
+                except Exception as e:
+                    raise GlassdoorException(str(e))
+        except Exception as e:
+            raise GlassdoorException(str(e))
+        return JobResponse(jobs=all_jobs)
+
+    def _fetch_jobs_page(
         self,
         scraper_input: ScraperInput,
         location_id: int,
@@ -49,13 +98,13 @@ class GlassdoorScraper(Scraper):
         """
         Scrapes a page of Glassdoor for jobs with scraper_input criteria
         """
+        self.scraper_input = scraper_input
         try:
-            payload = self.add_payload(
-                scraper_input, location_id, location_type, page_num, cursor
+            payload = self._add_payload(
+                location_id, location_type, page_num, cursor
             )
-            session = create_session(self.proxy, is_tls=False, has_retry=True)
-            response = session.post(
-                f"{self.url}/graph", headers=self.headers(), timeout=10, data=payload
+            response = self.session.post(
+                f"{self.base_url}/graph", headers=self.headers, timeout=10, data=payload
             )
             if response.status_code != 200:
                 raise GlassdoorException(
@@ -71,9 +120,8 @@ class GlassdoorScraper(Scraper):
 
         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}
+            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:
@@ -85,10 +133,12 @@ class GlassdoorScraper(Scraper):
             res_json["data"]["jobListings"]["paginationCursors"], page_num + 1
         )
 
-    def process_job(self, job_data):
-        """Processes a single job and fetches its description."""
+    def _process_job(self, job_data):
+        """
+        Processes a single job and fetches its description.
+        """
         job_id = job_data["jobview"]["job"]["listingId"]
-        job_url = f'{self.url}job-listing/j?jl={job_id}'
+        job_url = f'{self.base_url}job-listing/j?jl={job_id}'
         if job_url in self.seen_urls:
             return None
         self.seen_urls.add(job_url)
@@ -100,7 +150,7 @@ 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
@@ -108,15 +158,13 @@ class GlassdoorScraper(Scraper):
             location = self.parse_location(location_name)
 
         compensation = self.parse_compensation(job["header"])
-
         try:
-            description = self.fetch_job_description(job_id)
-        except Exception as e :
+            description = self._fetch_job_description(job_id)
+        except:
             description = None
-
-        job_post = JobPost(
+        return JobPost(
             title=title,
-            company_url=f"{self.url}Overview/W-EI_IE{company_id}.htm" if company_id else None,
+            company_url=f"{self.base_url}Overview/W-EI_IE{company_id}.htm" if company_id else None,
             company_name=company_name,
             date_posted=date_posted,
             job_url=job_url,
@@ -127,51 +175,12 @@ class GlassdoorScraper(Scraper):
             emails=extract_emails_from_text(description) if description else None,
             num_urgent_words=count_urgent_words(description) if description else None,
         )
-        return job_post
 
-    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+    def _fetch_job_description(self, job_id):
         """
-        Scrapes Glassdoor for jobs with scraper_input criteria.
-        :param scraper_input: Information about job search criteria.
-        :return: JobResponse containing a list of jobs.
+        Fetches the job description for a single job ID.
         """
-        scraper_input.results_wanted = min(900, scraper_input.results_wanted)
-        self.country = scraper_input.country
-        self.url = self.country.get_url()
-
-        location_id, location_type = self.get_location(
-            scraper_input.location, scraper_input.is_remote
-        )
-        all_jobs: list[JobPost] = []
-        cursor = None
-        max_pages = 30
-
-        try:
-            for page in range(
-                1 + (scraper_input.offset // self.jobs_per_page),
-                min(
-                    (scraper_input.results_wanted // self.jobs_per_page) + 2,
-                    max_pages + 1,
-                ),
-            ):
-                try:
-                    jobs, cursor = self.fetch_jobs_page(
-                        scraper_input, location_id, location_type, page, cursor
-                    )
-                    all_jobs.extend(jobs)
-                    if len(all_jobs) >= scraper_input.results_wanted:
-                        all_jobs = all_jobs[: scraper_input.results_wanted]
-                        break
-                except Exception as e:
-                    raise GlassdoorException(str(e))
-        except Exception as e:
-            raise GlassdoorException(str(e))
-
-        return JobResponse(jobs=all_jobs)
-
-    def fetch_job_description(self, job_id):
-        """Fetches the job description for a single job ID."""
-        url = f"{self.url}/graph"
+        url = f"{self.base_url}/graph"
         body = [
             {
                 "operationName": "JobDetailQuery",
@@ -196,20 +205,245 @@ class GlassdoorScraper(Scraper):
                 """
             }
         ]
-        response = requests.post(url, json=body, headers=GlassdoorScraper.headers())
-        if response.status_code != 200:
+        res = requests.post(url, json=body, headers=self.headers)
+        if res.status_code != 200:
             return None
-        data = response.json()[0]
+        data = res.json()[0]
         desc = data['data']['jobview']['job']['description']
-        soup = BeautifulSoup(desc, 'html.parser')
-        return modify_and_get_description(soup)
+        return markdown_converter(desc) if self.scraper_input.description_format == DescriptionFormat.MARKDOWN else desc
+
+    def _get_location(self, location: str, is_remote: bool) -> (int, str):
+        if not location or is_remote:
+            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)
+        if res.status_code != 200:
+            if res.status_code == 429:
+                logger.error(f'429 Response - Blocked by Glassdoor for too many requests')
+                return None, None
+            else:
+                logger.error(f'Glassdoor response status code {res.status_code}')
+                return None, None
+        items = res.json()
+
+        if not items:
+            raise ValueError(f"Location '{location}' not found on Glassdoor")
+        location_type = items[0]["locationType"]
+        if location_type == "C":
+            location_type = "CITY"
+        elif location_type == "S":
+            location_type = "STATE"
+        elif location_type == 'N':
+            location_type = "COUNTRY"
+        return int(items[0]["locationId"]), location_type
+
+    def _add_payload(
+        self,
+        location_id: int,
+        location_type: str,
+        page_num: int,
+        cursor: str | None = None,
+    ) -> str:
+        fromage = max(self.scraper_input.hours_old // 24, 1) if self.scraper_input.hours_old else None
+        filter_params = []
+        if self.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": filter_params,
+                "keyword": self.scraper_input.search_term,
+                "numJobsToShow": 30,
+                "locationType": location_type,
+                "locationId": int(location_id),
+                "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
+            ) {
+                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
+            }
+            """
+        }
+        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
 
@@ -220,7 +454,6 @@ class GlassdoorScraper(Scraper):
             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,
@@ -228,65 +461,6 @@ class GlassdoorScraper(Scraper):
             currency=currency,
         )
 
-    def get_location(self, location: str, is_remote: bool) -> (int, str):
-        if not location or is_remote:
-            return "11047", "STATE"  # remote options
-        url = f"{self.url}/findPopularLocationAjax.htm?maxLocationsToReturn=10&term={location}"
-        session = create_session(self.proxy, has_retry=True)
-        response = session.get(url)
-        if response.status_code != 200:
-            raise GlassdoorException(
-                f"bad response status code: {response.status_code}"
-            )
-        items = response.json()
-        if not items:
-            raise ValueError(f"Location '{location}' not found on Glassdoor")
-        location_type = items[0]["locationType"]
-        if location_type == "C":
-            location_type = "CITY"
-        elif location_type == "S":
-            location_type = "STATE"
-        return int(items[0]["locationId"]), location_type
-
-    @staticmethod
-    def add_payload(
-        scraper_input,
-        location_id: int,
-        location_type: str,
-        page_num: int,
-        cursor: str | None = None,
-    ) -> str:
-        payload = {
-            "operationName": "JobSearchResultsQuery",
-            "variables": {
-                "excludeJobListingIds": [],
-                "filterParams": [{"filterKey": "applicationType", "values": "1"}] if scraper_input.easy_apply else [],
-                "keyword": scraper_input.search_term,
-                "numJobsToShow": 30,
-                "locationType": location_type,
-                "locationId": int(location_id),
-                "parameterUrlInput": f"IL.0,12_I{location_type}{location_id}",
-                "pageNumber": page_num,
-                "pageCursor": cursor,
-            },
-            "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",
-        }
-
-        job_type_filters = {
-            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}
-            )
-        return json.dumps([payload])
-
     @staticmethod
     def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
         for job_type in JobType:
@@ -306,28 +480,21 @@ class GlassdoorScraper(Scraper):
             if cursor_data["pageNumber"] == page_num:
                 return cursor_data["cursor"]
 
-    @staticmethod
-    def headers() -> dict:
-        """
-        Returns headers needed for requests
-        :return: dict - Dictionary containing headers
-        """
-        return {
-            "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",
-            "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/",
-            "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",
-        }
+    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

@@ -6,11 +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
@@ -21,7 +21,8 @@ from ..utils import (
     extract_emails_from_text,
     create_session,
     get_enum_from_job_type,
-    modify_and_get_description
+    markdown_converter,
+    logger
 )
 from ...jobs import (
     JobPost,
@@ -30,6 +31,7 @@ from ...jobs import (
     Location,
     JobResponse,
     JobType,
+    DescriptionFormat
 )
 from .. import Scraper, ScraperInput, Site
 
@@ -39,219 +41,183 @@ class IndeedScraper(Scraper):
         """
         Initializes IndeedScraper with the Indeed job search url
         """
-        self.url = None
-        self.country = None
+        self.scraper_input = None
+        self.jobs_per_page = 25
+        self.num_workers = 10
+        self.seen_urls = set()
+        self.base_url = None
+        self.api_url = "https://apis.indeed.com/graphql"
         site = Site(Site.INDEED)
         super().__init__(site, proxy=proxy)
 
-        self.jobs_per_page = 15
-        self.seen_urls = set()
-
-    def scrape_page(
-        self, scraper_input: ScraperInput, page: int
-    ) -> tuple[list[JobPost], int]:
-        """
-        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
-        """
-        self.country = scraper_input.country
-        domain = self.country.indeed_domain_value
-        self.url = f"https://{domain}.indeed.com"
-
-        params = {
-            "q": scraper_input.search_term,
-            "l": scraper_input.location,
-            "filter": 0,
-            "start": scraper_input.offset + page * 10,
-            "sort": "date"
-        }
-        if scraper_input.distance:
-            params["radius"] = scraper_input.distance
-
-        sc_values = []
-        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))
-
-        if sc_values:
-            params["sc"] = "0kf:" + "".join(sc_values) + ";"
-        try:
-            session = create_session(self.proxy)
-            response = session.get(
-                f"{self.url}/jobs",
-                headers=self.get_headers(),
-                params=params,
-                allow_redirects=True,
-                timeout_seconds=10,
-            )
-            if response.status_code not in range(200, 400):
-                raise IndeedException(
-                    f"bad response with status code: {response.status_code}"
-                )
-        except Exception as e:
-            if "Proxy responded with" in str(e):
-                raise IndeedException("bad proxy")
-            raise IndeedException(str(e))
-
-        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")
-
-        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", {})
-            .get("mosaicProviderJobCardsModel", {})
-            .get("results")
-        ):
-            raise IndeedException("No jobs found.")
-
-        def process_job(job) -> JobPost | None:
-            job_url = f'{self.url}/jobs/viewjob?jk={job["jobkey"]}'
-            job_url_client = f'{self.url}/viewjob?jk={job["jobkey"]}'
-            if job_url in self.seen_urls:
-                return None
-
-            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,
-                location=Location(
-                    city=job.get("jobLocationCity"),
-                    state=job.get("jobLocationState"),
-                    country=self.country,
-                ),
-                job_type=job_type,
-                compensation=compensation,
-                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),
-            )
-            return job_post
-
-        jobs = jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]
-        with ThreadPoolExecutor(max_workers=1) as executor:
-            job_results: list[Future] = [
-                executor.submit(process_job, job) for job in jobs
-            ]
-
-        job_list = [result.result() for result in job_results if result.result()]
-
-        return job_list, total_num_jobs
-
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
         """
         Scrapes Indeed for jobs with scraper_input criteria
         :param scraper_input:
         :return: job_response
         """
-        pages_to_process = (
-            math.ceil(scraper_input.results_wanted / self.jobs_per_page) - 1
-        )
+        self.scraper_input = scraper_input
+        job_list = self._scrape_page()
+        pages_processed = 1
 
-        #: get first page to initialize session
-        job_list, total_results = self.scrape_page(scraper_input, 0)
+        while len(self.seen_urls) < scraper_input.results_wanted:
+            pages_to_process = math.ceil((scraper_input.results_wanted - len(self.seen_urls)) / self.jobs_per_page)
+            new_jobs = False
 
-        with ThreadPoolExecutor(max_workers=1) as executor:
-            futures: list[Future] = [
-                executor.submit(self.scrape_page, scraper_input, page)
-                for page in range(1, pages_to_process + 1)
-            ]
+            with ThreadPoolExecutor(max_workers=10) as executor:
+                futures: list[Future] = [
+                    executor.submit(self._scrape_page, page + pages_processed)
+                    for page in range(pages_to_process)
+                ]
 
-            for future in futures:
-                jobs, _ = future.result()
+                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
 
-                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(
-            jobs=job_list,
-            total_results=total_results,
-        )
-        return job_response
+        if len(self.seen_urls) > scraper_input.results_wanted:
+            job_list = job_list[:scraper_input.results_wanted]
 
-    def get_description(self, job_page_url: str) -> str | None:
+        return JobResponse(jobs=job_list)
+
+    def _scrape_page(self, page: int=0) -> list[JobPost]:
         """
-        Retrieves job description by going to the job page url
-        :param job_page_url:
-        :return: description
+        Scrapes a page of Indeed for jobs with scraper_input criteria
+        :param page:
+        :return: jobs found on page, total number of jobs found for search
         """
-        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}/viewjob?jk={jk_value}&spa=1"
-        session = create_session(self.proxy)
+        job_list = []
+        domain = self.scraper_input.country.indeed_domain_value
+        self.base_url = f"https://{domain}.indeed.com"
 
         try:
+            session = create_session(self.proxy)
             response = session.get(
-                formatted_url,
-                headers=self.get_headers(),
-                allow_redirects=True,
-                timeout_seconds=5,
+                f"{self.base_url}/m/jobs",
+                headers=self.headers,
+                params=self._add_params(page),
             )
+            if response.status_code not in range(200, 400):
+                if response.status_code == 429:
+                    logger.error(f'429 Response - Blocked by Indeed for too many requests')
+                else:
+                    logger.error(f'Indeed response status code {response.status_code}')
+                return job_list
+
         except Exception as e:
-            return None
+            if "Proxy responded with" in str(e):
+                logger.error(f'Indeed: Bad proxy')
+            else:
+                logger.error(f'Indeed: {str(e)}')
+            return job_list
 
-        if response.status_code not in range(200, 400):
-            return None
+        soup = BeautifulSoup(response.content, "html.parser")
+        if "did not match any jobs" in response.text:
+            return job_list
 
-        try:
-            data = json.loads(response.text)
-            job_description = data["body"]["jobInfoWrapperModel"]["jobInfoModel"][
-                "sanitizedJobDescription"
+        jobs = IndeedScraper._parse_jobs(soup)
+        if (
+            not jobs.get("metaData", {})
+            .get("mosaicProviderJobCardsModel", {})
+            .get("results")
+        ):
+            raise IndeedException("No jobs found.")
+
+        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)
             ]
-        except (KeyError, TypeError, IndexError):
-            return None
 
-        soup = BeautifulSoup(job_description, "html.parser")
-        return modify_and_get_description(soup)
+        job_list = [result.result() for result in job_results if result.result()]
+
+        return job_list
+
+    def _process_job(self, job: dict, job_detailed: dict) -> JobPost | None:
+        job_url = f'{self.base_url}/m/jobs/viewjob?jk={job["jobkey"]}'
+        job_url_client = f'{self.base_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']
+        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
+        date_posted = datetime.fromtimestamp(timestamp_seconds)
+        date_posted = date_posted.strftime("%Y-%m-%d")
+        return JobPost(
+            title=job["normTitle"],
+            description=description,
+            company_name=job["company"],
+            company_url=f"{self.base_url}{job_detailed['employer']['relativeCompanyPageUrl']}" if job_detailed[
+                'employer'] else None,
+            location=Location(
+                city=job.get("jobLocationCity"),
+                state=job.get("jobLocationState"),
+                country=self.scraper_input.country,
+            ),
+            job_type=job_type,
+            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_job_remote(job, job_detailed, description)
+        )
+
+    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(job: dict) -> list[JobType] | None:
         """
         Parses the job to get list of job types
         :param job:
@@ -270,18 +236,51 @@ class IndeedScraper(Scraper):
         return job_types
 
     @staticmethod
-    def parse_jobs(soup: BeautifulSoup) -> dict:
+    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:
         """
         Parses the jobs from the soup object
         :param soup:
         :return: jobs
         """
-
         def find_mosaic_script() -> Tag | None:
-            """
-            Finds jobcards script tag
-            :return: script_tag
-            """
             script_tags = soup.find_all("script")
 
             for tag in script_tags:
@@ -294,7 +293,6 @@ class IndeedScraper(Scraper):
             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*({.*?});'
@@ -311,46 +309,109 @@ class IndeedScraper(Scraper):
             )
 
     @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
+    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
 
     @staticmethod
-    def get_headers():
-        return {
-            "authority": "www.indeed.com",
-            "accept": "*/*",
-            "accept-language": "en-US,en;q=0.9",
-            "referer": "https://www.indeed.com/viewjob?jk=fe6182337d72c7b1&tk=1hcbfcmd0k62t802&from=serp&vjs=3&advn=8132938064490989&adid=408692607&ad=-6NYlbfkN0A3Osc99MJFDKjquSk4WOGT28ALb_ad4QMtrHreCb9ICg6MiSVy9oDAp3evvOrI7Q-O9qOtQTg1EPbthP9xWtBN2cOuVeHQijxHjHpJC65TjDtftH3AXeINjBvAyDrE8DrRaAXl8LD3Fs1e_xuDHQIssdZ2Mlzcav8m5jHrA0fA64ZaqJV77myldaNlM7-qyQpy4AsJQfvg9iR2MY7qeC5_FnjIgjKIy_lNi9OPMOjGRWXA94CuvC7zC6WeiJmBQCHISl8IOBxf7EdJZlYdtzgae3593TFxbkd6LUwbijAfjax39aAuuCXy3s9C4YgcEP3TwEFGQoTpYu9Pmle-Ae1tHGPgsjxwXkgMm7Cz5mBBdJioglRCj9pssn-1u1blHZM4uL1nK9p1Y6HoFgPUU9xvKQTHjKGdH8d4y4ETyCMoNF4hAIyUaysCKdJKitC8PXoYaWhDqFtSMR4Jys8UPqUV&xkcb=SoDD-_M3JLQfWnQTDh0LbzkdCdPP&xpse=SoBa6_I3JLW9FlWZlB0PbzkdCdPP&sjdu=i6xVERweJM_pVUvgf-MzuaunBTY7G71J5eEX6t4DrDs5EMPQdODrX7Nn-WIPMezoqr5wA_l7Of-3CtoiUawcHw",
-            "sec-ch-ua": '"Google Chrome";v="119", "Chromium";v="119", "Not?A_Brand";v="24"',
-            "sec-ch-ua-mobile": "?0",
-            "sec-ch-ua-platform": '"Windows"',
-            "sec-fetch-dest": "empty",
-            "sec-fetch-mode": "cors",
-            "sec-fetch-site": "same-origin",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+    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}")
 
-    @staticmethod
-    def is_remote_job(job: dict) -> bool:
+    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',
+        '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',
+    }
+    api_payload = {
+        "query": """
+        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
+                }}
+              }}
+            }}
+          }}
+        }}
         """
-        :param job:
-        :return: bool
-        """
-        for taxonomy in job.get("taxonomyAttributes", []):
-            if taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0:
-                return True
-        return False
+    }

src/jobspy/scrapers/linkedin/__init__.py

@@ -25,27 +25,30 @@ from ...jobs import (
     JobResponse,
     JobType,
     Country,
-    Compensation
+    Compensation,
+    DescriptionFormat
 )
 from ..utils import (
+    logger,
     count_urgent_words,
     extract_emails_from_text,
     get_enum_from_job_type,
     currency_parser,
-    modify_and_get_description
+    markdown_converter
 )
 
 
 class LinkedInScraper(Scraper):
-    DELAY = 3
+    base_url = "https://www.linkedin.com"
+    delay = 3
 
     def __init__(self, proxy: Optional[str] = None):
         """
         Initializes LinkedInScraper with the LinkedIn job search url
         """
+        self.scraper_input = None
         site = Site(Site.LINKEDIN)
         self.country = "worldwide"
-        self.url = "https://www.linkedin.com"
         super().__init__(site, proxy=proxy)
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
@@ -54,55 +57,57 @@ class LinkedInScraper(Scraper):
         :param scraper_input:
         :return: job_response
         """
+        self.scraper_input = scraper_input
         job_list: list[JobPost] = []
         seen_urls = set()
         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
+        )
+        continue_search = lambda: len(job_list) < scraper_input.results_wanted and page < 1000
 
-        def job_type_code(job_type_enum):
-            mapping = {
-                JobType.FULL_TIME: "F",
-                JobType.PART_TIME: "P",
-                JobType.INTERNSHIP: "I",
-                JobType.CONTRACT: "C",
-                JobType.TEMPORARY: "T",
-            }
-
-            return mapping.get(job_type_enum, "")
-
-        while 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,
                 "location": scraper_input.location,
                 "distance": scraper_input.distance,
                 "f_WT": 2 if scraper_input.is_remote else None,
-                "f_JT": job_type_code(scraper_input.job_type)
+                "f_JT": self.job_type_code(scraper_input.job_type)
                 if scraper_input.job_type
                 else None,
                 "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}
             try:
                 response = session.get(
-                    f"{self.url}/jobs-guest/jobs/api/seeMoreJobPostings/search?",
+                    f"{self.base_url}/jobs-guest/jobs/api/seeMoreJobPostings/search?",
                     params=params,
                     allow_redirects=True,
                     proxies=self.proxy,
-                    headers=self.headers(),
+                    headers=self.headers,
                     timeout=10,
                 )
-                response.raise_for_status()
-
-            except requests.HTTPError as e:
-                raise LinkedInException(f"bad response status code: {e.response.status_code}")
-            except ProxyError as e:
-                raise LinkedInException("bad proxy")
+                if response.status_code not in range(200, 400):
+                    if response.status_code == 429:
+                        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)
             except Exception as e:
-                raise LinkedInException(str(e))
+                if "Proxy responded with" in str(e):
+                    logger.error(f'Indeed: Bad proxy')
+                else:
+                    logger.error(f'Indeed: {str(e)}')
+                return JobResponse(job_list=job_list)
 
             soup = BeautifulSoup(response.text, "html.parser")
             job_cards = soup.find_all("div", class_="base-search-card")
@@ -115,37 +120,38 @@ class LinkedInScraper(Scraper):
                 if href_tag and "href" in href_tag.attrs:
                     href = href_tag.attrs["href"].split("?")[0]
                     job_id = href.split("-")[-1]
-                    job_url = f"{self.url}/jobs/view/{job_id}"
+                    job_url = f"{self.base_url}/jobs/view/{job_id}"
 
                 with url_lock:
                     if job_url in seen_urls:
                         continue
                     seen_urls.add(job_url)
-
-                # Call process_job directly without threading
                 try:
-                    job_post = self.process_job(job_card, job_url, scraper_input.full_description)
+                    job_post = self._process_job(job_card, job_url, scraper_input.linkedin_fetch_description)
                     if job_post:
                         job_list.append(job_post)
+                    if not continue_search():
+                       break
                 except Exception as e:
-                    raise LinkedInException("Exception occurred while processing jobs")
+                    raise LinkedInException(str(e))
 
-            page += 25
-            time.sleep(random.uniform(LinkedInScraper.DELAY, LinkedInScraper.DELAY + 2))
+            if continue_search():
+                time.sleep(random.uniform(self.delay, self.delay + 2))
+                page += 25
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
 
-    def process_job(self, job_card: Tag, job_url: str, full_descr: bool) -> Optional[JobPost]:
+    def _process_job(self, job_card: Tag, job_url: str, full_descr: bool) -> Optional[JobPost]:
         salary_tag = job_card.find('span', class_='job-search-card__salary-info')
 
         compensation = None
         if salary_tag:
-            salary_text = salary_tag.get_text(separator=' ').strip()
-            salary_values = [currency_parser(value) for value in salary_text.split('-')]
+            salary_text = salary_tag.get_text(separator=" ").strip()
+            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),
@@ -166,7 +172,7 @@ class LinkedInScraper(Scraper):
         company = company_a_tag.get_text(strip=True) if company_a_tag else "N/A"
 
         metadata_card = job_card.find("div", class_="base-search-card__metadata")
-        location = self.get_location(metadata_card)
+        location = self._get_location(metadata_card)
 
         datetime_tag = (
             metadata_card.find("time", class_="job-search-card__listdate")
@@ -178,12 +184,12 @@ class LinkedInScraper(Scraper):
             datetime_str = datetime_tag["datetime"]
             try:
                 date_posted = datetime.strptime(datetime_str, "%Y-%m-%d")
-            except Exception as e:
+            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)
+            description, job_type = self._get_job_description(job_url)
 
         return JobPost(
             title=title,
@@ -200,7 +206,7 @@ class LinkedInScraper(Scraper):
             num_urgent_words=count_urgent_words(description) if description else None,
         )
 
-    def get_job_description(
+    def _get_job_description(
         self, job_page_url: str
     ) -> tuple[None, None] | tuple[str | None, tuple[str | None, JobType | None]]:
         """
@@ -210,11 +216,9 @@ class LinkedInScraper(Scraper):
         """
         try:
             session = create_session(is_tls=False, has_retry=True)
-            response = session.get(job_page_url, timeout=5, proxies=self.proxy)
+            response = session.get(job_page_url, headers=self.headers, timeout=5, proxies=self.proxy)
             response.raise_for_status()
-        except requests.HTTPError as e:
-            return None, None
-        except Exception as e:
+        except:
             return None, None
         if response.url == "https://www.linkedin.com/signup":
             return None, None
@@ -223,41 +227,19 @@ 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:
-            description = modify_and_get_description(div_content)
+        if div_content is not None:
+            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")
+            if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
+                description = markdown_converter(description)
+        return description, self._parse_job_type(soup)
 
-        def get_job_type(
-            soup_job_type: BeautifulSoup,
-        ) -> list[JobType] | None:
-            """
-            Gets the job type from job page
-            :param soup_job_type:
-            :return: JobType
-            """
-            h3_tag = soup_job_type.find(
-                "h3",
-                class_="description__job-criteria-subheader",
-                string=lambda text: "Employment type" in text,
-            )
-
-            employment_type = None
-            if h3_tag:
-                employment_type_span = h3_tag.find_next_sibling(
-                    "span",
-                    class_="description__job-criteria-text description__job-criteria-text--criteria",
-                )
-                if employment_type_span:
-                    employment_type = employment_type_span.get_text(strip=True)
-                    employment_type = employment_type.lower()
-                    employment_type = employment_type.replace("-", "")
-
-            return [get_enum_from_job_type(employment_type)] if employment_type else []
-
-        return description, get_job_type(soup)
-
-    def get_location(self, metadata_card: Optional[Tag]) -> Location:
+    def _get_location(self, metadata_card: Optional[Tag]) -> Location:
         """
         Extracts the location data from the job metadata card.
         :param metadata_card
@@ -282,25 +264,50 @@ class LinkedInScraper(Scraper):
                 location = Location(
                     city=city,
                     state=state,
-                    country=Country.from_string(country),
+                    country=Country.from_string(country)
                 )
-
         return location
 
     @staticmethod
-    def headers() -> dict:
+    def _parse_job_type(soup_job_type: BeautifulSoup) -> list[JobType] | None:
+        """
+        Gets the job type from job page
+        :param soup_job_type:
+        :return: JobType
+        """
+        h3_tag = soup_job_type.find(
+            "h3",
+            class_="description__job-criteria-subheader",
+            string=lambda text: "Employment type" in text,
+        )
+        employment_type = None
+        if h3_tag:
+            employment_type_span = h3_tag.find_next_sibling(
+                "span",
+                class_="description__job-criteria-text description__job-criteria-text--criteria",
+            )
+            if employment_type_span:
+                employment_type = employment_type_span.get_text(strip=True)
+                employment_type = employment_type.lower()
+                employment_type = employment_type.replace("-", "")
+
+        return [get_enum_from_job_type(employment_type)] if employment_type else []
+
+    @staticmethod
+    def job_type_code(job_type_enum: JobType) -> str:
         return {
-            '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-language': 'en-US,en;q=0.9',
-            'cache-control': 'max-age=0',
-            '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',
-            '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'
-        }
+            JobType.FULL_TIME: "F",
+            JobType.PART_TIME: "P",
+            JobType.INTERNSHIP: "I",
+            JobType.CONTRACT: "C",
+            JobType.TEMPORARY: "T",
+        }.get(job_type_enum, "")
+
+    headers = {
+        "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-language": "en-US,en;q=0.9",
+        "cache-control": "max-age=0",
+        "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",
+    }

src/jobspy/scrapers/utils.py

@@ -1,20 +1,24 @@
 import re
+import logging
 import numpy as np
 
+import html2text
 import tls_client
 import requests
 from requests.adapters import HTTPAdapter, Retry
 
 from ..jobs import JobType
 
-
-def modify_and_get_description(soup):
-    for li in soup.find_all('li'):
-        li.string = "- " + li.get_text()
-
-    description = soup.get_text(separator='\n').strip()
-    description = re.sub(r'\n+', '\n', description)
-    return description
+text_maker = html2text.HTML2Text()
+logger = logging.getLogger("JobSpy")
+logger.propagate = False
+if not logger.handlers:
+    logger.setLevel(logging.ERROR)
+    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:
@@ -31,6 +35,17 @@ def count_urgent_words(description: str) -> int:
     return count
 
 
+def markdown_converter(description_html: str):
+    if description_html is None:
+        return ""
+    text_maker.ignore_links = False
+    try:
+        markdown = text_maker.handle(description_html)
+        return markdown.strip()
+    except AssertionError as e:
+        return ""
+
+
 def extract_emails_from_text(text: str) -> list[str] | None:
     if not text:
         return None
@@ -41,14 +56,10 @@ def extract_emails_from_text(text: str) -> list[str] | None:
 def create_session(proxy: dict | None = None, is_tls: bool = True, has_retry: bool = False, delay: int = 1) -> requests.Session:
     """
     Creates a requests session with optional tls, proxy, and retry settings.
-
     :return: A session object
     """
     if is_tls:
-        session = tls_client.Session(
-            client_identifier="chrome112",
-            random_tls_extension_order=True,
-        )
+        session = tls_client.Session(random_tls_extension_order=True)
         session.proxies = proxy
     else:
         session = requests.Session()
@@ -65,7 +76,6 @@ def create_session(proxy: dict | None = None, is_tls: bool = True, has_retry: bo
 
             session.mount('http://', adapter)
             session.mount('https://', adapter)
-
     return session
 
 
@@ -79,6 +89,7 @@ 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 +105,5 @@ def currency_parser(cur_str):
         num = float(cur_str)
 
     return np.round(num, 2)
+
+

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -6,34 +6,76 @@ This module contains routines to scrape ZipRecruiter.
 """
 import math
 import time
-import re
-from datetime import datetime, date
+from datetime import datetime
 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 (
+    logger,
+    count_urgent_words,
+    extract_emails_from_text,
+    create_session,
+    markdown_converter
+)
+from ...jobs import (
+    JobPost,
+    Compensation,
+    Location,
+    JobResponse,
+    JobType,
+    Country,
+    DescriptionFormat
+)
 
 
 class ZipRecruiterScraper(Scraper):
+    base_url = "https://www.ziprecruiter.com"
+    api_url = "https://api.ziprecruiter.com"
+
     def __init__(self, proxy: Optional[str] = None):
         """
         Initializes ZipRecruiterScraper with the ZipRecruiter job search url
         """
-        site = Site(Site.ZIP_RECRUITER)
-        self.url = "https://www.ziprecruiter.com"
+        self.scraper_input = None
         self.session = create_session(proxy)
-        self.get_cookies()
-        super().__init__(site, proxy=proxy)
+        self._get_cookies()
+        super().__init__(Site.ZIP_RECRUITER, proxy=proxy)
 
+        self.delay = 5
         self.jobs_per_page = 20
         self.seen_urls = set()
 
-    def find_jobs_in_page(
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+        """
+        Scrapes ZipRecruiter for jobs with scraper_input criteria.
+        :param scraper_input: Information about job search criteria.
+        :return: JobResponse containing a list of jobs.
+        """
+        self.scraper_input = scraper_input
+        job_list: list[JobPost] = []
+        continue_token = None
+
+        max_pages = math.ceil(scraper_input.results_wanted / self.jobs_per_page)
+        for page in range(1, max_pages + 1):
+            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
+            )
+            if jobs_on_page:
+                job_list.extend(jobs_on_page)
+            else:
+                break
+            if not continue_token:
+                break
+        return JobResponse(jobs=job_list[: scraper_input.results_wanted])
+
+    def _find_jobs_in_page(
         self, scraper_input: ScraperInput, continue_token: str | None = None
     ) -> Tuple[list[JobPost], Optional[str]]:
         """
@@ -42,96 +84,62 @@ class ZipRecruiterScraper(Scraper):
         :param continue_token:
         :return: jobs found on page
         """
-        params = self.add_params(scraper_input)
+        jobs_list = []
+        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),
+            res= self.session.get(
+                f"{self.api_url}/jobs-app/jobs",
+                headers=self.headers,
+                params=params
             )
-            if response.status_code != 200:
-                raise ZipRecruiterException(
-                    f"bad response status code: {response.status_code}"
-                )
+            if res.status_code not in range(200, 400):
+                if res.status_code == 429:
+                    logger.error(f'429 Response - Blocked by ZipRecruiter for too many requests')
+                else:
+                    logger.error(f'ZipRecruiter response status code {res.status_code}')
+                return jobs_list, ""
         except Exception as e:
-            if "Proxy responded with non 200 code" in str(e):
-                raise ZipRecruiterException("bad proxy")
-            raise ZipRecruiterException(str(e))
+            if "Proxy responded with" in str(e):
+                logger.error(f'Indeed: Bad proxy')
+            else:
+                logger.error(f'Indeed: {str(e)}')
+            return jobs_list, ""
 
-        time.sleep(5)
-        response_data = response.json()
-        jobs_list = response_data.get("jobs", [])
-        next_continue_token = response_data.get("continue", None)
 
+        res_data = res.json()
+        jobs_list = res_data.get("jobs", [])
+        next_continue_token = res_data.get("continue", None)
         with ThreadPoolExecutor(max_workers=self.jobs_per_page) as executor:
-            job_results = [executor.submit(self.process_job, job) for job in jobs_list]
+            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:
+    def _process_job(self, job: dict) -> JobPost | None:
         """
-        Scrapes ZipRecruiter for jobs with scraper_input criteria.
-        :param scraper_input: Information about job search criteria.
-        :return: JobResponse containing a list of jobs.
+        Processes an individual job dict from the response
         """
-        job_list: list[JobPost] = []
-        continue_token = None
-
-        max_pages = math.ceil(scraper_input.results_wanted / self.jobs_per_page)
-
-        for page in range(1, max_pages + 1):
-            if len(job_list) >= scraper_input.results_wanted:
-                break
-
-            jobs_on_page, continue_token = self.find_jobs_in_page(
-                scraper_input, continue_token
-            )
-            if jobs_on_page:
-                job_list.extend(jobs_on_page)
-
-            if not continue_token:
-                break
-
-        if len(job_list) > scraper_input.results_wanted:
-            job_list = job_list[: scraper_input.results_wanted]
-
-        return JobResponse(jobs=job_list)
-
-    @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"{self.base_url}/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_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
+        description = job.get("job_description", "").strip()
+        description = markdown_converter(description) if self.scraper_input.description_format == DescriptionFormat.MARKDOWN else description
+        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)
 
         location = Location(
             city=job.get("job_city"), state=job.get("job_state"), country=country_enum
         )
-        job_type = ZipRecruiterScraper.get_job_type_enum(
+        job_type = self._get_job_type_enum(
             job.get("employment_type", "").replace("_", "").lower()
         )
-
-        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()
-
+        date_posted = datetime.fromisoformat(job['posted_time'].rstrip("Z")).date()
         return JobPost(
             title=title,
             company_name=company,
@@ -156,60 +164,47 @@ class ZipRecruiterScraper(Scraper):
             num_urgent_words=count_urgent_words(description) if description else None,
         )
 
-    def get_cookies(self):
-        url="https://api.ziprecruiter.com/jobs-app/event"
+    def _get_cookies(self):
         data="event_type=session&logged_in=false&number_of_retry=1&property=model%3AiPhone&property=os%3AiOS&property=locale%3Aen_us&property=app_build_number%3A4734&property=app_version%3A91.0&property=manufacturer%3AApple&property=timestamp%3A2024-01-12T12%3A04%3A42-06%3A00&property=screen_height%3A852&property=os_version%3A16.6.1&property=source%3Ainstall&property=screen_width%3A393&property=device_model%3AiPhone%2014%20Pro&property=brand%3AApple"
-        self.session.post(url, data=data, headers=ZipRecruiterScraper.headers())
+        self.session.post(f"{self.api_url}/jobs-app/event", data=data, headers=self.headers)
 
     @staticmethod
-    def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
+    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]
         return None
 
     @staticmethod
-    def add_params(scraper_input) -> dict[str, str | Any]:
+    def _add_params(scraper_input) -> dict[str, str | Any]:
         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":
-                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 job_type_value:
-            params[
-                "refine_by_employment"
-            ] = f"employment_type:employment_type:{job_type_value}"
-
+            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]
+        if scraper_input.easy_apply:
+            params['zipapply'] = 1
         if scraper_input.is_remote:
-            params["refine_by_location_type"] = "only_remote"
-
+            params["remote"] = 1
         if scraper_input.distance:
             params["radius"] = scraper_input.distance
+        return {k: v for k, v in params.items() if v is not None}
 
-        return params
-
-    @staticmethod
-    def headers() -> dict:
-        """
-        Returns headers needed for requests
-        :return: dict - Dictionary containing headers
-        """
-        return {
-            "Host": "api.ziprecruiter.com",
-            "accept": "*/*",
-            "x-zr-zva-override": "100000000;vid:ZT1huzm_EQlDTVEc",
-            "x-pushnotificationid": "0ff4983d38d7fc5b3370297f2bcffcf4b3321c418f5c22dd152a0264707602a0",
-            "x-deviceid": "D77B3A92-E589-46A4-8A39-6EF6F1D86006",
-            "user-agent": "Job Search/87.0 (iPhone; CPU iOS 16_6_1 like Mac OS X)",
-            "authorization": "Basic YTBlZjMyZDYtN2I0Yy00MWVkLWEyODMtYTI1NDAzMzI0YTcyOg==",
-            "accept-language": "en-US,en;q=0.9",
-        }
+    headers = {
+        "Host": "api.ziprecruiter.com",
+        "accept": "*/*",
+        "x-zr-zva-override": "100000000;vid:ZT1huzm_EQlDTVEc",
+        "x-pushnotificationid": "0ff4983d38d7fc5b3370297f2bcffcf4b3321c418f5c22dd152a0264707602a0",
+        "x-deviceid": "D77B3A92-E589-46A4-8A39-6EF6F1D86006",
+        "user-agent": "Job Search/87.0 (iPhone; CPU iOS 16_6_1 like Mac OS X)",
+        "authorization": "Basic YTBlZjMyZDYtN2I0Yy00MWVkLWEyODMtYTI1NDAzMzI0YTcyOg==",
+        "accept-language": "en-US,en;q=0.9",
+    }