.github/workflows/publish-to-pypi.yml

@@ -1,9 +1,5 @@
 name: Publish JobSpy to PyPi
-on:
+on: push
-  push:
-    branches:
-      - main
-  workflow_dispatch:
 
 jobs:
   build-n-publish:
@@ -31,7 +27,7 @@ jobs:
           build
 
       - name: Publish distribution 📦 to PyPI
-        if: startsWith(github.ref, 'refs/tags') || github.event_name == 'workflow_dispatch'
+        if: startsWith(github.ref, 'refs/tags')
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           password: ${{ secrets.PYPI_API_TOKEN }}

README.md

@@ -4,7 +4,7 @@
 
 ## Features
 
-- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, **ZipRecruiter**, **Bayt** & **Naukri** concurrently
+- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, **ZipRecruiter**, & **Bayt** concurrently
 - Aggregates the job postings in a dataframe
 - Proxies support to bypass blocking
 
@@ -25,7 +25,7 @@ import csv
 from jobspy import scrape_jobs
 
 jobs = scrape_jobs(
-    site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor", "google", "bayt", "naukri"],
+    site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor", "google", "bayt"],
     search_term="software engineer",
     google_search_term="software engineer jobs near San Francisco, CA since yesterday",
     location="San Francisco, CA",
@@ -51,7 +51,6 @@ linkedin       Software Engineer - Early Career  Lockheed Martin   Sunnyvale
 linkedin       Full-Stack Software Engineer      Rain              New York      NY     fulltime  yearly    None        None        https://www.linkedin.com/jobs/view/3696158877      Rain’s mission is to create the fastest and ea...
 zip_recruiter Software Engineer - New Grad       ZipRecruiter      Santa Monica  CA     fulltime  yearly    130000      150000      https://www.ziprecruiter.com/jobs/ziprecruiter...  We offer a hybrid work environment. Most US-ba...
 zip_recruiter Software Developer                 TEKsystems        Phoenix       AZ     fulltime  hourly    65          75          https://www.ziprecruiter.com/jobs/teksystems-0...  Top Skills' Details• 6 years of Java developme...
-
 ```
 
 ### Parameters for `scrape_jobs()`
@@ -221,7 +220,6 @@ JobPost
 │   ├── country
 │   ├── city
 │   ├── state
-├── is_remote
 ├── description
 ├── job_type: fulltime, parttime, internship, contract
 ├── job_function
@@ -231,7 +229,8 @@ JobPost
 │   ├── currency
 │   └── salary_source: direct_data, description (parsed from posting)
 ├── date_posted
-└── emails
+├── emails
+└── is_remote
 
 Linkedin specific
 └── job_level
@@ -246,12 +245,4 @@ Indeed specific
 ├── company_revenue_label
 ├── company_description
 └── company_logo
-
-Naukri specific
-├── skills
-├── experience_range
-├── company_rating
-├── company_reviews_count
-├── vacancy_count
-└── work_from_home_type
 ```

jobspy/__init__.py

@@ -10,7 +10,6 @@ from jobspy.glassdoor import Glassdoor
 from jobspy.google import Google
 from jobspy.indeed import Indeed
 from jobspy.linkedin import LinkedIn
-from jobspy.naukri import Naukri
 from jobspy.model import JobType, Location, JobResponse, Country
 from jobspy.model import SalarySource, ScraperInput, Site
 from jobspy.util import (
@@ -58,7 +57,6 @@ def scrape_jobs(
         Site.GLASSDOOR: Glassdoor,
         Site.GOOGLE: Google,
         Site.BAYT: BaytScraper,
-        Site.NAUKRI: Naukri,
     }
     set_logger_level(verbose)
     job_type = get_enum_from_value(job_type) if job_type else None
@@ -141,7 +139,6 @@ def scrape_jobs(
                     **job_data["location"]
                 ).display_location()
 
-            # Handle compensation
             compensation_obj = job_data.get("compensation")
             if compensation_obj and isinstance(compensation_obj, dict):
                 job_data["interval"] = (
@@ -160,6 +157,7 @@ def scrape_jobs(
                     and job_data["max_amount"]
                 ):
                     convert_to_annual(job_data)
+
             else:
                 if country_enum == Country.USA:
                     (
@@ -178,17 +176,6 @@ def scrape_jobs(
                 if "min_amount" in job_data and job_data["min_amount"]
                 else None
             )
-
-            #naukri-specific fields
-            job_data["skills"] = (
-                ", ".join(job_data["skills"]) if job_data["skills"] else None
-            )
-            job_data["experience_range"] = job_data.get("experience_range")
-            job_data["company_rating"] = job_data.get("company_rating")
-            job_data["company_reviews_count"] = job_data.get("company_reviews_count")
-            job_data["vacancy_count"] = job_data.get("vacancy_count")
-            job_data["work_from_home_type"] = job_data.get("work_from_home_type")
-
             job_df = pd.DataFrame([job_data])
             jobs_dfs.append(job_df)
 

jobspy/exception.py

@@ -34,7 +34,3 @@ class GoogleJobsException(Exception):
 class BaytException(Exception):
     def __init__(self, message=None):
         super().__init__(message or "An error occurred with Bayt")
-
-class NaukriException(Exception):
-    def __init__(self,message=None):
-        super().__init__(message or "An error occurred with Naukri")

jobspy/indeed/util.py

@@ -20,7 +20,7 @@ def get_job_type(attributes: list) -> list[JobType]:
 def get_compensation(compensation: dict) -> Compensation | None:
     """
     Parses the job to get compensation
-    :param compensation:
+    :param sssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrompensation:
     :return: compensation object
     """
     if not compensation["baseSalary"] and not compensation["estimated"]:

jobspy/linkedin/__init__.py

@@ -14,11 +14,10 @@ from bs4.element import Tag
 from jobspy.exception import LinkedInException
 from jobspy.linkedin.constant import headers
 from jobspy.linkedin.util import (
-    is_job_remote,
     job_type_code,
     parse_job_type,
     parse_job_level,
-    parse_company_industry
+    parse_company_industry,
 )
 from jobspy.model import (
     JobPost,
@@ -174,7 +173,7 @@ class LinkedIn(Scraper):
     ) -> Optional[JobPost]:
         salary_tag = job_card.find("span", class_="job-search-card__salary-info")
 
-        compensation = description = None
+        compensation = None
         if salary_tag:
             salary_text = salary_tag.get_text(separator=" ").strip()
             salary_values = [currency_parser(value) for value in salary_text.split("-")]
@@ -218,8 +217,6 @@ class LinkedIn(Scraper):
         job_details = {}
         if full_descr:
             job_details = self._get_job_details(job_id)
-            description = job_details.get("description")
-        is_remote = is_job_remote(title, description, location)
 
         return JobPost(
             id=f"li-{job_id}",
@@ -227,7 +224,6 @@ class LinkedIn(Scraper):
             company_name=company,
             company_url=company_url,
             location=location,
-            is_remote=is_remote,
             date_posted=date_posted,
             job_url=f"{self.base_url}/jobs/view/{job_id}",
             compensation=compensation,
@@ -236,7 +232,7 @@ class LinkedIn(Scraper):
             company_industry=job_details.get("company_industry"),
             description=job_details.get("description"),
             job_url_direct=job_details.get("job_url_direct"),
-            emails=extract_emails_from_text(description),
+            emails=extract_emails_from_text(job_details.get("description")),
             company_logo=job_details.get("company_logo"),
             job_function=job_details.get("job_function"),
         )

jobspy/linkedin/util.py

@@ -1,6 +1,6 @@
 from bs4 import BeautifulSoup
 
-from jobspy.model import JobType, Location
+from jobspy.model import JobType
 from jobspy.util import get_enum_from_job_type
 
 
@@ -83,14 +83,3 @@ def parse_company_industry(soup_industry: BeautifulSoup) -> str | None:
             industry = industry_span.get_text(strip=True)
 
     return industry
-
-
-def is_job_remote(title: dict, description: str, location: Location) -> bool:
-    """
-    Searches the title, location, and description to check if job is remote
-    """
-    remote_keywords = ["remote", "work from home", "wfh"]
-    location = location.display_location()
-    full_string = f'{title} {description} {location}'.lower()
-    is_remote = any(keyword in full_string for keyword in remote_keywords)
-    return is_remote

jobspy/model.py

@@ -69,20 +69,16 @@ class Country(Enum):
     AUSTRIA = ("austria", "at", "at")
     BAHRAIN = ("bahrain", "bh")
     BELGIUM = ("belgium", "be", "fr:be")
-    BULGARIA = ("bulgaria", "bg")
     BRAZIL = ("brazil", "br", "com.br")
     CANADA = ("canada", "ca", "ca")
     CHILE = ("chile", "cl")
     CHINA = ("china", "cn")
     COLOMBIA = ("colombia", "co")
     COSTARICA = ("costa rica", "cr")
-    CROATIA = ("croatia", "hr")
-    CYPRUS = ("cyprus", "cy")
     CZECHREPUBLIC = ("czech republic,czechia", "cz")
     DENMARK = ("denmark", "dk")
     ECUADOR = ("ecuador", "ec")
     EGYPT = ("egypt", "eg")
-    ESTONIA = ("estonia", "ee")
     FINLAND = ("finland", "fi")
     FRANCE = ("france", "fr", "fr")
     GERMANY = ("germany", "de", "de")
@@ -96,8 +92,6 @@ class Country(Enum):
     ITALY = ("italy", "it", "it")
     JAPAN = ("japan", "jp")
     KUWAIT = ("kuwait", "kw")
-    LATVIA = ("latvia", "lv")
-    LITHUANIA = ("lithuania", "lt")
     LUXEMBOURG = ("luxembourg", "lu")
     MALAYSIA = ("malaysia", "malaysia:my", "com")
     MALTA = ("malta", "malta:mt", "mt")
@@ -118,8 +112,6 @@ class Country(Enum):
     ROMANIA = ("romania", "ro")
     SAUDIARABIA = ("saudi arabia", "sa")
     SINGAPORE = ("singapore", "sg", "sg")
-    SLOVAKIA = ("slovakia", "sk")
-    SLOVENIA = ("slovenia", "sl")
     SOUTHAFRICA = ("south africa", "za")
     SOUTHKOREA = ("south korea", "kr")
     SPAIN = ("spain", "es", "es")
@@ -254,13 +246,13 @@ class JobPost(BaseModel):
     is_remote: bool | None = None
     listing_type: str | None = None
 
-    # LinkedIn specific
+    # linkedin specific
     job_level: str | None = None
 
-    # LinkedIn and Indeed specific
+    # linkedin and indeed specific
     company_industry: str | None = None
 
-    # Indeed specific
+    # indeed specific
     company_addresses: str | None = None
     company_num_employees: str | None = None
     company_revenue: str | None = None
@@ -268,16 +260,9 @@ class JobPost(BaseModel):
     company_logo: str | None = None
     banner_photo_url: str | None = None
 
-    # LinkedIn only atm
+    # linkedin only atm
     job_function: str | None = None
 
-    # Naukri specific
-    skills: list[str] | None = None  #from tagsAndSkills
-    experience_range: str | None = None  #from experienceText
-    company_rating: float | None = None  #from ambitionBoxData.AggregateRating
-    company_reviews_count: int | None = None  #from ambitionBoxData.ReviewsCount
-    vacancy_count: int | None = None  #from vacancy
-    work_from_home_type: str | None = None  #from clusters.wfhType (e.g., "Hybrid", "Remote")
 
 class JobResponse(BaseModel):
     jobs: list[JobPost] = []
@@ -290,7 +275,6 @@ class Site(Enum):
     GLASSDOOR = "glassdoor"
     GOOGLE = "google"
     BAYT = "bayt"
-    NAUKRI = "naukri"
 
 
 class SalarySource(Enum):

jobspy/naukri/__init__.py

@@ -1,301 +0,0 @@
-from __future__ import annotations
-
-import math
-import random
-import time
-from datetime import datetime, date, timedelta
-from typing import Optional
-
-import regex as re
-import requests
-
-from jobspy.exception import NaukriException
-from jobspy.naukri.constant import headers as naukri_headers
-from jobspy.naukri.util import (
-    is_job_remote,
-    parse_job_type,
-    parse_company_industry,
-)
-from jobspy.model import (
-    JobPost,
-    Location,
-    JobResponse,
-    Country,
-    Compensation,
-    DescriptionFormat,
-    Scraper,
-    ScraperInput,
-    Site,
-)
-from jobspy.util import (
-    extract_emails_from_text,
-    currency_parser,
-    markdown_converter,
-    create_session,
-    create_logger,
-)
-
-log = create_logger("Naukri")
-
-class Naukri(Scraper):
-    base_url = "https://www.naukri.com/jobapi/v3/search"
-    delay = 3
-    band_delay = 4
-    jobs_per_page = 20  
-
-    def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
-    ):
-        """
-        Initializes NaukriScraper with the Naukri API URL
-        """
-        super().__init__(Site.NAUKRI, proxies=proxies, ca_cert=ca_cert)
-        self.session = create_session(
-            proxies=self.proxies,
-            ca_cert=ca_cert,
-            is_tls=False,
-            has_retry=True,
-            delay=5,
-            clear_cookies=True,
-        )
-        self.session.headers.update(naukri_headers)
-        self.scraper_input = None
-        self.country = "India"  #naukri is india-focused by default
-        log.info("Naukri scraper initialized")
-
-    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
-        """
-        Scrapes Naukri API for jobs with scraper_input criteria
-        :param scraper_input:
-        :return: job_response
-        """
-        self.scraper_input = scraper_input
-        job_list: list[JobPost] = []
-        seen_ids = set()
-        start = scraper_input.offset or 0
-        page = (start // self.jobs_per_page) + 1
-        request_count = 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 <= 50  # Arbitrary limit
-        )
-
-        while continue_search():
-            request_count += 1
-            log.info(
-                f"Scraping page {request_count} / {math.ceil(scraper_input.results_wanted / self.jobs_per_page)} "
-                f"for search term: {scraper_input.search_term}"
-            )
-            params = {
-                "noOfResults": self.jobs_per_page,
-                "urlType": "search_by_keyword",
-                "searchType": "adv",
-                "keyword": scraper_input.search_term,
-                "pageNo": page,
-                "k": scraper_input.search_term,
-                "seoKey": f"{scraper_input.search_term.lower().replace(' ', '-')}-jobs",
-                "src": "jobsearchDesk",
-                "latLong": "",
-                "location": scraper_input.location,
-                "remote": "true" if scraper_input.is_remote else None,
-            }
-            if seconds_old:
-                params["days"] = seconds_old // 86400  # Convert to days
-
-            params = {k: v for k, v in params.items() if v is not None}
-            try:
-                log.debug(f"Sending request to {self.base_url} with params: {params}")
-                response = self.session.get(self.base_url, params=params, timeout=10)
-                if response.status_code not in range(200, 400):
-                    err = f"Naukri API response status code {response.status_code} - {response.text}"
-                    log.error(err)
-                    return JobResponse(jobs=job_list)
-                data = response.json()
-                job_details = data.get("jobDetails", [])
-                log.info(f"Received {len(job_details)} job entries from API")
-                if not job_details:
-                    log.warning("No job details found in API response")
-                    break
-            except Exception as e:
-                log.error(f"Naukri API request failed: {str(e)}")
-                return JobResponse(jobs=job_list)
-
-            for job in job_details:
-                job_id = job.get("jobId")
-                if not job_id or job_id in seen_ids:
-                    continue
-                seen_ids.add(job_id)
-                log.debug(f"Processing job ID: {job_id}")
-
-                try:
-                    fetch_desc = scraper_input.linkedin_fetch_description
-                    job_post = self._process_job(job, job_id, fetch_desc)
-                    if job_post:
-                        job_list.append(job_post)
-                        log.info(f"Added job: {job_post.title} (ID: {job_id})")
-                    if not continue_search():
-                        break
-                except Exception as e:
-                    log.error(f"Error processing job ID {job_id}: {str(e)}")
-                    raise NaukriException(str(e))
-
-            if continue_search():
-                time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
-                page += 1
-
-        job_list = job_list[:scraper_input.results_wanted]
-        log.info(f"Scraping completed. Total jobs collected: {len(job_list)}")
-        return JobResponse(jobs=job_list)
-
-    def _process_job(
-        self, job: dict, job_id: str, full_descr: bool
-    ) -> Optional[JobPost]:
-        """
-        Processes a single job from API response into a JobPost object
-        """
-        title = job.get("title", "N/A")
-        company = job.get("companyName", "N/A")
-        company_url = f"https://www.naukri.com/{job.get('staticUrl', '')}" if job.get("staticUrl") else None
-
-        location = self._get_location(job.get("placeholders", []))
-        compensation = self._get_compensation(job.get("placeholders", []))
-        date_posted = self._parse_date(job.get("footerPlaceholderLabel"), job.get("createdDate"))
-
-        job_url = f"https://www.naukri.com{job.get('jdURL', f'/job/{job_id}')}"
-        description = job.get("jobDescription") if full_descr else None
-        if description and self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
-            description = markdown_converter(description)
-
-        job_type = parse_job_type(description) if description else None
-        company_industry = parse_company_industry(description) if description else None
-        is_remote = is_job_remote(title, description or "", location)
-        company_logo = job.get("logoPathV3") or job.get("logoPath")
-
-        # Naukri-specific fields
-        skills = job.get("tagsAndSkills", "").split(",") if job.get("tagsAndSkills") else None
-        experience_range = job.get("experienceText")
-        ambition_box = job.get("ambitionBoxData", {})
-        company_rating = float(ambition_box.get("AggregateRating")) if ambition_box.get("AggregateRating") else None
-        company_reviews_count = ambition_box.get("ReviewsCount")
-        vacancy_count = job.get("vacancy")
-        work_from_home_type = self._infer_work_from_home_type(job.get("placeholders", []), title, description or "")
-
-        job_post = JobPost(
-            id=f"nk-{job_id}",
-            title=title,
-            company_name=company,
-            company_url=company_url,
-            location=location,
-            is_remote=is_remote,
-            date_posted=date_posted,
-            job_url=job_url,
-            compensation=compensation,
-            job_type=job_type,
-            company_industry=company_industry,
-            description=description,
-            emails=extract_emails_from_text(description or ""),
-            company_logo=company_logo,
-            skills=skills,
-            experience_range=experience_range,
-            company_rating=company_rating,
-            company_reviews_count=company_reviews_count,
-            vacancy_count=vacancy_count,
-            work_from_home_type=work_from_home_type,
-        )
-        log.debug(f"Processed job: {title} at {company}")
-        return job_post
-
-    def _get_location(self, placeholders: list[dict]) -> Location:
-        """
-        Extracts location data from placeholders
-        """
-        location = Location(country=Country.INDIA)
-        for placeholder in placeholders:
-            if placeholder.get("type") == "location":
-                location_str = placeholder.get("label", "")
-                parts = location_str.split(", ")
-                city = parts[0] if parts else None
-                state = parts[1] if len(parts) > 1 else None
-                location = Location(city=city, state=state, country=Country.INDIA)
-                log.debug(f"Parsed location: {location.display_location()}")
-                break
-        return location
-
-    def _get_compensation(self, placeholders: list[dict]) -> Optional[Compensation]:
-        """
-        Extracts compensation data from placeholders, handling Indian salary formats (Lakhs, Crores)
-        """
-        for placeholder in placeholders:
-            if placeholder.get("type") == "salary":
-                salary_text = placeholder.get("label", "").strip()
-                if salary_text == "Not disclosed":
-                    log.debug("Salary not disclosed")
-                    return None
-
-                # Handle Indian salary formats (e.g., "12-16 Lacs P.A.", "1-5 Cr")
-                salary_match = re.match(r"(\d+(?:\.\d+)?)\s*-\s*(\d+(?:\.\d+)?)\s*(Lacs|Lakh|Cr)\s*(P\.A\.)?", salary_text, re.IGNORECASE)
-                if salary_match:
-                    min_salary, max_salary, unit = salary_match.groups()[:3]
-                    min_salary, max_salary = float(min_salary), float(max_salary)
-                    currency = "INR"
-
-                    # Convert to base units (INR)
-                    if unit.lower() in ("lacs", "lakh"):
-                        min_salary *= 100000  # 1 Lakh = 100,000 INR
-                        max_salary *= 100000
-                    elif unit.lower() == "cr":
-                        min_salary *= 10000000  # 1 Crore = 10,000,000 INR
-                        max_salary *= 10000000
-
-                    log.debug(f"Parsed salary: {min_salary} - {max_salary} INR")
-                    return Compensation(
-                        min_amount=int(min_salary),
-                        max_amount=int(max_salary),
-                        currency=currency,
-                    )
-                else:
-                    log.debug(f"Could not parse salary: {salary_text}")
-                    return None
-        return None
-
-    def _parse_date(self, label: str, created_date: int) -> Optional[date]:
-        """
-        Parses date from footerPlaceholderLabel or createdDate, returning a date object
-        """
-        today = datetime.now()
-        if not label:
-            if created_date:
-                return datetime.fromtimestamp(created_date / 1000).date()  # Convert to date
-            return None
-        label = label.lower()
-        if "today" in label or "just now" in label or "few hours" in label:
-            log.debug("Date parsed as today")
-            return today.date()
-        elif "ago" in label:
-            match = re.search(r"(\d+)\s*day", label)
-            if match:
-                days = int(match.group(1))
-                parsed_date = (today - timedelta(days = days)).date()
-                log.debug(f"Date parsed: {days} days ago -> {parsed_date}")
-                return parsed_date
-        elif created_date:
-            parsed_date = datetime.fromtimestamp(created_date / 1000).date()
-            log.debug(f"Date parsed from timestamp: {parsed_date}")
-            return parsed_date
-        log.debug("No date parsed")
-        return None
-
-    def _infer_work_from_home_type(self, placeholders: list[dict], title: str, description: str) -> Optional[str]:
-        """
-        Infers work-from-home type from job data (e.g., 'Hybrid', 'Remote', 'Work from office')
-        """
-        location_str = next((p["label"] for p in placeholders if p["type"] == "location"), "").lower()
-        if "hybrid" in location_str or "hybrid" in title.lower() or "hybrid" in description.lower():
-            return "Hybrid"
-        elif "remote" in location_str or "remote" in title.lower() or "remote" in description.lower():
-            return "Remote"
-        elif "work from office" in description.lower() or not ("remote" in description.lower() or "hybrid" in description.lower()):
-            return "Work from office"
-        return None

jobspy/naukri/constant.py

@@ -1,11 +0,0 @@
-headers = {
-    "authority": "www.naukri.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",
-    "appid": "109",
-    "systemid": "Naukri",
-    "Nkparam": "Ppy0YK9uSHqPtG3bEejYc04RTpUN2CjJOrqA68tzQt0SKJHXZKzz9M8cZtKLVkoOuQmfe4cTb1r2CwfHaxW5Tg==",
-    "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",
-}

jobspy/naukri/util.py

@@ -1,34 +0,0 @@
-from __future__ import annotations
-
-from bs4 import BeautifulSoup
-from jobspy.model import JobType, Location
-from jobspy.util import get_enum_from_job_type
-
-
-def parse_job_type(soup: BeautifulSoup) -> list[JobType] | None:
-    """
-    Gets the job type from the job page
-    """
-    job_type_tag = soup.find("span", class_="job-type")
-    if job_type_tag:
-        job_type_str = job_type_tag.get_text(strip=True).lower().replace("-", "")
-        return [get_enum_from_job_type(job_type_str)] if job_type_str else None
-    return None
-
-
-def parse_company_industry(soup: BeautifulSoup) -> str | None:
-    """
-    Gets the company industry from the job page
-    """
-    industry_tag = soup.find("span", class_="industry")
-    return industry_tag.get_text(strip=True) if industry_tag else None
-
-
-def is_job_remote(title: str, description: str, location: Location) -> bool:
-    """
-    Searches the title, description, and location to check if the job is remote
-    """
-    remote_keywords = ["remote", "work from home", "wfh"]
-    location_str = location.display_location()
-    full_string = f"{title} {description} {location_str}".lower()
-    return any(keyword in full_string for keyword in remote_keywords)

jobspy/util.py

@@ -47,12 +47,11 @@ class RotatingProxySession:
         """Utility method to format a proxy string into a dictionary."""
         if proxy.startswith("http://") or proxy.startswith("https://"):
             return {"http": proxy, "https": proxy}
-        if proxy.startswith("socks5://"):
-            return {"http": proxy, "https": proxy}
         return {"http": f"http://{proxy}", "https": f"http://{proxy}"}
 
 
 class RequestsRotating(RotatingProxySession, requests.Session):
+
     def __init__(self, proxies=None, has_retry=False, delay=1, clear_cookies=False):
         RotatingProxySession.__init__(self, proxies=proxies)
         requests.Session.__init__(self)
@@ -87,6 +86,7 @@ class RequestsRotating(RotatingProxySession, requests.Session):
 
 
 class TLSRotating(RotatingProxySession, tls_client.Session):
+
     def __init__(self, proxies=None):
         RotatingProxySession.__init__(self, proxies=proxies)
         tls_client.Session.__init__(self, random_tls_extension_order=True)
@@ -344,11 +344,4 @@ desired_order = [
     "company_num_employees",
     "company_revenue",
     "company_description",
-    # naukri-specific fields
-    "skills",
-    "experience_range",
-    "company_rating",
-    "company_reviews_count",
-    "vacancy_count",
-    "work_from_home_type",
 ]

pyproject.toml

@@ -4,12 +4,12 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.80"
+version = "1.1.77"
 description = "Job scraper for LinkedIn, Indeed, Glassdoor, ZipRecruiter & Bayt"
 authors = ["Cullen Watson <cullen@cullenwatson.com>", "Zachary Hampton <zachary@zacharysproducts.com>"]
 homepage = "https://github.com/cullenwatson/JobSpy"
 readme = "README.md"
-keywords = [ "jobs-scraper", "linkedin", "indeed", "glassdoor", "ziprecruiter", "bayt", "naukri"]
+keywords = [ "jobs-scraper", "linkedin", "indeed", "glassdoor", "ziprecruiter", "bayt"]
 [[tool.poetry.packages]]
 include = "jobspy"