fix(linkedin): add fallback for date parsing on new job listings (#343)

LinkedIn uses two CSS classes for job posting dates:
- `job-search-card__listdate` for older posts
- `job-search-card__listdate--new` for recent posts (< 24h)

The scraper only checked the first class, causing `date_posted` to be
None for all fresh listings. This adds a fallback to also check for
the `--new` variant.

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @cullenwatson

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

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

README.md

@@ -4,7 +4,7 @@
 
 ## Features
 
-- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, **ZipRecruiter**, & **Bayt** concurrently
+- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, **ZipRecruiter**, & other job boards 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"],
+    site_name=["indeed", "linkedin", "zip_recruiter", "google"], # "glassdoor", "bayt", "naukri", "bdjobs"
     search_term="software engineer",
     google_search_term="software engineer jobs near San Francisco, CA since yesterday",
     location="San Francisco, CA",
@@ -51,6 +51,7 @@ 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()`
@@ -58,7 +59,7 @@ zip_recruiter Software Developer                 TEKsystems        Phoenix
 ```plaintext
 Optional
 ├── site_name (list|str): 
-|    linkedin, zip_recruiter, indeed, glassdoor, google, bayt
+|    linkedin, zip_recruiter, indeed, glassdoor, google, bayt, bdjobs
 |    (default is all)
 │
 ├── search_term (str)
@@ -85,6 +86,9 @@ Optional
 │
 ├── easy_apply (bool): 
 |    filters for jobs that are hosted on the job board site (LinkedIn easy apply filter no longer works)
+|
+├── user_agent (str): 
+|    override the default user agent which may be outdated
 │
 ├── description_format (str): 
 |    markdown, html (Format type of the job descriptions. Default is markdown.)
@@ -220,6 +224,7 @@ JobPost
 │   ├── country
 │   ├── city
 │   ├── state
+├── is_remote
 ├── description
 ├── job_type: fulltime, parttime, internship, contract
 ├── job_function
@@ -229,8 +234,7 @@ JobPost
 │   ├── currency
 │   └── salary_source: direct_data, description (parsed from posting)
 ├── date_posted
-├── emails
-└── is_remote
+└── emails
 
 Linkedin specific
 └── job_level
@@ -245,4 +249,12 @@ 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

@@ -6,10 +6,12 @@ from typing import Tuple
 import pandas as pd
 
 from jobspy.bayt import BaytScraper
+from jobspy.bdjobs import BDJobs
 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 (
@@ -24,6 +26,8 @@ from jobspy.util import (
 from jobspy.ziprecruiter import ZipRecruiter
 
 
+# Update the SCRAPER_MAPPING dictionary in the scrape_jobs function
+
 def scrape_jobs(
     site_name: str | list[str] | Site | list[Site] | None = None,
     search_term: str | None = None,
@@ -44,6 +48,7 @@ def scrape_jobs(
     hours_old: int = None,
     enforce_annual_salary: bool = False,
     verbose: int = 0,
+    user_agent: str = None,
     **kwargs,
 ) -> pd.DataFrame:
     """
@@ -57,6 +62,8 @@ def scrape_jobs(
         Site.GLASSDOOR: Glassdoor,
         Site.GOOGLE: Google,
         Site.BAYT: BaytScraper,
+        Site.NAUKRI: Naukri,
+        Site.BDJOBS: BDJobs,  # Add BDJobs to the scraper mapping
     }
     set_logger_level(verbose)
     job_type = get_enum_from_value(job_type) if job_type else None
@@ -96,10 +103,11 @@ def scrape_jobs(
 
     def scrape_site(site: Site) -> Tuple[str, JobResponse]:
         scraper_class = SCRAPER_MAPPING[site]
-        scraper = scraper_class(proxies=proxies, ca_cert=ca_cert)
+        scraper = scraper_class(proxies=proxies, ca_cert=ca_cert, user_agent=user_agent)
         scraped_data: JobResponse = scraper.scrape(scraper_input)
         cap_name = site.value.capitalize()
         site_name = "ZipRecruiter" if cap_name == "Zip_recruiter" else cap_name
+        site_name = "LinkedIn" if cap_name == "Linkedin" else cap_name
         create_logger(site_name).info(f"finished scraping")
         return site.value, scraped_data
 
@@ -139,6 +147,7 @@ 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"] = (
@@ -157,7 +166,6 @@ def scrape_jobs(
                     and job_data["max_amount"]
                 ):
                     convert_to_annual(job_data)
-
             else:
                 if country_enum == Country.USA:
                     (
@@ -176,6 +184,17 @@ 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)
 
@@ -200,3 +219,9 @@ def scrape_jobs(
         ).reset_index(drop=True)
     else:
         return pd.DataFrame()
+
+
+# Add BDJobs to __all__
+__all__ = [
+    "BDJobs",
+]

jobspy/bayt/__init__.py

@@ -25,7 +25,7 @@ class BaytScraper(Scraper):
     band_delay = 3
 
     def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         super().__init__(Site.BAYT, proxies=proxies, ca_cert=ca_cert)
         self.scraper_input = None

jobspy/bdjobs/__init__.py

@@ -0,0 +1,353 @@
+# __init__.py
+from __future__ import annotations
+
+import random
+import time
+from datetime import datetime
+from typing import Optional, List, Dict, Any
+from urllib.parse import urljoin
+
+from bs4 import BeautifulSoup
+from bs4.element import Tag
+
+from jobspy.exception import BDJobsException
+from jobspy.bdjobs.constant import headers, search_params
+from jobspy.bdjobs.util import (
+    parse_location,
+    parse_date,
+    find_job_listings,
+    is_job_remote,
+)
+from jobspy.model import (
+    JobPost,
+    Location,
+    JobResponse,
+    Country,
+    Scraper,
+    ScraperInput,
+    Site,
+    DescriptionFormat,
+)
+from jobspy.util import (
+    extract_emails_from_text,
+    create_session,
+    create_logger,
+    remove_attributes,
+    markdown_converter,
+)
+
+log = create_logger("BDJobs")
+
+
+class BDJobs(Scraper):
+    base_url = "https://jobs.bdjobs.com"
+    search_url = "https://jobs.bdjobs.com/jobsearch.asp"
+    delay = 2
+    band_delay = 3
+
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
+    ):
+        """
+        Initializes BDJobsScraper with the BDJobs job search url
+        """
+        super().__init__(Site.BDJOBS, 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(headers)
+        self.scraper_input = None
+        self.country = "bangladesh"
+
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+        """
+        Scrapes BDJobs for jobs with scraper_input criteria
+        :param scraper_input:
+        :return: job_response
+        """
+        self.scraper_input = scraper_input
+        job_list: list[JobPost] = []
+        seen_ids = set()
+        page = 1
+        request_count = 0
+
+        # Set up search parameters
+        params = search_params.copy()
+        params["txtsearch"] = scraper_input.search_term
+
+        continue_search = lambda: len(job_list) < scraper_input.results_wanted
+
+        while continue_search():
+            request_count += 1
+            log.info(f"search page: {request_count}")
+
+            try:
+                # Add page parameter if needed
+                if page > 1:
+                    params["pg"] = page
+
+                response = self.session.get(
+                    self.search_url,
+                    params=params,
+                    timeout=getattr(scraper_input, "request_timeout", 60),
+                )
+
+                if response.status_code != 200:
+                    log.error(f"BDJobs response status code {response.status_code}")
+                    break
+
+                soup = BeautifulSoup(response.text, "html.parser")
+                job_cards = find_job_listings(soup)
+
+                if not job_cards or len(job_cards) == 0:
+                    log.info("No more job listings found")
+                    break
+
+                log.info(f"Found {len(job_cards)} job cards on page {page}")
+
+                for job_card in job_cards:
+                    try:
+                        job_post = self._process_job(job_card)
+                        if job_post and job_post.id not in seen_ids:
+                            seen_ids.add(job_post.id)
+                            job_list.append(job_post)
+
+                            if not continue_search():
+                                break
+                    except Exception as e:
+                        log.error(f"Error processing job card: {str(e)}")
+
+                page += 1
+                # Add delay between requests
+                time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
+
+            except Exception as e:
+                log.error(f"Error during scraping: {str(e)}")
+                break
+
+        job_list = job_list[: scraper_input.results_wanted]
+        return JobResponse(jobs=job_list)
+
+    def _process_job(self, job_card: Tag) -> Optional[JobPost]:
+        """
+        Processes a job card element into a JobPost object
+        :param job_card: Job card element
+        :return: JobPost object
+        """
+        try:
+            # Extract job ID and URL
+            job_link = job_card.find("a", href=lambda h: h and "jobdetail" in h.lower())
+            if not job_link:
+                return None
+
+            job_url = job_link.get("href")
+            if not job_url.startswith("http"):
+                job_url = urljoin(self.base_url, job_url)
+
+            # Extract job ID from URL
+            job_id = (
+                job_url.split("jobid=")[-1].split("&")[0]
+                if "jobid=" in job_url
+                else f"bdjobs-{hash(job_url)}"
+            )
+
+            # Extract title
+            title = job_link.get_text(strip=True)
+            if not title:
+                title_elem = job_card.find(
+                    ["h2", "h3", "h4", "strong", "div"],
+                    class_=lambda c: c and "job-title-text" in c,
+                )
+                title = title_elem.get_text(strip=True) if title_elem else "N/A"
+
+            # Extract company name - IMPROVED
+            company_elem = job_card.find(
+                ["span", "div"],
+                class_=lambda c: c and "comp-name-text" in (c or "").lower(),
+            )
+            if company_elem:
+                company_name = company_elem.get_text(strip=True)
+            else:
+                # Try alternative selectors
+                company_elem = job_card.find(
+                    ["span", "div"],
+                    class_=lambda c: c
+                    and any(
+                        term in (c or "").lower()
+                        for term in ["company", "org", "comp-name"]
+                    ),
+                )
+                company_name = (
+                    company_elem.get_text(strip=True) if company_elem else "N/A"
+                )
+
+            # Extract location
+            location_elem = job_card.find(
+                ["span", "div"],
+                class_=lambda c: c and "locon-text-d" in (c or "").lower(),
+            )
+            if not location_elem:
+                location_elem = job_card.find(
+                    ["span", "div"],
+                    class_=lambda c: c
+                    and any(
+                        term in (c or "").lower()
+                        for term in ["location", "area", "locon"]
+                    ),
+                )
+            location_text = (
+                location_elem.get_text(strip=True)
+                if location_elem
+                else "Dhaka, Bangladesh"
+            )
+
+            # Create Location object
+            location = parse_location(location_text, self.country)
+
+            # Extract date posted
+            date_elem = job_card.find(
+                ["span", "div"],
+                class_=lambda c: c
+                and any(
+                    term in (c or "").lower()
+                    for term in ["date", "deadline", "published"]
+                ),
+            )
+            date_posted = None
+            if date_elem:
+                date_text = date_elem.get_text(strip=True)
+                date_posted = parse_date(date_text)
+
+            # Check if job is remote
+            is_remote = is_job_remote(title, location=location)
+
+            # Create job post object
+            job_post = JobPost(
+                id=job_id,
+                title=title,
+                company_name=company_name,  # Use company_name instead of company
+                location=location,
+                date_posted=date_posted,
+                job_url=job_url,
+                is_remote=is_remote,
+                site=self.site,
+            )
+
+            # Always fetch description for BDJobs
+            job_details = self._get_job_details(job_url)
+            job_post.description = job_details.get("description", "")
+            job_post.job_type = job_details.get("job_type", "")
+
+            return job_post
+        except Exception as e:
+            log.error(f"Error in _process_job: {str(e)}")
+            return None
+
+    def _get_job_details(self, job_url: str) -> Dict[str, Any]:
+        """
+        Gets detailed job information from the job page
+        :param job_url: Job page URL
+        :return: Dictionary with job details
+        """
+        try:
+            response = self.session.get(job_url, timeout=60)
+            if response.status_code != 200:
+                return {}
+
+            soup = BeautifulSoup(response.text, "html.parser")
+
+            # Find job description - IMPROVED based on correct.py
+            description = ""
+
+            # Try to find the job content div first (as in correct.py)
+            job_content_div = soup.find("div", class_="jobcontent")
+            if job_content_div:
+                # Look for responsibilities section
+                responsibilities_heading = job_content_div.find(
+                    "h4", id="job_resp"
+                ) or job_content_div.find(
+                    ["h4", "h5"], string=lambda s: s and "responsibilities" in s.lower()
+                )
+                if responsibilities_heading:
+                    responsibilities_elements = []
+                    # Find all following elements until the next heading or hr
+                    for sibling in responsibilities_heading.find_next_siblings():
+                        if sibling.name in ["hr", "h4", "h5"]:
+                            break
+                        if sibling.name == "ul":
+                            responsibilities_elements.extend(
+                                li.get_text(separator=" ", strip=True)
+                                for li in sibling.find_all("li")
+                            )
+                        elif sibling.name == "p":
+                            responsibilities_elements.append(
+                                sibling.get_text(separator=" ", strip=True)
+                            )
+
+                description = (
+                    "\n".join(responsibilities_elements)
+                    if responsibilities_elements
+                    else ""
+                )
+
+            # If no description found yet, try the original approach
+            if not description:
+                description_elem = soup.find(
+                    ["div", "section"],
+                    class_=lambda c: c
+                    and any(
+                        term in (c or "").lower()
+                        for term in ["job-description", "details", "requirements"]
+                    ),
+                )
+                if description_elem:
+                    description_elem = remove_attributes(description_elem)
+                    description = description_elem.prettify(formatter="html")
+                    if (
+                        hasattr(self.scraper_input, "description_format")
+                        and self.scraper_input.description_format
+                        == DescriptionFormat.MARKDOWN
+                    ):
+                        description = markdown_converter(description)
+
+            # Extract job type
+            job_type_elem = soup.find(
+                ["span", "div"],
+                string=lambda s: s
+                and any(
+                    term in (s or "").lower()
+                    for term in ["job type", "employment type"]
+                ),
+            )
+            job_type = None
+            if job_type_elem:
+                job_type_text = job_type_elem.find_next(["span", "div"]).get_text(
+                    strip=True
+                )
+                job_type = job_type_text if job_type_text else None
+
+            # Extract company industry
+            industry_elem = soup.find(
+                ["span", "div"], string=lambda s: s and "industry" in (s or "").lower()
+            )
+            company_industry = None
+            if industry_elem:
+                industry_text = industry_elem.find_next(["span", "div"]).get_text(
+                    strip=True
+                )
+                company_industry = industry_text if industry_text else None
+
+            return {
+                "description": description,
+                "job_type": job_type,
+                "company_industry": company_industry,
+            }
+
+        except Exception as e:
+            log.error(f"Error getting job details: {str(e)}")
+            return {}

jobspy/bdjobs/constant.py

@@ -0,0 +1,32 @@
+#constant.py
+# Headers for BDJobs requests
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
+    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+    "Accept-Language": "en-US,en;q=0.5",
+    "Connection": "keep-alive",
+    "Referer": "https://jobs.bdjobs.com/",
+    "Cache-Control": "max-age=0",
+}
+
+# Search parameters that work best for BDJobs
+search_params = {
+    "hidJobSearch": "jobsearch",
+}
+
+# Selectors for job listings
+job_selectors = [
+    "div.job-item",  # Catches both normal and premium job cards, as well as other types
+    "div.sout-jobs-wrapper", # Catches job listings in the main search results page
+    "div.norm-jobs-wrapper", # Catches normal job listings
+    "div.featured-wrap",     # Catches featured job listings
+]
+
+# Date formats used by BDJobs
+date_formats = [
+    "%d %b %Y",
+    "%d-%b-%Y",
+    "%d %B %Y",
+    "%B %d, %Y",
+    "%d/%m/%Y",
+]

jobspy/bdjobs/util.py

@@ -0,0 +1,100 @@
+#util.py
+from bs4 import BeautifulSoup
+from datetime import datetime
+from typing import Optional, List, Dict, Any
+
+from jobspy.model import Location, Country
+
+
+def parse_location(location_text: str, country: str = "bangladesh") -> Location:
+    """
+    Parses location text into a Location object
+    :param location_text: Location text from job listing
+    :param country: Default country
+    :return: Location object
+    """
+    parts = location_text.split(",")
+    if len(parts) >= 2:
+        city = parts[0].strip()
+        state = parts[1].strip()
+        return Location(
+            city=city,
+            state=state,
+            country=Country.from_string(country)
+        )
+    else:
+        return Location(
+            city=location_text.strip(),
+            country=Country.from_string(country)
+        )
+
+
+def parse_date(date_text: str) -> Optional[datetime]:
+    """
+    Parses date text into a datetime object
+    :param date_text: Date text from job listing
+    :return: datetime object or None if parsing fails
+    """
+    from .constant import date_formats
+    
+    try:
+        # Clean up date text
+        if "Deadline:" in date_text:
+            date_text = date_text.replace("Deadline:", "").strip()
+        
+        # Try different date formats
+        for fmt in date_formats:
+            try:
+                return datetime.strptime(date_text, fmt)
+            except ValueError:
+                continue
+        
+        return None
+    except Exception:
+        return None
+
+
+def find_job_listings(soup: BeautifulSoup) -> List[Any]:
+    """
+    Finds job listing elements in the HTML
+    :param soup: BeautifulSoup object
+    :return: List of job card elements
+    """
+    from .constant import job_selectors
+    
+    # Try different selectors
+    for selector in job_selectors:
+        if "." in selector:
+            tag_name, class_name = selector.split(".", 1)
+            elements = soup.find_all(tag_name, class_=class_name)
+            if elements and len(elements) > 0:
+                return elements
+    
+    # If no selectors match, look for job detail links
+    job_links = soup.find_all("a", href=lambda h: h and "jobdetail" in h.lower())
+    if job_links:
+        # Return parent elements of job links
+        return [link.parent for link in job_links]
+    
+    return []
+
+
+def is_job_remote(title: str, description: str = None, location: Location = None) -> bool:
+    """
+    Determines if a job is remote based on title, description, and location
+    :param title: Job title
+    :param description: Job description
+    :param location: Job location
+    :return: True if job is remote, False otherwise
+    """
+    remote_keywords = ["remote", "work from home", "wfh", "home based"]
+    
+    # Combine all text fields
+    full_text = title.lower()
+    if description:
+        full_text += " " + description.lower()
+    if location:
+        full_text += " " + location.display_location().lower()
+    
+    # Check for remote keywords
+    return any(keyword in full_text for keyword in remote_keywords)

jobspy/exception.py

@@ -34,3 +34,12 @@ 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")
+
+
+class BDJobsException(Exception):
+    def __init__(self, message=None):
+        super().__init__(message or "An error occurred with BDJobs")

jobspy/glassdoor/__init__.py

@@ -34,13 +34,13 @@ log = create_logger("Glassdoor")
 
 class Glassdoor(Scraper):
     def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         """
         Initializes GlassdoorScraper with the Glassdoor job search url
         """
         site = Site(Site.GLASSDOOR)
-        super().__init__(site, proxies=proxies, ca_cert=ca_cert)
+        super().__init__(site, proxies=proxies, ca_cert=ca_cert, user_agent=user_agent)
 
         self.base_url = None
         self.country = None
@@ -65,6 +65,8 @@ class Glassdoor(Scraper):
         )
         token = self._get_csrf_token()
         headers["gd-csrf-token"] = token if token else fallback_token
+        if self.user_agent:
+            headers["user-agent"] = self.user_agent
         self.session.headers.update(headers)
 
         location_id, location_type = self._get_location(

jobspy/glassdoor/constant.py

@@ -13,7 +13,7 @@ headers = {
     "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",
+    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36",
 }
 query_template = """
         query JobSearchResultsQuery(

jobspy/google/__init__.py

@@ -22,7 +22,7 @@ from jobspy.google.util import log, find_job_info_initial_page, find_job_info
 
 class Google(Scraper):
     def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         """
         Initializes Google Scraper with the Goodle jobs search url

jobspy/indeed/__init__.py

@@ -28,7 +28,7 @@ log = create_logger("Indeed")
 
 class Indeed(Scraper):
     def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         """
         Initializes IndeedScraper with the Indeed API url

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 sssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrompensation:
+    :param compensation:
     :return: compensation object
     """
     if not compensation["baseSalary"] and not compensation["estimated"]:

jobspy/linkedin/__init__.py

@@ -14,10 +14,11 @@ 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,
@@ -34,6 +35,7 @@ from jobspy.util import (
     extract_emails_from_text,
     currency_parser,
     markdown_converter,
+    plain_converter,
     create_session,
     remove_attributes,
     create_logger,
@@ -49,7 +51,7 @@ class LinkedIn(Scraper):
     jobs_per_page = 25
 
     def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         """
         Initializes LinkedInScraper with the LinkedIn job search url
@@ -163,7 +165,7 @@ class LinkedIn(Scraper):
 
             if continue_search():
                 time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
-                start += len(job_list)
+                start += len(job_cards)
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
@@ -173,7 +175,7 @@ class LinkedIn(Scraper):
     ) -> Optional[JobPost]:
         salary_tag = job_card.find("span", class_="job-search-card__salary-info")
 
-        compensation = None
+        compensation = description = None
         if salary_tag:
             salary_text = salary_tag.get_text(separator=" ").strip()
             salary_values = [currency_parser(value) for value in salary_text.split("-")]
@@ -207,6 +209,10 @@ class LinkedIn(Scraper):
             if metadata_card
             else None
         )
+        if not datetime_tag and metadata_card:
+            datetime_tag = metadata_card.find(
+                "time", class_="job-search-card__listdate--new"
+            )
         date_posted = None
         if datetime_tag and "datetime" in datetime_tag.attrs:
             datetime_str = datetime_tag["datetime"]
@@ -217,6 +223,8 @@ 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}",
@@ -224,6 +232,7 @@ 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,
@@ -232,7 +241,7 @@ 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(job_details.get("description")),
+            emails=extract_emails_from_text(description),
             company_logo=job_details.get("company_logo"),
             job_function=job_details.get("job_function"),
         )
@@ -263,7 +272,8 @@ class LinkedIn(Scraper):
             description = div_content.prettify(formatter="html")
             if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
                 description = markdown_converter(description)
-
+            elif self.scraper_input.description_format == DescriptionFormat.PLAIN:
+                description = plain_converter(description)
         h3_tag = soup.find(
             "h3", text=lambda text: text and "Job function" in text.strip()
         )

jobspy/linkedin/util.py

@@ -1,6 +1,6 @@
 from bs4 import BeautifulSoup
 
-from jobspy.model import JobType
+from jobspy.model import JobType, Location
 from jobspy.util import get_enum_from_job_type
 
 
@@ -83,3 +83,14 @@ 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

@@ -68,17 +68,22 @@ class Country(Enum):
     AUSTRALIA = ("australia", "au", "com.au")
     AUSTRIA = ("austria", "at", "at")
     BAHRAIN = ("bahrain", "bh")
+    BANGLADESH = ("bangladesh", "bd")  # Added Bangladesh
     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")
@@ -92,6 +97,8 @@ 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")
@@ -112,6 +119,8 @@ 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")
@@ -225,7 +234,7 @@ class Compensation(BaseModel):
 class DescriptionFormat(Enum):
     MARKDOWN = "markdown"
     HTML = "html"
-
+    PLAIN = "plain"
 
 class JobPost(BaseModel):
     id: str | None = None
@@ -246,13 +255,13 @@ 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
@@ -260,9 +269,16 @@ 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] = []
@@ -275,6 +291,8 @@ class Site(Enum):
     GLASSDOOR = "glassdoor"
     GOOGLE = "google"
     BAYT = "bayt"
+    NAUKRI = "naukri"
+    BDJOBS = "bdjobs"  # Add this line
 
 
 class SalarySource(Enum):
@@ -298,17 +316,20 @@ class ScraperInput(BaseModel):
     linkedin_company_ids: list[int] | None = None
     description_format: DescriptionFormat | None = DescriptionFormat.MARKDOWN
 
+    request_timeout: int = 60
+
     results_wanted: int = 15
     hours_old: int | None = None
 
 
 class Scraper(ABC):
     def __init__(
-        self, site: Site, proxies: list[str] | None = None, ca_cert: str | None = None
+        self, site: Site, proxies: list[str] | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         self.site = site
         self.proxies = proxies
         self.ca_cert = ca_cert
+        self.user_agent = user_agent
 
     @abstractmethod
     def scrape(self, scraper_input: ScraperInput) -> JobResponse: ...

jobspy/naukri/__init__.py

@@ -0,0 +1,304 @@
+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, user_agent: 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}')}"
+        raw_description = job.get("jobDescription") if full_descr else None
+
+        job_type = parse_job_type(raw_description) if raw_description else None
+        company_industry = parse_company_industry(raw_description) if raw_description else None
+
+        description = raw_description
+        if description and self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
+            description = markdown_converter(description)
+
+        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

@@ -0,0 +1,11 @@
+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

@@ -0,0 +1,38 @@
+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 |str) -> list[JobType] | None:
+    """
+    Gets the job type from the job page
+    """
+    if isinstance(soup, str):
+        soup = BeautifulSoup(soup, "html.parser")
+    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) -> str | None:
+    """
+    Gets the company industry from the job page
+    """
+    if isinstance(soup, str):
+        soup = BeautifulSoup(soup, "html.parser")
+    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

@@ -47,11 +47,12 @@ 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)
@@ -86,7 +87,6 @@ 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)
@@ -157,6 +157,15 @@ def markdown_converter(description_html: str):
     markdown = md(description_html)
     return markdown.strip()
 
+def plain_converter(decription_html:str):
+    from bs4 import BeautifulSoup
+    if decription_html is None:
+        return None
+    soup = BeautifulSoup(decription_html, "html.parser")
+    text = soup.get_text(separator=" ")
+    text = re.sub(r'\s+',' ',text)
+    return text.strip()
+
 
 def extract_emails_from_text(text: str) -> list[str] | None:
     if not text:
@@ -344,4 +353,11 @@ 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",
 ]

jobspy/ziprecruiter/__init__.py

@@ -38,7 +38,7 @@ class ZipRecruiter(Scraper):
     api_url = "https://api.ziprecruiter.com"
 
     def __init__(
-        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None, user_agent: str | None = None
     ):
         """
         Initializes ZipRecruiterScraper with the ZipRecruiter job search url

poetry.lock

@@ -749,17 +749,6 @@ files = [
 [package.extras]
 all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
 
-[[package]]
-name = "iniconfig"
-version = "2.0.0"
-description = "brain-dead simple config-ini parsing"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
-    {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
-]
-
 [[package]]
 name = "ipykernel"
 version = "6.29.5"
@@ -1229,13 +1218,13 @@ files = [
 
 [[package]]
 name = "markdownify"
-version = "0.13.1"
+version = "1.1.0"
 description = "Convert HTML to markdown."
 optional = false
 python-versions = "*"
 files = [
-    {file = "markdownify-0.13.1-py3-none-any.whl", hash = "sha256:1d181d43d20902bcc69d7be85b5316ed174d0dda72ff56e14ae4c95a4a407d22"},
-    {file = "markdownify-0.13.1.tar.gz", hash = "sha256:ab257f9e6bd4075118828a28c9d02f8a4bfeb7421f558834aa79b2dfeb32a098"},
+    {file = "markdownify-1.1.0-py3-none-any.whl", hash = "sha256:32a5a08e9af02c8a6528942224c91b933b4bd2c7d078f9012943776fc313eeef"},
+    {file = "markdownify-1.1.0.tar.gz", hash = "sha256:449c0bbbf1401c5112379619524f33b63490a8fa479456d41de9dc9e37560ebd"},
 ]
 
 [package.dependencies]
@@ -1710,21 +1699,6 @@ docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.0.2)", "sphinx-a
 test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.2)", "pytest-cov (>=5)", "pytest-mock (>=3.14)"]
 type = ["mypy (>=1.11.2)"]
 
-[[package]]
-name = "pluggy"
-version = "1.5.0"
-description = "plugin and hook calling mechanisms for python"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"},
-    {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"},
-]
-
-[package.extras]
-dev = ["pre-commit", "tox"]
-testing = ["pytest", "pytest-benchmark"]
-
 [[package]]
 name = "pre-commit"
 version = "4.0.1"
@@ -1975,28 +1949,6 @@ files = [
 [package.extras]
 windows-terminal = ["colorama (>=0.4.6)"]
 
-[[package]]
-name = "pytest"
-version = "7.4.4"
-description = "pytest: simple powerful testing with Python"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "pytest-7.4.4-py3-none-any.whl", hash = "sha256:b090cdf5ed60bf4c45261be03239c2c1c22df034fbffe691abe93cd80cea01d8"},
-    {file = "pytest-7.4.4.tar.gz", hash = "sha256:2cf0005922c6ace4a3e2ec8b4080eb0d9753fdc93107415332f50ce9e7994280"},
-]
-
-[package.dependencies]
-colorama = {version = "*", markers = "sys_platform == \"win32\""}
-exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
-iniconfig = "*"
-packaging = "*"
-pluggy = ">=0.12,<2.0"
-tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
-
-[package.extras]
-testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
-
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -2869,4 +2821,4 @@ files = [
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "57169347d2ce0ff19c4d3024ce000651bb3a816e36f454618f480741094fb4a7"
+content-hash = "6260adc8f96f6cf1ba4e2c23f05504c19e67140b9d346aed3d12eea6957b2104"

pyproject.toml

@@ -4,12 +4,12 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.77"
+version = "1.1.82"
 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"]
+keywords = [ "jobs-scraper", "linkedin", "indeed", "glassdoor", "ziprecruiter", "bayt", "naukri"]
 [[tool.poetry.packages]]
 include = "jobspy"
 
@@ -21,10 +21,10 @@ python = "^3.10"
 requests = "^2.31.0"
 beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"
-NUMPY = "1.26.3"
+numpy = ">=1.26.0"
 pydantic = "^2.3.0"
 tls-client = "^1.0.1"
-markdownify = "^0.13.1"
+markdownify = "^1.1.0"
 regex = "^2024.4.28"
 
 [tool.poetry.group.dev.dependencies]