support for socks5 proxies (#266)

Co-authored-by: Piotr Geca <piotr.geca@npl.co.uk>

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

@@ -1,9 +1,13 @@
-name: Publish Python 🐍 distributions 📦 to PyPI
-on: push
+name: Publish JobSpy to PyPi
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
 
 jobs:
   build-n-publish:
-    name: Build and publish Python 🐍 distributions 📦 to PyPI
+    name: Build and publish JobSpy to PyPi
     runs-on: ubuntu-latest
 
     steps:
@@ -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 }}

.github/workflows/python-test.yml

@@ -1,22 +0,0 @@
-name: Python Tests
-
-on:
-  pull_request:
-    branches:
-      - main
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: '3.8'
-      - name: Install dependencies
-        run: |
-          pip install poetry
-          poetry install
-      - name: Run tests
-        run: poetry run pytest tests/test_all.py

README.md

@@ -1,17 +1,12 @@
 <img src="https://github.com/cullenwatson/JobSpy/assets/78247585/ae185b7e-e444-4712-8bb9-fa97f53e896b" width="400">
 
-**JobSpy** is a simple, yet comprehensive, job scraping library.
-
-**Not technical?** Try out the web scraping tool on our site at [usejobspy.com](https://usejobspy.com).
-
-*Looking to build a data-focused software product?* **[Book a call](https://bunsly.com/)** *to
-work with us.*
+**JobSpy** is a job scraping library with the goal of aggregating all the jobs from popular job boards with one tool.
 
 ## Features
 
-- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, & **ZipRecruiter** simultaneously
-- Aggregates the job postings in a Pandas DataFrame
-- Proxies support
+- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, **ZipRecruiter**, **Bayt** & **Naukri** concurrently
+- Aggregates the job postings in a dataframe
+- Proxies support to bypass blocking
 
 ![jobspy](https://github.com/cullenwatson/JobSpy/assets/78247585/ec7ef355-05f6-4fd3-8161-a817e31c5c57)
 
@@ -30,16 +25,16 @@ import csv
 from jobspy import scrape_jobs
 
 jobs = scrape_jobs(
-    site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor", "google"],
+    site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor", "google", "bayt", "naukri"],
     search_term="software engineer",
+    google_search_term="software engineer jobs near San Francisco, CA since yesterday",
     location="San Francisco, CA",
     results_wanted=20,
-    hours_old=72, # (only Linkedin/Indeed is hour specific, others round up to days old)
-    country_indeed='USA',  # only needed for indeed / glassdoor
+    hours_old=72,
+    country_indeed='USA',
     
-    # linkedin_fetch_description=True # get more info such as full description, direct job url for linkedin (slower)
+    # linkedin_fetch_description=True # gets more info such as description, direct job url (slower)
     # proxies=["208.195.175.46:65095", "208.195.175.45:65095", "localhost"],
-    
 )
 print(f"Found {len(jobs)} jobs")
 print(jobs.head())
@@ -56,6 +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()`
@@ -63,10 +59,13 @@ zip_recruiter Software Developer                 TEKsystems        Phoenix
 ```plaintext
 Optional
 ├── site_name (list|str): 
-|    linkedin, zip_recruiter, indeed, glassdoor 
-|    (default is all four)
+|    linkedin, zip_recruiter, indeed, glassdoor, google, bayt
+|    (default is all)
 │
 ├── search_term (str)
+|
+├── google_search_term (str)
+|     search term for google jobs. This is the only param for filtering google jobs.
 │
 ├── location (str)
 │
@@ -86,7 +85,7 @@ Optional
 |    number of job results to retrieve for each site specified in 'site_name'
 │
 ├── easy_apply (bool): 
-|    filters for jobs that are hosted on the job board site
+|    filters for jobs that are hosted on the job board site (LinkedIn easy apply filter no longer works)
 │
 ├── description_format (str): 
 |    markdown, html (Format type of the job descriptions. Default is markdown.)
@@ -131,46 +130,6 @@ Optional
 |    - easy_apply
 ```
 
-
-### JobPost Schema
-
-```plaintext
-JobPost
-├── title
-├── company
-├── company_url
-├── job_url
-├── location
-│   ├── country
-│   ├── city
-│   ├── state
-├── description
-├── job_type: fulltime, parttime, internship, contract
-├── job_function
-│   ├── interval: yearly, monthly, weekly, daily, hourly
-│   ├── min_amount
-│   ├── max_amount
-│   ├── currency
-│   └── salary_source: direct_data, description (parsed from posting)
-├── date_posted
-├── emails
-└── is_remote
-
-Linkedin specific
-└── job_level
-
-Linkedin & Indeed specific
-└── company_industry
-
-Indeed specific
-├── company_country
-├── company_addresses
-├── company_employees_label
-├── company_revenue_label
-├── company_description
-└── company_logo
-```
-
 ## Supported Countries for Job Searching
 
 ### **LinkedIn**
@@ -207,6 +166,11 @@ You can specify the following countries when searching on Indeed (use the exact
 | United Arab Emirates | UK*          | USA*       | Uruguay        |
 | Venezuela            | Vietnam*     |            |                |
 
+### **Bayt**
+
+Bayt only uses the search_term parameter currently and searches internationally
+
+
 
 ## Notes
 * Indeed is the best scraper currently with no rate limiting.  
@@ -217,7 +181,23 @@ You can specify the following countries when searching on Indeed (use the exact
 
 ---
 **Q: Why is Indeed giving unrelated roles?**  
-**A:** Indeed is searching each one of your terms e.g. software intern, it searches software OR intern. Try search_term='"software intern"' in quotes for stricter searching
+**A:** Indeed searches the description too.
+
+- use - to remove words
+- "" for exact match
+
+Example of a good Indeed query
+
+```py
+search_term='"engineering intern" software summer (java OR python OR c++) 2025 -tax -marketing'
+```
+
+This searches the description/title and must include software, summer, 2025, one of the languages, engineering intern exactly, no tax, no marketing.
+
+---
+
+**Q: No results when using "google"?**  
+**A:** You have to use super specific syntax. Search for google jobs on your browser and then whatever pops up in the google jobs search box after applying some filters is what you need to copy & paste into the google_search_term. 
 
 ---
 
@@ -229,8 +209,49 @@ You can specify the following countries when searching on Indeed (use the exact
 
 ---
 
-**Q: Encountering issues with your queries?**  
-**A:** Try reducing the number of `results_wanted` and/or broadening the filters. If problems
-persist, [submit an issue](https://github.com/Bunsly/JobSpy/issues).
+### JobPost Schema
 
----
+```plaintext
+JobPost
+├── title
+├── company
+├── company_url
+├── job_url
+├── location
+│   ├── country
+│   ├── city
+│   ├── state
+├── is_remote
+├── description
+├── job_type: fulltime, parttime, internship, contract
+├── job_function
+│   ├── interval: yearly, monthly, weekly, daily, hourly
+│   ├── min_amount
+│   ├── max_amount
+│   ├── currency
+│   └── salary_source: direct_data, description (parsed from posting)
+├── date_posted
+└── emails
+
+Linkedin specific
+└── job_level
+
+Linkedin & Indeed specific
+└── company_industry
+
+Indeed specific
+├── company_country
+├── company_addresses
+├── company_employees_label
+├── 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

@@ -1,29 +1,34 @@
 from __future__ import annotations
 
-import pandas as pd
-from typing import Tuple
 from concurrent.futures import ThreadPoolExecutor, as_completed
+from typing import Tuple
 
-from .jobs import JobType, Location
-from .scrapers.utils import set_logger_level, extract_salary, create_logger
-from .scrapers.indeed import IndeedScraper
-from .scrapers.ziprecruiter import ZipRecruiterScraper
-from .scrapers.glassdoor import GlassdoorScraper
-from .scrapers.google import GoogleJobsScraper
-from .scrapers.linkedin import LinkedInScraper
-from .scrapers import SalarySource, ScraperInput, Site, JobResponse, Country
-from .scrapers.exceptions import (
-    LinkedInException,
-    IndeedException,
-    ZipRecruiterException,
-    GlassdoorException,
-    GoogleJobsException,
+import pandas as pd
+
+from jobspy.bayt import BaytScraper
+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 (
+    set_logger_level,
+    extract_salary,
+    create_logger,
+    get_enum_from_value,
+    map_str_to_site,
+    convert_to_annual,
+    desired_order,
 )
+from jobspy.ziprecruiter import ZipRecruiter
 
 
 def scrape_jobs(
     site_name: str | list[str] | Site | list[Site] | None = None,
     search_term: str | None = None,
+    google_search_term: str | None = None,
     location: str | None = None,
     distance: int | None = 50,
     is_remote: bool = False,
@@ -31,7 +36,6 @@ def scrape_jobs(
     easy_apply: bool | None = None,
     results_wanted: int = 15,
     country_indeed: str = "usa",
-    hyperlinks: bool = False,
     proxies: list[str] | str | None = None,
     ca_cert: str | None = None,
     description_format: str = "markdown",
@@ -40,31 +44,23 @@ def scrape_jobs(
     offset: int | None = 0,
     hours_old: int = None,
     enforce_annual_salary: bool = False,
-    verbose: int = 2,
+    verbose: int = 0,
     **kwargs,
 ) -> pd.DataFrame:
     """
-    Simultaneously scrapes job data from multiple job sites.
-    :return: pandas dataframe containing job data
+    Scrapes job data from job boards concurrently
+    :return: Pandas DataFrame containing job data
     """
     SCRAPER_MAPPING = {
-        Site.LINKEDIN: LinkedInScraper,
-        Site.INDEED: IndeedScraper,
-        Site.ZIP_RECRUITER: ZipRecruiterScraper,
-        Site.GLASSDOOR: GlassdoorScraper,
-        Site.GOOGLE: GoogleJobsScraper,
+        Site.LINKEDIN: LinkedIn,
+        Site.INDEED: Indeed,
+        Site.ZIP_RECRUITER: ZipRecruiter,
+        Site.GLASSDOOR: Glassdoor,
+        Site.GOOGLE: Google,
+        Site.BAYT: BaytScraper,
+        Site.NAUKRI: Naukri,
     }
     set_logger_level(verbose)
-
-    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:
-            if value_str in job_type.value:
-                return job_type
-        raise Exception(f"Invalid job type: {value_str}")
-
     job_type = get_enum_from_value(job_type) if job_type else None
 
     def get_site_type():
@@ -86,6 +82,7 @@ def scrape_jobs(
         site_type=get_site_type(),
         country=country_enum,
         search_term=search_term,
+        google_search_term=google_search_term,
         location=location,
         distance=distance,
         is_remote=is_remote,
@@ -123,28 +120,12 @@ def scrape_jobs(
             site_value, scraped_data = future.result()
             site_to_jobs_dict[site_value] = scraped_data
 
-    def convert_to_annual(job_data: dict):
-        if job_data["interval"] == "hourly":
-            job_data["min_amount"] *= 2080
-            job_data["max_amount"] *= 2080
-        if job_data["interval"] == "monthly":
-            job_data["min_amount"] *= 12
-            job_data["max_amount"] *= 12
-        if job_data["interval"] == "weekly":
-            job_data["min_amount"] *= 52
-            job_data["max_amount"] *= 52
-        if job_data["interval"] == "daily":
-            job_data["min_amount"] *= 260
-            job_data["max_amount"] *= 260
-        job_data["interval"] = "yearly"
-
     jobs_dfs: list[pd.DataFrame] = []
 
     for site, job_response in site_to_jobs_dict.items():
         for job in job_response.jobs:
             job_data = job.dict()
             job_url = job_data["job_url"]
-            job_data["job_url_hyper"] = f'<a href="{job_url}">{job_url}</a>'
             job_data["site"] = site
             job_data["company"] = job_data["company_name"]
             job_data["job_type"] = (
@@ -160,6 +141,7 @@ 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"] = (
@@ -178,7 +160,6 @@ def scrape_jobs(
                     and job_data["max_amount"]
                 ):
                     convert_to_annual(job_data)
-
             else:
                 if country_enum == Country.USA:
                     (
@@ -197,6 +178,17 @@ 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)
 
@@ -207,38 +199,6 @@ def scrape_jobs(
         # Step 2: Concatenate the filtered DataFrames
         jobs_df = pd.concat(filtered_dfs, ignore_index=True)
 
-        # Desired column order
-        desired_order = [
-            "id",
-            "site",
-            "job_url_hyper" if hyperlinks else "job_url",
-            "job_url_direct",
-            "title",
-            "company",
-            "location",
-            "job_type",
-            "date_posted",
-            "salary_source",
-            "interval",
-            "min_amount",
-            "max_amount",
-            "currency",
-            "is_remote",
-            "job_level",
-            "job_function",
-            "listing_type",
-            "emails",
-            "description",
-            "company_industry",
-            "company_url",
-            "company_logo",
-            "company_url_direct",
-            "company_addresses",
-            "company_num_employees",
-            "company_revenue",
-            "company_description",
-        ]
-
         # Step 3: Ensure all desired columns are present, adding missing ones as empty
         for column in desired_order:
             if column not in jobs_df.columns:
@@ -248,6 +208,8 @@ def scrape_jobs(
         jobs_df = jobs_df[desired_order]
 
         # Step 4: Sort the DataFrame as required
-        return jobs_df.sort_values(by=["site", "date_posted"], ascending=[True, False])
+        return jobs_df.sort_values(
+            by=["site", "date_posted"], ascending=[True, False]
+        ).reset_index(drop=True)
     else:
-        return pd.DataFrame()
+        return pd.DataFrame()

jobspy/bayt/__init__.py

@@ -0,0 +1,145 @@
+from __future__ import annotations
+
+import random
+import time
+
+from bs4 import BeautifulSoup
+
+from jobspy.model import (
+    Scraper,
+    ScraperInput,
+    Site,
+    JobPost,
+    JobResponse,
+    Location,
+    Country,
+)
+from jobspy.util import create_logger, create_session
+
+log = create_logger("Bayt")
+
+
+class BaytScraper(Scraper):
+    base_url = "https://www.bayt.com"
+    delay = 2
+    band_delay = 3
+
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+    ):
+        super().__init__(Site.BAYT, proxies=proxies, ca_cert=ca_cert)
+        self.scraper_input = None
+        self.session = None
+        self.country = "worldwide"
+
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+        self.scraper_input = scraper_input
+        self.session = create_session(
+            proxies=self.proxies, ca_cert=self.ca_cert, is_tls=False, has_retry=True
+        )
+        job_list: list[JobPost] = []
+        page = 1
+        results_wanted = (
+            scraper_input.results_wanted if scraper_input.results_wanted else 10
+        )
+
+        while len(job_list) < results_wanted:
+            log.info(f"Fetching Bayt jobs page {page}")
+            job_elements = self._fetch_jobs(self.scraper_input.search_term, page)
+            if not job_elements:
+                break
+
+            if job_elements:
+                log.debug(
+                    "First job element snippet:\n" + job_elements[0].prettify()[:500]
+                )
+
+            initial_count = len(job_list)
+            for job in job_elements:
+                try:
+                    job_post = self._extract_job_info(job)
+                    if job_post:
+                        job_list.append(job_post)
+                        if len(job_list) >= results_wanted:
+                            break
+                    else:
+                        log.debug(
+                            "Extraction returned None. Job snippet:\n"
+                            + job.prettify()[:500]
+                        )
+                except Exception as e:
+                    log.error(f"Bayt: Error extracting job info: {str(e)}")
+                    continue
+
+            if len(job_list) == initial_count:
+                log.info(f"No new jobs found on page {page}. Ending pagination.")
+                break
+
+            page += 1
+            time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
+
+        job_list = job_list[: scraper_input.results_wanted]
+        return JobResponse(jobs=job_list)
+
+    def _fetch_jobs(self, query: str, page: int) -> list | None:
+        """
+        Grabs the job results for the given query and page number.
+        """
+        try:
+            url = f"{self.base_url}/en/international/jobs/{query}-jobs/?page={page}"
+            response = self.session.get(url)
+            response.raise_for_status()
+            soup = BeautifulSoup(response.text, "html.parser")
+            job_listings = soup.find_all("li", attrs={"data-js-job": ""})
+            log.debug(f"Found {len(job_listings)} job listing elements")
+            return job_listings
+        except Exception as e:
+            log.error(f"Bayt: Error fetching jobs - {str(e)}")
+            return None
+
+    def _extract_job_info(self, job: BeautifulSoup) -> JobPost | None:
+        """
+        Extracts the job information from a single job listing.
+        """
+        # Find the h2 element holding the title and link (no class filtering)
+        job_general_information = job.find("h2")
+        if not job_general_information:
+            return
+
+        job_title = job_general_information.get_text(strip=True)
+        job_url = self._extract_job_url(job_general_information)
+        if not job_url:
+            return
+
+        # Extract company name using the original approach:
+        company_tag = job.find("div", class_="t-nowrap p10l")
+        company_name = (
+            company_tag.find("span").get_text(strip=True)
+            if company_tag and company_tag.find("span")
+            else None
+        )
+
+        # Extract location using the original approach:
+        location_tag = job.find("div", class_="t-mute t-small")
+        location = location_tag.get_text(strip=True) if location_tag else None
+
+        job_id = f"bayt-{abs(hash(job_url))}"
+        location_obj = Location(
+            city=location,
+            country=Country.from_string(self.country),
+        )
+        return JobPost(
+            id=job_id,
+            title=job_title,
+            company_name=company_name,
+            location=location_obj,
+            job_url=job_url,
+        )
+
+    def _extract_job_url(self, job_general_information: BeautifulSoup) -> str | None:
+        """
+        Pulls the job URL from the 'a' within the h2 element.
+        """
+        a_tag = job_general_information.find("a")
+        if a_tag and a_tag.has_attr("href"):
+            return self.base_url + a_tag["href"].strip()

jobspy/exception.py

@@ -1,5 +1,5 @@
 """
-jobspy.scrapers.exceptions
+jobspy.jobboard.exceptions
 ~~~~~~~~~~~~~~~~~~~
 
 This module contains the set of Scrapers' exceptions.
@@ -29,3 +29,12 @@ class GlassdoorException(Exception):
 class GoogleJobsException(Exception):
     def __init__(self, message=None):
         super().__init__(message or "An error occurred with Google Jobs")
+
+
+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/glassdoor/__init__.py

@@ -1,41 +1,38 @@
-"""
-jobspy.scrapers.glassdoor
-~~~~~~~~~~~~~~~~~~~
-
-This module contains routines to scrape Glassdoor.
-"""
-
 from __future__ import annotations
 
 import re
 import json
 import requests
-from typing import Optional, Tuple
+from typing import Tuple
 from datetime import datetime, timedelta
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
-from .constants import fallback_token, query_template, headers
-from .. import Scraper, ScraperInput, Site
-from ..utils import extract_emails_from_text, create_logger
-from ..exceptions import GlassdoorException
-from ..utils import (
+from jobspy.glassdoor.constant import fallback_token, query_template, headers
+from jobspy.glassdoor.util import (
+    get_cursor_for_page,
+    parse_compensation,
+    parse_location,
+)
+from jobspy.util import (
+    extract_emails_from_text,
+    create_logger,
     create_session,
     markdown_converter,
 )
-from ...jobs import (
+from jobspy.exception import GlassdoorException
+from jobspy.model import (
     JobPost,
-    Compensation,
-    CompensationInterval,
-    Location,
     JobResponse,
-    JobType,
     DescriptionFormat,
+    Scraper,
+    ScraperInput,
+    Site,
 )
 
-logger = create_logger("Glassdoor")
+log = create_logger("Glassdoor")
 
 
-class GlassdoorScraper(Scraper):
+class Glassdoor(Scraper):
     def __init__(
         self, proxies: list[str] | str | None = None, ca_cert: str | None = None
     ):
@@ -64,7 +61,7 @@ class GlassdoorScraper(Scraper):
         self.base_url = self.scraper_input.country.get_glassdoor_url()
 
         self.session = create_session(
-            proxies=self.proxies, ca_cert=self.ca_cert, is_tls=True, has_retry=True
+            proxies=self.proxies, ca_cert=self.ca_cert, has_retry=True
         )
         token = self._get_csrf_token()
         headers["gd-csrf-token"] = token if token else fallback_token
@@ -74,7 +71,7 @@ class GlassdoorScraper(Scraper):
             scraper_input.location, scraper_input.is_remote
         )
         if location_type is None:
-            logger.error("Glassdoor: location not parsed")
+            log.error("Glassdoor: location not parsed")
             return JobResponse(jobs=[])
         job_list: list[JobPost] = []
         cursor = None
@@ -83,7 +80,7 @@ class GlassdoorScraper(Scraper):
         tot_pages = (scraper_input.results_wanted // self.jobs_per_page) + 2
         range_end = min(tot_pages, self.max_pages + 1)
         for page in range(range_start, range_end):
-            logger.info(f"search page: {page} / {range_end-1}")
+            log.info(f"search page: {page} / {range_end - 1}")
             try:
                 jobs, cursor = self._fetch_jobs_page(
                     scraper_input, location_id, location_type, page, cursor
@@ -93,7 +90,7 @@ class GlassdoorScraper(Scraper):
                     job_list = job_list[: scraper_input.results_wanted]
                     break
             except Exception as e:
-                logger.error(f"Glassdoor: {str(e)}")
+                log.error(f"Glassdoor: {str(e)}")
                 break
         return JobResponse(jobs=job_list)
 
@@ -129,7 +126,7 @@ class GlassdoorScraper(Scraper):
             ValueError,
             Exception,
         ) as e:
-            logger.error(f"Glassdoor: {str(e)}")
+            log.error(f"Glassdoor: {str(e)}")
             return jobs, None
 
         jobs_data = res_json["data"]["jobListings"]["jobListings"]
@@ -146,7 +143,7 @@ class GlassdoorScraper(Scraper):
                 except Exception as exc:
                     raise GlassdoorException(f"Glassdoor generated an exception: {exc}")
 
-        return jobs, self.get_cursor_for_page(
+        return jobs, get_cursor_for_page(
             res_json["data"]["jobListings"]["paginationCursors"], page_num + 1
         )
 
@@ -185,9 +182,9 @@ class GlassdoorScraper(Scraper):
         if location_type == "S":
             is_remote = True
         else:
-            location = self.parse_location(location_name)
+            location = parse_location(location_name)
 
-        compensation = self.parse_compensation(job["header"])
+        compensation = parse_compensation(job["header"])
         try:
             description = self._fetch_job_description(job_id)
         except:
@@ -264,12 +261,12 @@ class GlassdoorScraper(Scraper):
         if res.status_code != 200:
             if res.status_code == 429:
                 err = f"429 Response - Blocked by Glassdoor for too many requests"
-                logger.error(err)
+                log.error(err)
                 return None, None
             else:
                 err = f"Glassdoor response status code {res.status_code}"
                 err += f" - {res.text}"
-                logger.error(f"Glassdoor response status code {res.status_code}")
+                log.error(f"Glassdoor response status code {res.status_code}")
                 return None, None
         items = res.json()
 
@@ -321,44 +318,3 @@ class GlassdoorScraper(Scraper):
                 {"filterKey": "jobType", "values": self.scraper_input.job_type.value[0]}
             )
         return json.dumps([payload])
-
-    @staticmethod
-    def parse_compensation(data: dict) -> Optional[Compensation]:
-        pay_period = data.get("payPeriod")
-        adjusted_pay = data.get("payPeriodAdjustedPay")
-        currency = data.get("payCurrency", "USD")
-        if not pay_period or not adjusted_pay:
-            return None
-
-        interval = None
-        if pay_period == "ANNUAL":
-            interval = CompensationInterval.YEARLY
-        elif pay_period:
-            interval = CompensationInterval.get_interval(pay_period)
-        min_amount = int(adjusted_pay.get("p10") // 1)
-        max_amount = int(adjusted_pay.get("p90") // 1)
-        return Compensation(
-            interval=interval,
-            min_amount=min_amount,
-            max_amount=max_amount,
-            currency=currency,
-        )
-
-    @staticmethod
-    def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
-        for job_type in JobType:
-            if job_type_str in job_type.value:
-                return [job_type]
-
-    @staticmethod
-    def parse_location(location_name: str) -> Location | None:
-        if not location_name or location_name == "Remote":
-            return
-        city, _, state = location_name.partition(", ")
-        return Location(city=city, state=state)
-
-    @staticmethod
-    def get_cursor_for_page(pagination_cursors, page_num):
-        for cursor_data in pagination_cursors:
-            if cursor_data["pageNumber"] == page_num:
-                return cursor_data["cursor"]

jobspy/glassdoor/util.py

@@ -0,0 +1,42 @@
+from jobspy.model import Compensation, CompensationInterval, Location, JobType
+
+
+def parse_compensation(data: dict) -> Compensation | None:
+    pay_period = data.get("payPeriod")
+    adjusted_pay = data.get("payPeriodAdjustedPay")
+    currency = data.get("payCurrency", "USD")
+    if not pay_period or not adjusted_pay:
+        return None
+
+    interval = None
+    if pay_period == "ANNUAL":
+        interval = CompensationInterval.YEARLY
+    elif pay_period:
+        interval = CompensationInterval.get_interval(pay_period)
+    min_amount = int(adjusted_pay.get("p10") // 1)
+    max_amount = int(adjusted_pay.get("p90") // 1)
+    return Compensation(
+        interval=interval,
+        min_amount=min_amount,
+        max_amount=max_amount,
+        currency=currency,
+    )
+
+
+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]
+
+
+def parse_location(location_name: str) -> Location | None:
+    if not location_name or location_name == "Remote":
+        return
+    city, _, state = location_name.partition(", ")
+    return Location(city=city, state=state)
+
+
+def get_cursor_for_page(pagination_cursors, page_num):
+    for cursor_data in pagination_cursors:
+        if cursor_data["pageNumber"] == page_num:
+            return cursor_data["cursor"]

jobspy/google/__init__.py

@@ -1,10 +1,3 @@
-"""
-jobspy.scrapers.google
-~~~~~~~~~~~~~~~~~~~
-
-This module contains routines to scrape Glassdoor.
-"""
-
 from __future__ import annotations
 
 import math
@@ -13,33 +6,30 @@ import json
 from typing import Tuple
 from datetime import datetime, timedelta
 
-from .constants import headers_jobs, headers_initial, async_param
-from .. import Scraper, ScraperInput, Site
-from ..utils import extract_emails_from_text, create_logger, extract_job_type
-from ..utils import (
-    create_session,
-)
-from ...jobs import (
+from jobspy.google.constant import headers_jobs, headers_initial, async_param
+from jobspy.model import (
+    Scraper,
+    ScraperInput,
+    Site,
     JobPost,
     JobResponse,
     Location,
     JobType,
 )
-
-logger = create_logger("Google")
+from jobspy.util import extract_emails_from_text, extract_job_type, create_session
+from jobspy.google.util import log, find_job_info_initial_page, find_job_info
 
 
-class GoogleJobsScraper(Scraper):
+class Google(Scraper):
     def __init__(
         self, proxies: list[str] | str | None = None, ca_cert: str | None = None
     ):
         """
-        Initializes GlassdoorScraper with the Glassdoor job search url
+        Initializes Google Scraper with the Goodle jobs search url
         """
         site = Site(Site.GOOGLE)
         super().__init__(site, proxies=proxies, ca_cert=ca_cert)
 
-        self.base_url = None
         self.country = None
         self.session = None
         self.scraper_input = None
@@ -50,35 +40,39 @@ class GoogleJobsScraper(Scraper):
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
         """
-        Scrapes Glassdoor for jobs with scraper_input criteria.
+        Scrapes Google 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_glassdoor_url()
 
         self.session = create_session(
             proxies=self.proxies, ca_cert=self.ca_cert, is_tls=False, has_retry=True
         )
-        forward_cursor = self._get_initial_cursor()
+        forward_cursor, job_list = self._get_initial_cursor_and_jobs()
         if forward_cursor is None:
-            logger.error("initial cursor not found")
-            return JobResponse(jobs=[])
+            log.warning(
+                "initial cursor not found, try changing your query or there was at most 10 results"
+            )
+            return JobResponse(jobs=job_list)
 
         page = 1
-        job_list: list[JobPost] = []
 
         while (
             len(self.seen_urls) < scraper_input.results_wanted + scraper_input.offset
             and forward_cursor
         ):
-            logger.info(
+            log.info(
                 f"search page: {page} / {math.ceil(scraper_input.results_wanted / self.jobs_per_page)}"
             )
-            jobs, forward_cursor = self._get_jobs_next_page(forward_cursor)
+            try:
+                jobs, forward_cursor = self._get_jobs_next_page(forward_cursor)
+            except Exception as e:
+                log.error(f"failed to get jobs on page: {page}, {e}")
+                break
             if not jobs:
-                logger.info(f"found no jobs on page: {page}")
+                log.info(f"found no jobs on page: {page}")
                 break
             job_list += jobs
             page += 1
@@ -89,8 +83,8 @@ class GoogleJobsScraper(Scraper):
             ]
         )
 
-    def _get_initial_cursor(self):
-        """Gets initial cursor to paginate through job listings"""
+    def _get_initial_cursor_and_jobs(self) -> Tuple[str, list[JobPost]]:
+        """Gets initial cursor and jobs to paginate through job listings"""
         query = f"{self.scraper_input.search_term} jobs"
 
         def get_time_range(hours_old):
@@ -123,13 +117,22 @@ class GoogleJobsScraper(Scraper):
         if self.scraper_input.is_remote:
             query += " remote"
 
+        if self.scraper_input.google_search_term:
+            query = self.scraper_input.google_search_term
+
         params = {"q": query, "udm": "8"}
         response = self.session.get(self.url, headers=headers_initial, params=params)
 
         pattern_fc = r'<div jsname="Yust4d"[^>]+data-async-fc="([^"]+)"'
         match_fc = re.search(pattern_fc, response.text)
         data_async_fc = match_fc.group(1) if match_fc else None
-        return data_async_fc
+        jobs_raw = find_job_info_initial_page(response.text)
+        jobs = []
+        for job_raw in jobs_raw:
+            job_post = self._parse_job(job_raw)
+            if job_post:
+                jobs.append(job_post)
+        return data_async_fc, jobs
 
     def _get_jobs_next_page(self, forward_cursor: str) -> Tuple[list[JobPost], str]:
         params = {"fc": [forward_cursor], "fcv": ["3"], "async": [async_param]}
@@ -149,69 +152,51 @@ class GoogleJobsScraper(Scraper):
         match_fc = re.search(pattern_fc, job_data)
         data_async_fc = match_fc.group(1) if match_fc else None
         jobs_on_page = []
-
         for array in parsed:
-
             _, job_data = array
             if not job_data.startswith("[[["):
                 continue
             job_d = json.loads(job_data)
 
-            job_info = self._find_job_info(job_d)
-
-            job_url = job_info[3][0][0] if job_info[3] and job_info[3][0] else None
-            if job_url in self.seen_urls:
-                continue
-            self.seen_urls.add(job_url)
-
-            title = job_info[0]
-            company_name = job_info[1]
-            location = city = job_info[2]
-            state = country = date_posted = None
-            if location and "," in location:
-                city, state, *country = [*map(lambda x: x.strip(), location.split(","))]
-
-            days_ago_str = job_info[12]
-            if type(days_ago_str) == str:
-                match = re.search(r"\d+", days_ago_str)
-                days_ago = int(match.group()) if match else None
-                date_posted = (datetime.now() - timedelta(days=days_ago)).date()
-
-            description = job_info[19]
-
-            job_post = JobPost(
-                id=f"go-{job_info[28]}",
-                title=title,
-                company_name=company_name,
-                location=Location(
-                    city=city, state=state, country=country[0] if country else None
-                ),
-                job_url=job_url,
-                job_url_direct=job_url,
-                date_posted=date_posted,
-                is_remote="remote" in description.lower()
-                or "wfh" in description.lower(),
-                description=description,
-                emails=extract_emails_from_text(description),
-                job_type=extract_job_type(description),
-            )
-            jobs_on_page.append(job_post)
+            job_info = find_job_info(job_d)
+            job_post = self._parse_job(job_info)
+            if job_post:
+                jobs_on_page.append(job_post)
         return jobs_on_page, data_async_fc
 
-    @staticmethod
-    def _find_job_info(jobs_data: list | dict) -> list | None:
-        """Iterates through the JSON data to find the job listings"""
-        if isinstance(jobs_data, dict):
-            for key, value in jobs_data.items():
-                if key == "520084652" and isinstance(value, list):
-                    return value
-                else:
-                    result = GoogleJobsScraper._find_job_info(value)
-                    if result:
-                        return result
-        elif isinstance(jobs_data, list):
-            for item in jobs_data:
-                result = GoogleJobsScraper._find_job_info(item)
-                if result:
-                    return result
-        return None
+    def _parse_job(self, job_info: list):
+        job_url = job_info[3][0][0] if job_info[3] and job_info[3][0] else None
+        if job_url in self.seen_urls:
+            return
+        self.seen_urls.add(job_url)
+
+        title = job_info[0]
+        company_name = job_info[1]
+        location = city = job_info[2]
+        state = country = date_posted = None
+        if location and "," in location:
+            city, state, *country = [*map(lambda x: x.strip(), location.split(","))]
+
+        days_ago_str = job_info[12]
+        if type(days_ago_str) == str:
+            match = re.search(r"\d+", days_ago_str)
+            days_ago = int(match.group()) if match else None
+            date_posted = (datetime.now() - timedelta(days=days_ago)).date()
+
+        description = job_info[19]
+
+        job_post = JobPost(
+            id=f"go-{job_info[28]}",
+            title=title,
+            company_name=company_name,
+            location=Location(
+                city=city, state=state, country=country[0] if country else None
+            ),
+            job_url=job_url,
+            date_posted=date_posted,
+            is_remote="remote" in description.lower() or "wfh" in description.lower(),
+            description=description,
+            emails=extract_emails_from_text(description),
+            job_type=extract_job_type(description),
+        )
+        return job_post

jobspy/google/util.py

@@ -0,0 +1,41 @@
+import re
+
+from jobspy.util import create_logger
+
+log = create_logger("Google")
+
+
+def find_job_info(jobs_data: list | dict) -> list | None:
+    """Iterates through the JSON data to find the job listings"""
+    if isinstance(jobs_data, dict):
+        for key, value in jobs_data.items():
+            if key == "520084652" and isinstance(value, list):
+                return value
+            else:
+                result = find_job_info(value)
+                if result:
+                    return result
+    elif isinstance(jobs_data, list):
+        for item in jobs_data:
+            result = find_job_info(item)
+            if result:
+                return result
+    return None
+
+
+def find_job_info_initial_page(html_text: str):
+    pattern = f'520084652":(' + r"\[.*?\]\s*])\s*}\s*]\s*]\s*]\s*]\s*]"
+    results = []
+    matches = re.finditer(pattern, html_text)
+
+    import json
+
+    for match in matches:
+        try:
+            parsed_data = json.loads(match.group(1))
+            results.append(parsed_data)
+
+        except json.JSONDecodeError as e:
+            log.error(f"Failed to parse match: {str(e)}")
+            results.append({"raw_match": match.group(0), "error": str(e)})
+    return results

jobspy/indeed/__init__.py

@@ -1,39 +1,32 @@
-"""
-jobspy.scrapers.indeed
-~~~~~~~~~~~~~~~~~~~
-
-This module contains routines to scrape Indeed.
-"""
-
 from __future__ import annotations
 
 import math
-from typing import Tuple
 from datetime import datetime
+from typing import Tuple
 
-from .constants import job_search_query, api_headers
-from .. import Scraper, ScraperInput, Site
-from ..utils import (
-    extract_emails_from_text,
-    get_enum_from_job_type,
-    markdown_converter,
-    create_session,
-    create_logger,
-)
-from ...jobs import (
+from jobspy.indeed.constant import job_search_query, api_headers
+from jobspy.indeed.util import is_job_remote, get_compensation, get_job_type
+from jobspy.model import (
+    Scraper,
+    ScraperInput,
+    Site,
     JobPost,
-    Compensation,
-    CompensationInterval,
     Location,
     JobResponse,
     JobType,
     DescriptionFormat,
 )
+from jobspy.util import (
+    extract_emails_from_text,
+    markdown_converter,
+    create_session,
+    create_logger,
+)
 
-logger = create_logger("Indeed")
+log = create_logger("Indeed")
 
 
-class IndeedScraper(Scraper):
+class Indeed(Scraper):
     def __init__(
         self, proxies: list[str] | str | None = None, ca_cert: str | None = None
     ):
@@ -71,12 +64,12 @@ class IndeedScraper(Scraper):
         cursor = None
 
         while len(self.seen_urls) < scraper_input.results_wanted + scraper_input.offset:
-            logger.info(
+            log.info(
                 f"search page: {page} / {math.ceil(scraper_input.results_wanted / self.jobs_per_page)}"
             )
             jobs, cursor = self._scrape_page(cursor)
             if not jobs:
-                logger.info(f"found no jobs on page: {page}")
+                log.info(f"found no jobs on page: {page}")
                 break
             job_list += jobs
             page += 1
@@ -122,9 +115,10 @@ class IndeedScraper(Scraper):
             headers=api_headers_temp,
             json=payload,
             timeout=10,
+            verify=False,
         )
         if not response.ok:
-            logger.info(
+            log.info(
                 f"responded with status code: {response.status_code} (submit GitHub issue if this appears to be a bug)"
             )
             return jobs, new_cursor
@@ -212,7 +206,7 @@ class IndeedScraper(Scraper):
         if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
             description = markdown_converter(description)
 
-        job_type = self._get_job_type(job["attributes"])
+        job_type = get_job_type(job["attributes"])
         timestamp_seconds = job["datePublished"] / 1000
         date_posted = datetime.fromtimestamp(timestamp_seconds).strftime("%Y-%m-%d")
         employer = job["employer"].get("dossier") if job["employer"] else None
@@ -233,14 +227,14 @@ class IndeedScraper(Scraper):
                 country=job.get("location", {}).get("countryCode"),
             ),
             job_type=job_type,
-            compensation=self._get_compensation(job["compensation"]),
+            compensation=get_compensation(job["compensation"]),
             date_posted=date_posted,
             job_url=job_url,
             job_url_direct=(
                 job["recruit"].get("viewJobUrl") if job.get("recruit") else None
             ),
             emails=extract_emails_from_text(description) if description else None,
-            is_remote=self._is_job_remote(job, description),
+            is_remote=is_job_remote(job, description),
             company_addresses=(
                 employer_details["addresses"][0]
                 if employer_details.get("addresses")
@@ -264,86 +258,3 @@ class IndeedScraper(Scraper):
                 else None
             ),
         )
-
-    @staticmethod
-    def _get_job_type(attributes: list) -> list[JobType]:
-        """
-        Parses the attributes to get list of job types
-        :param attributes:
-        :return: list of JobType
-        """
-        job_types: list[JobType] = []
-        for attribute in attributes:
-            job_type_str = attribute["label"].replace("-", "").replace(" ", "").lower()
-            job_type = get_enum_from_job_type(job_type_str)
-            if job_type:
-                job_types.append(job_type)
-        return job_types
-
-    @staticmethod
-    def _get_compensation(compensation: dict) -> Compensation | None:
-        """
-        Parses the job to get compensation
-        :param job:
-        :return: compensation object
-        """
-        if not compensation["baseSalary"] and not compensation["estimated"]:
-            return None
-        comp = (
-            compensation["baseSalary"]
-            if compensation["baseSalary"]
-            else compensation["estimated"]["baseSalary"]
-        )
-        if not comp:
-            return None
-        interval = IndeedScraper._get_compensation_interval(comp["unitOfWork"])
-        if not interval:
-            return None
-        min_range = comp["range"].get("min")
-        max_range = comp["range"].get("max")
-        return Compensation(
-            interval=interval,
-            min_amount=int(min_range) if min_range is not None else None,
-            max_amount=int(max_range) if max_range is not None else None,
-            currency=(
-                compensation["estimated"]["currencyCode"]
-                if compensation["estimated"]
-                else compensation["currencyCode"]
-            ),
-        )
-
-    @staticmethod
-    def _is_job_remote(job: dict, description: str) -> bool:
-        """
-        Searches the description, location, and attributes to check if job is remote
-        """
-        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["attributes"]
-        )
-        is_remote_in_description = any(
-            keyword in description.lower() for keyword in remote_keywords
-        )
-        is_remote_in_location = any(
-            keyword in job["location"]["formatted"]["long"].lower()
-            for keyword in remote_keywords
-        )
-        return (
-            is_remote_in_attributes or is_remote_in_description or is_remote_in_location
-        )
-
-    @staticmethod
-    def _get_compensation_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}")

jobspy/indeed/util.py

@@ -0,0 +1,83 @@
+from jobspy.model import CompensationInterval, JobType, Compensation
+from jobspy.util import get_enum_from_job_type
+
+
+def get_job_type(attributes: list) -> list[JobType]:
+    """
+    Parses the attributes to get list of job types
+    :param attributes:
+    :return: list of JobType
+    """
+    job_types: list[JobType] = []
+    for attribute in attributes:
+        job_type_str = attribute["label"].replace("-", "").replace(" ", "").lower()
+        job_type = get_enum_from_job_type(job_type_str)
+        if job_type:
+            job_types.append(job_type)
+    return job_types
+
+
+def get_compensation(compensation: dict) -> Compensation | None:
+    """
+    Parses the job to get compensation
+    :param compensation:
+    :return: compensation object
+    """
+    if not compensation["baseSalary"] and not compensation["estimated"]:
+        return None
+    comp = (
+        compensation["baseSalary"]
+        if compensation["baseSalary"]
+        else compensation["estimated"]["baseSalary"]
+    )
+    if not comp:
+        return None
+    interval = get_compensation_interval(comp["unitOfWork"])
+    if not interval:
+        return None
+    min_range = comp["range"].get("min")
+    max_range = comp["range"].get("max")
+    return Compensation(
+        interval=interval,
+        min_amount=int(min_range) if min_range is not None else None,
+        max_amount=int(max_range) if max_range is not None else None,
+        currency=(
+            compensation["estimated"]["currencyCode"]
+            if compensation["estimated"]
+            else compensation["currencyCode"]
+        ),
+    )
+
+
+def is_job_remote(job: dict, description: str) -> bool:
+    """
+    Searches the description, location, and attributes to check if job is remote
+    """
+    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["attributes"]
+    )
+    is_remote_in_description = any(
+        keyword in description.lower() for keyword in remote_keywords
+    )
+    is_remote_in_location = any(
+        keyword in job["location"]["formatted"]["long"].lower()
+        for keyword in remote_keywords
+    )
+    return is_remote_in_attributes or is_remote_in_description or is_remote_in_location
+
+
+def get_compensation_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}")

jobspy/linkedin/__init__.py

@@ -1,47 +1,49 @@
-"""
-jobspy.scrapers.linkedin
-~~~~~~~~~~~~~~~~~~~
-
-This module contains routines to scrape LinkedIn.
-"""
-
 from __future__ import annotations
 
 import math
-import time
 import random
-import regex as re
-from typing import Optional
+import time
 from datetime import datetime
-
-from bs4.element import Tag
-from bs4 import BeautifulSoup
+from typing import Optional
 from urllib.parse import urlparse, urlunparse, unquote
 
-from .constants import headers
-from .. import Scraper, ScraperInput, Site
-from ..exceptions import LinkedInException
-from ..utils import create_session, remove_attributes, create_logger
-from ...jobs import (
+import regex as re
+from bs4 import BeautifulSoup
+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
+)
+from jobspy.model import (
     JobPost,
     Location,
     JobResponse,
-    JobType,
     Country,
     Compensation,
     DescriptionFormat,
+    Scraper,
+    ScraperInput,
+    Site,
 )
-from ..utils import (
+from jobspy.util import (
     extract_emails_from_text,
-    get_enum_from_job_type,
     currency_parser,
     markdown_converter,
+    create_session,
+    remove_attributes,
+    create_logger,
 )
 
-logger = create_logger("LinkedIn")
+log = create_logger("LinkedIn")
 
 
-class LinkedInScraper(Scraper):
+class LinkedIn(Scraper):
     base_url = "https://www.linkedin.com"
     delay = 3
     band_delay = 4
@@ -86,7 +88,7 @@ class LinkedInScraper(Scraper):
         )
         while continue_search():
             request_count += 1
-            logger.info(
+            log.info(
                 f"search page: {request_count} / {math.ceil(scraper_input.results_wanted / 10)}"
             )
             params = {
@@ -95,7 +97,7 @@ class LinkedInScraper(Scraper):
                 "distance": scraper_input.distance,
                 "f_WT": 2 if scraper_input.is_remote else None,
                 "f_JT": (
-                    self.job_type_code(scraper_input.job_type)
+                    job_type_code(scraper_input.job_type)
                     if scraper_input.job_type
                     else None
                 ),
@@ -126,13 +128,13 @@ class LinkedInScraper(Scraper):
                     else:
                         err = f"LinkedIn response status code {response.status_code}"
                         err += f" - {response.text}"
-                    logger.error(err)
+                    log.error(err)
                     return JobResponse(jobs=job_list)
             except Exception as e:
                 if "Proxy responded with" in str(e):
-                    logger.error(f"LinkedIn: Bad proxy")
+                    log.error(f"LinkedIn: Bad proxy")
                 else:
-                    logger.error(f"LinkedIn: {str(e)}")
+                    log.error(f"LinkedIn: {str(e)}")
                 return JobResponse(jobs=job_list)
 
             soup = BeautifulSoup(response.text, "html.parser")
@@ -172,7 +174,7 @@ class LinkedInScraper(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("-")]
@@ -216,6 +218,8 @@ class LinkedInScraper(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}",
@@ -223,6 +227,7 @@ class LinkedInScraper(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,
@@ -231,7 +236,7 @@ class LinkedInScraper(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"),
         )
@@ -282,9 +287,9 @@ class LinkedInScraper(Scraper):
         )
         return {
             "description": description,
-            "job_level": self._parse_job_level(soup),
-            "company_industry": self._parse_company_industry(soup),
-            "job_type": self._parse_job_type(soup),
+            "job_level": parse_job_level(soup),
+            "company_industry": parse_company_industry(soup),
+            "job_type": parse_job_type(soup),
             "job_url_direct": self._parse_job_url_direct(soup),
             "company_logo": company_logo,
             "job_function": job_function,
@@ -316,77 +321,6 @@ class LinkedInScraper(Scraper):
                 location = Location(city=city, state=state, country=country)
         return location
 
-    @staticmethod
-    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 _parse_job_level(soup_job_level: BeautifulSoup) -> str | None:
-        """
-        Gets the job level from job page
-        :param soup_job_level:
-        :return: str
-        """
-        h3_tag = soup_job_level.find(
-            "h3",
-            class_="description__job-criteria-subheader",
-            string=lambda text: "Seniority level" in text,
-        )
-        job_level = None
-        if h3_tag:
-            job_level_span = h3_tag.find_next_sibling(
-                "span",
-                class_="description__job-criteria-text description__job-criteria-text--criteria",
-            )
-            if job_level_span:
-                job_level = job_level_span.get_text(strip=True)
-
-        return job_level
-
-    @staticmethod
-    def _parse_company_industry(soup_industry: BeautifulSoup) -> str | None:
-        """
-        Gets the company industry from job page
-        :param soup_industry:
-        :return: str
-        """
-        h3_tag = soup_industry.find(
-            "h3",
-            class_="description__job-criteria-subheader",
-            string=lambda text: "Industries" in text,
-        )
-        industry = None
-        if h3_tag:
-            industry_span = h3_tag.find_next_sibling(
-                "span",
-                class_="description__job-criteria-text description__job-criteria-text--criteria",
-            )
-            if industry_span:
-                industry = industry_span.get_text(strip=True)
-
-        return industry
-
     def _parse_job_url_direct(self, soup: BeautifulSoup) -> str | None:
         """
         Gets the job url direct from job page
@@ -403,13 +337,3 @@ class LinkedInScraper(Scraper):
                 job_url_direct = unquote(job_url_direct_match.group())
 
         return job_url_direct
-
-    @staticmethod
-    def job_type_code(job_type_enum: JobType) -> str:
-        return {
-            JobType.FULL_TIME: "F",
-            JobType.PART_TIME: "P",
-            JobType.INTERNSHIP: "I",
-            JobType.CONTRACT: "C",
-            JobType.TEMPORARY: "T",
-        }.get(job_type_enum, "")

jobspy/linkedin/util.py

@@ -0,0 +1,96 @@
+from bs4 import BeautifulSoup
+
+from jobspy.model import JobType, Location
+from jobspy.util import get_enum_from_job_type
+
+
+def job_type_code(job_type_enum: JobType) -> str:
+    return {
+        JobType.FULL_TIME: "F",
+        JobType.PART_TIME: "P",
+        JobType.INTERNSHIP: "I",
+        JobType.CONTRACT: "C",
+        JobType.TEMPORARY: "T",
+    }.get(job_type_enum, "")
+
+
+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 []
+
+
+def parse_job_level(soup_job_level: BeautifulSoup) -> str | None:
+    """
+    Gets the job level from job page
+    :param soup_job_level:
+    :return: str
+    """
+    h3_tag = soup_job_level.find(
+        "h3",
+        class_="description__job-criteria-subheader",
+        string=lambda text: "Seniority level" in text,
+    )
+    job_level = None
+    if h3_tag:
+        job_level_span = h3_tag.find_next_sibling(
+            "span",
+            class_="description__job-criteria-text description__job-criteria-text--criteria",
+        )
+        if job_level_span:
+            job_level = job_level_span.get_text(strip=True)
+
+    return job_level
+
+
+def parse_company_industry(soup_industry: BeautifulSoup) -> str | None:
+    """
+    Gets the company industry from job page
+    :param soup_industry:
+    :return: str
+    """
+    h3_tag = soup_industry.find(
+        "h3",
+        class_="description__job-criteria-subheader",
+        string=lambda text: "Industries" in text,
+    )
+    industry = None
+    if h3_tag:
+        industry_span = h3_tag.find_next_sibling(
+            "span",
+            class_="description__job-criteria-text description__job-criteria-text--criteria",
+        )
+        if industry_span:
+            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

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from abc import ABC, abstractmethod
 from typing import Optional
 from datetime import date
 from enum import Enum
@@ -68,16 +69,20 @@ 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")
@@ -91,6 +96,8 @@ 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")
@@ -111,6 +118,8 @@ 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")
@@ -245,13 +254,13 @@ 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
@@ -259,9 +268,63 @@ 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] = []
+
+
+class Site(Enum):
+    LINKEDIN = "linkedin"
+    INDEED = "indeed"
+    ZIP_RECRUITER = "zip_recruiter"
+    GLASSDOOR = "glassdoor"
+    GOOGLE = "google"
+    BAYT = "bayt"
+    NAUKRI = "naukri"
+
+
+class SalarySource(Enum):
+    DIRECT_DATA = "direct_data"
+    DESCRIPTION = "description"
+
+
+class ScraperInput(BaseModel):
+    site_type: list[Site]
+    search_term: str | None = None
+    google_search_term: str | None = None
+
+    location: str | None = None
+    country: Country | None = Country.USA
+    distance: int | None = None
+    is_remote: 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(ABC):
+    def __init__(
+        self, site: Site, proxies: list[str] | None = None, ca_cert: str | None = None
+    ):
+        self.site = site
+        self.proxies = proxies
+        self.ca_cert = ca_cert
+
+    @abstractmethod
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse: ...

jobspy/naukri/__init__.py

@@ -0,0 +1,301 @@
+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

@@ -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 +1,34 @@
+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

@@ -1,16 +1,19 @@
 from __future__ import annotations
 
-import re
 import logging
+import re
 from itertools import cycle
 
+import numpy as np
 import requests
 import tls_client
-import numpy as np
+import urllib3
 from markdownify import markdownify as md
 from requests.adapters import HTTPAdapter, Retry
 
-from ..jobs import CompensationInterval, JobType
+from jobspy.model import CompensationInterval, JobType, Site
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
 
 def create_logger(name: str):
@@ -44,11 +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)
@@ -83,7 +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)
@@ -129,7 +132,7 @@ def create_session(
     return session
 
 
-def set_logger_level(verbose: int = 2):
+def set_logger_level(verbose: int):
     """
     Adjusts the logger's level. This function allows the logging level to be changed at runtime.
 
@@ -283,3 +286,69 @@ def extract_job_type(description: str):
             listing_types.append(key)
 
     return listing_types if listing_types else None
+
+
+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:
+        if value_str in job_type.value:
+            return job_type
+    raise Exception(f"Invalid job type: {value_str}")
+
+
+def convert_to_annual(job_data: dict):
+    if job_data["interval"] == "hourly":
+        job_data["min_amount"] *= 2080
+        job_data["max_amount"] *= 2080
+    if job_data["interval"] == "monthly":
+        job_data["min_amount"] *= 12
+        job_data["max_amount"] *= 12
+    if job_data["interval"] == "weekly":
+        job_data["min_amount"] *= 52
+        job_data["max_amount"] *= 52
+    if job_data["interval"] == "daily":
+        job_data["min_amount"] *= 260
+        job_data["max_amount"] *= 260
+    job_data["interval"] = "yearly"
+
+
+desired_order = [
+    "id",
+    "site",
+    "job_url",
+    "job_url_direct",
+    "title",
+    "company",
+    "location",
+    "date_posted",
+    "job_type",
+    "salary_source",
+    "interval",
+    "min_amount",
+    "max_amount",
+    "currency",
+    "is_remote",
+    "job_level",
+    "job_function",
+    "listing_type",
+    "emails",
+    "description",
+    "company_industry",
+    "company_url",
+    "company_logo",
+    "company_url_direct",
+    "company_addresses",
+    "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

@@ -1,46 +1,39 @@
-"""
-jobspy.scrapers.ziprecruiter
-~~~~~~~~~~~~~~~~~~~
-
-This module contains routines to scrape ZipRecruiter.
-"""
-
 from __future__ import annotations
 
 import json
 import math
 import re
 import time
-from datetime import datetime
-from typing import Optional, Tuple, Any
-
 from concurrent.futures import ThreadPoolExecutor
+from datetime import datetime
 
 from bs4 import BeautifulSoup
 
-from .constants import headers
-from .. import Scraper, ScraperInput, Site
-from ..utils import (
+from jobspy.ziprecruiter.constant import headers, get_cookie_data
+from jobspy.util import (
     extract_emails_from_text,
     create_session,
     markdown_converter,
     remove_attributes,
     create_logger,
 )
-from ...jobs import (
+from jobspy.model import (
     JobPost,
     Compensation,
     Location,
     JobResponse,
-    JobType,
     Country,
     DescriptionFormat,
+    Scraper,
+    ScraperInput,
+    Site,
 )
+from jobspy.ziprecruiter.util import get_job_type_enum, add_params
 
-logger = create_logger("ZipRecruiter")
+log = create_logger("ZipRecruiter")
 
 
-class ZipRecruiterScraper(Scraper):
+class ZipRecruiter(Scraper):
     base_url = "https://www.ziprecruiter.com"
     api_url = "https://api.ziprecruiter.com"
 
@@ -77,7 +70,7 @@ class ZipRecruiterScraper(Scraper):
                 break
             if page > 1:
                 time.sleep(self.delay)
-            logger.info(f"search page: {page} / {max_pages}")
+            log.info(f"search page: {page} / {max_pages}")
             jobs_on_page, continue_token = self._find_jobs_in_page(
                 scraper_input, continue_token
             )
@@ -91,7 +84,7 @@ class ZipRecruiterScraper(Scraper):
 
     def _find_jobs_in_page(
         self, scraper_input: ScraperInput, continue_token: str | None = None
-    ) -> Tuple[list[JobPost], Optional[str]]:
+    ) -> tuple[list[JobPost], str | None]:
         """
         Scrapes a page of ZipRecruiter for jobs with scraper_input criteria
         :param scraper_input:
@@ -99,7 +92,7 @@ class ZipRecruiterScraper(Scraper):
         :return: jobs found on page
         """
         jobs_list = []
-        params = self._add_params(scraper_input)
+        params = add_params(scraper_input)
         if continue_token:
             params["continue_from"] = continue_token
         try:
@@ -110,13 +103,13 @@ class ZipRecruiterScraper(Scraper):
                 else:
                     err = f"ZipRecruiter response status code {res.status_code}"
                     err += f" with response: {res.text}"  # ZipRecruiter likely not available in EU
-                logger.error(err)
+                log.error(err)
                 return jobs_list, ""
         except Exception as e:
             if "Proxy responded with" in str(e):
-                logger.error(f"Indeed: Bad proxy")
+                log.error(f"Indeed: Bad proxy")
             else:
-                logger.error(f"Indeed: {str(e)}")
+                log.error(f"Indeed: {str(e)}")
             return jobs_list, ""
 
         res_data = res.json()
@@ -152,7 +145,7 @@ class ZipRecruiterScraper(Scraper):
         location = Location(
             city=job.get("job_city"), state=job.get("job_state"), country=country_enum
         )
-        job_type = self._get_job_type_enum(
+        job_type = get_job_type_enum(
             job.get("employment_type", "").replace("_", "").lower()
         )
         date_posted = datetime.fromisoformat(job["posted_time"].rstrip("Z")).date()
@@ -201,13 +194,17 @@ class ZipRecruiterScraper(Scraper):
                 else ""
             )
             description_full = job_description_clean + company_description_clean
-            script_tag = soup.find("script", type="application/json")
-            if script_tag:
-                job_json = json.loads(script_tag.string)
-                job_url_val = job_json["model"].get("saveJobURL", "")
-                m = re.search(r"job_url=(.+)", job_url_val)
-                if m:
-                    job_url_direct = m.group(1)
+
+            try:
+                script_tag = soup.find("script", type="application/json")
+                if script_tag:
+                    job_json = json.loads(script_tag.string)
+                    job_url_val = job_json["model"].get("saveJobURL", "")
+                    m = re.search(r"job_url=(.+)", job_url_val)
+                    if m:
+                        job_url_direct = m.group(1)
+            except:
+                job_url_direct = None
 
             if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
                 description_full = markdown_converter(description_full)
@@ -215,33 +212,8 @@ class ZipRecruiterScraper(Scraper):
         return description_full, job_url_direct
 
     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"
+        """
+        Sends a session event to the API with device properties.
+        """
         url = f"{self.api_url}/jobs-app/event"
-        self.session.post(url, data=data)
-
-    @staticmethod
-    def _get_job_type_enum(job_type_str: str) -> list[JobType] | None:
-        for job_type in JobType:
-            if job_type_str in job_type.value:
-                return [job_type]
-        return None
-
-    @staticmethod
-    def _add_params(scraper_input) -> dict[str, str | Any]:
-        params = {
-            "search": scraper_input.search_term,
-            "location": scraper_input.location,
-        }
-        if scraper_input.hours_old:
-            params["days"] = max(scraper_input.hours_old // 24, 1)
-        job_type_map = {JobType.FULL_TIME: "full_time", JobType.PART_TIME: "part_time"}
-        if scraper_input.job_type:
-            job_type = scraper_input.job_type
-            params["employment_type"] = job_type_map.get(job_type, job_type.value[0])
-        if scraper_input.easy_apply:
-            params["zipapply"] = 1
-        if scraper_input.is_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}
+        self.session.post(url, data=get_cookie_data)

jobspy/ziprecruiter/constant.py

@@ -0,0 +1,29 @@
+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",
+}
+
+get_cookie_data = [
+    ("event_type", "session"),
+    ("logged_in", "false"),
+    ("number_of_retry", "1"),
+    ("property", "model:iPhone"),
+    ("property", "os:iOS"),
+    ("property", "locale:en_us"),
+    ("property", "app_build_number:4734"),
+    ("property", "app_version:91.0"),
+    ("property", "manufacturer:Apple"),
+    ("property", "timestamp:2025-01-12T12:04:42-06:00"),
+    ("property", "screen_height:852"),
+    ("property", "os_version:16.6.1"),
+    ("property", "source:install"),
+    ("property", "screen_width:393"),
+    ("property", "device_model:iPhone 14 Pro"),
+    ("property", "brand:Apple"),
+]

jobspy/ziprecruiter/util.py

@@ -0,0 +1,31 @@
+from jobspy.model import JobType
+
+
+def add_params(scraper_input) -> dict[str, str | int]:
+    params: dict[str, str | int] = {
+        "search": scraper_input.search_term,
+        "location": scraper_input.location,
+    }
+    if scraper_input.hours_old:
+        params["days"] = max(scraper_input.hours_old // 24, 1)
+
+    job_type_map = {JobType.FULL_TIME: "full_time", JobType.PART_TIME: "part_time"}
+    if scraper_input.job_type:
+        job_type = scraper_input.job_type
+        params["employment_type"] = job_type_map.get(job_type, job_type.value[0])
+
+    if scraper_input.easy_apply:
+        params["zipapply"] = 1
+    if scraper_input.is_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}
+
+
+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

poetry.toml

@@ -1,2 +0,0 @@
-[virtualenvs]
-in-project = true

pyproject.toml

@@ -1,15 +1,20 @@
+[build-system]
+requires = [ "poetry-core",]
+build-backend = "poetry.core.masonry.api"
+
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.73"
-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"
+version = "1.1.80"
+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']
+keywords = [ "jobs-scraper", "linkedin", "indeed", "glassdoor", "ziprecruiter", "bayt", "naukri"]
+[[tool.poetry.packages]]
+include = "jobspy"
 
-packages = [
-    { include = "jobspy", from = "src" }
-]
+[tool.black]
+line-length = 88
 
 [tool.poetry.dependencies]
 python = "^3.10"
@@ -22,16 +27,7 @@ tls-client = "^1.0.1"
 markdownify = "^0.13.1"
 regex = "^2024.4.28"
 
-
 [tool.poetry.group.dev.dependencies]
-pytest = "^7.4.1"
 jupyter = "^1.0.0"
 black = "*"
 pre-commit = "*"
-
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
-
-[tool.black]
-line-length = 88

src/jobspy/scrapers/__init__.py

@@ -1,56 +0,0 @@
-from __future__ import annotations
-
-from abc import ABC, abstractmethod
-
-from ..jobs import (
-    Enum,
-    BaseModel,
-    JobType,
-    JobResponse,
-    Country,
-    DescriptionFormat,
-)
-
-
-class Site(Enum):
-    LINKEDIN = "linkedin"
-    INDEED = "indeed"
-    ZIP_RECRUITER = "zip_recruiter"
-    GLASSDOOR = "glassdoor"
-    GOOGLE = "google"
-
-
-class SalarySource(Enum):
-    DIRECT_DATA = "direct_data"
-    DESCRIPTION = "description"
-
-
-class ScraperInput(BaseModel):
-    site_type: list[Site]
-    search_term: str | None = None
-
-    location: str | None = None
-    country: Country | None = Country.USA
-    distance: int | None = None
-    is_remote: 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(ABC):
-    def __init__(
-        self, site: Site, proxies: list[str] | None = None, ca_cert: str | None = None
-    ):
-        self.site = site
-        self.proxies = proxies
-        self.ca_cert = ca_cert
-
-    @abstractmethod
-    def scrape(self, scraper_input: ScraperInput) -> JobResponse: ...

src/jobspy/scrapers/ziprecruiter/constants.py

@@ -1,10 +0,0 @@
-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",
-}

tests/test_all.py

@@ -1,18 +0,0 @@
-from jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_all():
-    sites = [
-        "indeed",
-        "glassdoor",
-    ]  # ziprecruiter/linkedin needs good ip, and temp fix to pass test on ci
-    result = scrape_jobs(
-        site_name=sites,
-        search_term="engineer",
-        results_wanted=5,
-    )
-
-    assert (
-        isinstance(result, pd.DataFrame) and len(result) == len(sites) * 5
-    ), "Result should be a non-empty DataFrame"

tests/test_glassdoor.py

@@ -1,13 +0,0 @@
-from jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_glassdoor():
-    result = scrape_jobs(
-        site_name="glassdoor",
-        search_term="engineer",
-        results_wanted=5,
-    )
-    assert (
-        isinstance(result, pd.DataFrame) and len(result) == 5
-    ), "Result should be a non-empty DataFrame"

tests/test_google.py

@@ -1,12 +0,0 @@
-from jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_google():
-    result = scrape_jobs(
-        site_name="google", search_term="software engineer", results_wanted=5
-    )
-
-    assert (
-        isinstance(result, pd.DataFrame) and len(result) == 5
-    ), "Result should be a non-empty DataFrame"

tests/test_indeed.py

@@ -1,13 +0,0 @@
-from jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_indeed():
-    result = scrape_jobs(
-        site_name="indeed",
-        search_term="engineer",
-        results_wanted=5,
-    )
-    assert (
-        isinstance(result, pd.DataFrame) and len(result) == 5
-    ), "Result should be a non-empty DataFrame"

tests/test_linkedin.py

@@ -1,9 +0,0 @@
-from jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_linkedin():
-    result = scrape_jobs(site_name="linkedin", search_term="engineer", results_wanted=5)
-    assert (
-        isinstance(result, pd.DataFrame) and len(result) == 5
-    ), "Result should be a non-empty DataFrame"

tests/test_ziprecruiter.py

@@ -1,12 +0,0 @@
-from jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_ziprecruiter():
-    result = scrape_jobs(
-        site_name="zip_recruiter", search_term="software engineer", results_wanted=5
-    )
-
-    assert (
-        isinstance(result, pd.DataFrame) and len(result) == 5
-    ), "Result should be a non-empty DataFrame"