docs:readme

The previous regex did not capture all expected matches in the returned content

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

@@ -1,33 +1,50 @@
 name: Publish Python 🐍 distributions 📦 to PyPI
-on: push
+on:
+  pull_request:
+    types:
+      - closed
+
+permissions:
+  contents: write
 
 jobs:
   build-n-publish:
     name: Build and publish Python 🐍 distributions 📦 to PyPI
     runs-on: ubuntu-latest
 
+    if: github.event.pull_request.merged == true && github.event.pull_request.base.ref == 'main'
+
     steps:
       - uses: actions/checkout@v3
+
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
           python-version: "3.10"
 
+      - name: Install dependencies
+        run: pip install toml
+
+      - name: Increment version
+        run: python increment_version.py
+
+      - name: Commit version increment
+        run: |
+          git config --global user.name 'github-actions'
+          git config --global user.email 'github-actions@github.com'
+          git add pyproject.toml
+          git commit -m 'Increment version'
+
+      - name: Push changes
+        run: git push
+
       - name: Install poetry
-        run: >-
-          python3 -m
-          pip install
-          poetry
-          --user
+        run: pip install poetry --user
 
       - name: Build distribution 📦
-        run: >-
-          python3 -m
-          poetry
-          build
+        run: poetry build
 
       - name: Publish distribution 📦 to PyPI
-        if: startsWith(github.ref, 'refs/tags')
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          password: ${{ secrets.PYPI_API_TOKEN }}

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**, & **ZipRecruiter** simultaneously
-- Aggregates the job postings in a Pandas DataFrame
-- Proxies support
+- Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, **Google**, **ZipRecruiter**, & **Bayt** 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"],
+    site_name=["indeed", "linkedin", "zip_recruiter", "glassdoor", "google", "bayt"],
     search_term="software engineer",
-    location="Dallas, TX",
+    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 full description , direct job url , company industry and job level (seniority level) 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())
@@ -63,10 +58,13 @@ 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)
 │
@@ -79,14 +77,14 @@ Optional
 ├── proxies (list): 
 |    in format ['user:pass@host:port', 'localhost']
 |    each job board scraper will round robin through the proxies
-│
+|
 ├── is_remote (bool)
 │
 ├── results_wanted (int): 
 |    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.)
@@ -110,6 +108,12 @@ Optional
 |
 ├── country_indeed (str): 
 |    filters the country on Indeed & Glassdoor (see below for correct spelling)
+|
+├── enforce_annual_salary (bool): 
+|    converts wages to annual salary
+|
+├── ca_cert (str)
+|    path to CA Certificate file for proxies
 ```
 
 ```
@@ -125,49 +129,6 @@ Optional
 |    - easy_apply
 ```
 
-
-### JobPost Schema
-
-```plaintext
-JobPost
-├── title (str)
-├── company (str)
-├── company_url (str)
-├── job_url (str)
-├── location (object)
-│   ├── country (str)
-│   ├── city (str)
-│   ├── state (str)
-├── description (str)
-├── job_type (str): fulltime, parttime, internship, contract
-├── job_function (str)
-├── compensation (object)
-│   ├── interval (str): yearly, monthly, weekly, daily, hourly
-│   ├── min_amount (int)
-│   ├── max_amount (int)
-│   └── currency (enum)
-├── date_posted (date)
-├── emails (str)
-└── is_remote (bool)
-
-Linkedin specific
-└── job_level (str)
-
-Linkedin & Indeed specific
-└── company_industry (str)
-
-Indeed specific
-├── company_country (str)
-└── company_addresses (str)
-└── company_employees_label (str)
-└── company_revenue_label (str)
-└── company_description (str)
-└── ceo_name (str)
-└── ceo_photo_url (str)
-└── logo_photo_url (str)
-└── banner_photo_url (str)
-```
-
 ## Supported Countries for Job Searching
 
 ### **LinkedIn**
@@ -204,6 +165,11 @@ 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.  
@@ -213,10 +179,24 @@ You can specify the following countries when searching on Indeed (use the exact
 ## Frequently Asked Questions
 
 ---
+**Q: Why is Indeed giving unrelated roles?**  
+**A:** Indeed searches the description too.
 
-**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).
+- 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. 
 
 ---
 
@@ -227,3 +207,42 @@ persist, [submit an issue](https://github.com/Bunsly/JobSpy/issues).
 - Try using the proxies param to change your IP address.
 
 ---
+
+### 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
+```

increment_version.py

@@ -0,0 +1,21 @@
+import toml
+
+def increment_version(version):
+    major, minor, patch = map(int, version.split('.'))
+    patch += 1
+    return f"{major}.{minor}.{patch}"
+
+# Load pyproject.toml
+with open('pyproject.toml', 'r') as file:
+    pyproject = toml.load(file)
+
+# Increment the version
+current_version = pyproject['tool']['poetry']['version']
+new_version = increment_version(current_version)
+pyproject['tool']['poetry']['version'] = new_version
+
+# Save the updated pyproject.toml
+with open('pyproject.toml', 'w') as file:
+    toml.dump(pyproject, file)
+
+print(f"Version updated from {current_version} to {new_version}")

pyproject.toml

@@ -1,36 +1,35 @@
+[build-system]
+requires = [ "poetry-core",]
+build-backend = "poetry.core.masonry.api"
+
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.59"
+version = "1.1.76"
 description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
-authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
+authors = [ "Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>",]
 homepage = "https://github.com/Bunsly/JobSpy"
 readme = "README.md"
+keywords = [ "jobs-scraper", "linkedin", "indeed", "glassdoor", "ziprecruiter",]
+[[tool.poetry.packages]]
+include = "jobspy"
+from = "src"
 
-packages = [
-    { include = "jobspy", from = "src" }
-]
+[tool.black]
+line-length = 88
 
 [tool.poetry.dependencies]
 python = "^3.10"
 requests = "^2.31.0"
 beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"
-NUMPY = "1.24.2"
+NUMPY = "1.26.3"
 pydantic = "^2.3.0"
 tls-client = "^1.0.1"
-markdownify = "^0.11.6"
+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/__init__.py

@@ -5,23 +5,27 @@ from typing import Tuple
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from .jobs import JobType, Location
-from .scrapers.utils import logger, set_logger_level, extract_salary
+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 ScraperInput, Site, JobResponse, Country
+from .scrapers.bayt import BaytScraper
+from .scrapers import SalarySource, ScraperInput, Site, JobResponse, Country
 from .scrapers.exceptions import (
     LinkedInException,
     IndeedException,
     ZipRecruiterException,
     GlassdoorException,
+    GoogleJobsException,
 )
 
 
 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,
@@ -31,12 +35,14 @@ def scrape_jobs(
     country_indeed: str = "usa",
     hyperlinks: bool = False,
     proxies: list[str] | str | None = None,
+    ca_cert: str | None = None,
     description_format: str = "markdown",
     linkedin_fetch_description: bool | None = False,
     linkedin_company_ids: list[int] | None = None,
     offset: int | None = 0,
     hours_old: int = None,
-    verbose: int = 2,
+    enforce_annual_salary: bool = False,
+    verbose: int = 0,
     **kwargs,
 ) -> pd.DataFrame:
     """
@@ -48,6 +54,8 @@ def scrape_jobs(
         Site.INDEED: IndeedScraper,
         Site.ZIP_RECRUITER: ZipRecruiterScraper,
         Site.GLASSDOOR: GlassdoorScraper,
+        Site.GOOGLE: GoogleJobsScraper,
+        Site.BAYT: BaytScraper,
     }
     set_logger_level(verbose)
 
@@ -81,6 +89,7 @@ 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,
@@ -96,11 +105,11 @@ def scrape_jobs(
 
     def scrape_site(site: Site) -> Tuple[str, JobResponse]:
         scraper_class = SCRAPER_MAPPING[site]
-        scraper = scraper_class(proxies=proxies)
+        scraper = scraper_class(proxies=proxies, ca_cert=ca_cert)
         scraped_data: JobResponse = scraper.scrape(scraper_input)
         cap_name = site.value.capitalize()
         site_name = "ZipRecruiter" if cap_name == "Zip_recruiter" else cap_name
-        logger.info(f"{site_name} finished scraping")
+        create_logger(site_name).info(f"finished scraping")
         return site.value, scraped_data
 
     site_to_jobs_dict = {}
@@ -165,7 +174,8 @@ def scrape_jobs(
                 job_data["min_amount"] = compensation_obj.get("min_amount")
                 job_data["max_amount"] = compensation_obj.get("max_amount")
                 job_data["currency"] = compensation_obj.get("currency", "USD")
-                if (
+                job_data["salary_source"] = SalarySource.DIRECT_DATA.value
+                if enforce_annual_salary and (
                     job_data["interval"]
                     and job_data["interval"] != "yearly"
                     and job_data["min_amount"]
@@ -180,8 +190,17 @@ def scrape_jobs(
                         job_data["min_amount"],
                         job_data["max_amount"],
                         job_data["currency"],
-                    ) = extract_salary(job_data["description"])
+                    ) = extract_salary(
+                        job_data["description"],
+                        enforce_annual_salary=enforce_annual_salary,
+                    )
+                    job_data["salary_source"] = SalarySource.DESCRIPTION.value
 
+            job_data["salary_source"] = (
+                job_data["salary_source"]
+                if "min_amount" in job_data and job_data["min_amount"]
+                else None
+            )
             job_df = pd.DataFrame([job_data])
             jobs_dfs.append(job_df)
 
@@ -201,8 +220,9 @@ def scrape_jobs(
             "title",
             "company",
             "location",
-            "job_type",
             "date_posted",
+            "job_type",
+            "salary_source",
             "interval",
             "min_amount",
             "max_amount",
@@ -210,20 +230,17 @@ def scrape_jobs(
             "is_remote",
             "job_level",
             "job_function",
-            "company_industry",
             "listing_type",
             "emails",
             "description",
+            "company_industry",
             "company_url",
+            "company_logo",
             "company_url_direct",
             "company_addresses",
             "company_num_employees",
             "company_revenue",
             "company_description",
-            "logo_photo_url",
-            "banner_photo_url",
-            "ceo_name",
-            "ceo_photo_url",
         ]
 
         # Step 3: Ensure all desired columns are present, adding missing ones as empty
@@ -235,6 +252,8 @@ 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()

src/jobspy/jobs/__init__.py

@@ -92,7 +92,8 @@ class Country(Enum):
     JAPAN = ("japan", "jp")
     KUWAIT = ("kuwait", "kw")
     LUXEMBOURG = ("luxembourg", "lu")
-    MALAYSIA = ("malaysia", "malaysia")
+    MALAYSIA = ("malaysia", "malaysia:my", "com")
+    MALTA = ("malta", "malta:mt", "mt")
     MEXICO = ("mexico", "mx", "com.mx")
     MOROCCO = ("morocco", "ma")
     NETHERLANDS = ("netherlands", "nl", "nl")
@@ -117,7 +118,7 @@ class Country(Enum):
     SWITZERLAND = ("switzerland", "ch", "de:ch")
     TAIWAN = ("taiwan", "tw")
     THAILAND = ("thailand", "th")
-    TURKEY = ("turkey", "tr")
+    TURKEY = ("türkiye,turkey", "tr")
     UKRAINE = ("ukraine", "ua")
     UNITEDARABEMIRATES = ("united arab emirates", "ae")
     UK = ("uk,united kingdom", "uk:gb", "co.uk")
@@ -255,9 +256,7 @@ class JobPost(BaseModel):
     company_num_employees: str | None = None
     company_revenue: str | None = None
     company_description: str | None = None
-    ceo_name: str | None = None
-    ceo_photo_url: str | None = None
-    logo_photo_url: str | None = None
+    company_logo: str | None = None
     banner_photo_url: str | None = None
 
     # linkedin only atm

src/jobspy/scrapers/__init__.py

@@ -17,11 +17,19 @@ class Site(Enum):
     INDEED = "indeed"
     ZIP_RECRUITER = "zip_recruiter"
     GLASSDOOR = "glassdoor"
+    GOOGLE = "google"
+    BAYT = "bayt"
+
+
+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
@@ -39,9 +47,12 @@ class ScraperInput(BaseModel):
 
 
 class Scraper(ABC):
-    def __init__(self, site: Site, proxies: list[str] | None = None):
-        self.proxies = proxies
+    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/bayt/__init__.py

@@ -0,0 +1,145 @@
+"""
+jobspy.scrapers.bayt
+~~~~~~~~~~~~~~~~~~~
+
+This module contains routines to scrape Bayt.
+"""
+
+from __future__ import annotations
+
+import random
+import time
+
+from bs4 import BeautifulSoup
+
+from .. import Scraper, ScraperInput, Site
+from ..utils import create_logger, create_session
+from ...jobs import JobPost, JobResponse, Location, Country
+
+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()

src/jobspy/scrapers/exceptions.py

@@ -24,3 +24,13 @@ class ZipRecruiterException(Exception):
 class GlassdoorException(Exception):
     def __init__(self, message=None):
         super().__init__(message or "An error occurred with Glassdoor")
+
+
+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")

src/jobspy/scrapers/glassdoor/__init__.py

@@ -14,13 +14,13 @@ from typing import Optional, 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
+from ..utils import extract_emails_from_text, create_logger
 from ..exceptions import GlassdoorException
 from ..utils import (
     create_session,
     markdown_converter,
-    logger,
 )
 from ...jobs import (
     JobPost,
@@ -32,14 +32,18 @@ from ...jobs import (
     DescriptionFormat,
 )
 
+log = create_logger("Glassdoor")
+
 
 class GlassdoorScraper(Scraper):
-    def __init__(self, proxies: list[str] | str | None = None):
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+    ):
         """
         Initializes GlassdoorScraper with the Glassdoor job search url
         """
         site = Site(Site.GLASSDOOR)
-        super().__init__(site, proxies=proxies)
+        super().__init__(site, proxies=proxies, ca_cert=ca_cert)
 
         self.base_url = None
         self.country = None
@@ -59,15 +63,18 @@ class GlassdoorScraper(Scraper):
         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, is_tls=True, has_retry=True)
+        self.session = create_session(
+            proxies=self.proxies, ca_cert=self.ca_cert, has_retry=True
+        )
         token = self._get_csrf_token()
-        self.headers["gd-csrf-token"] = token if token else self.fallback_token
+        headers["gd-csrf-token"] = token if token else fallback_token
+        self.session.headers.update(headers)
 
         location_id, location_type = self._get_location(
             scraper_input.location, scraper_input.is_remote
         )
         if location_type is None:
-            logger.error("Glassdoor: location not parsed")
+            log.error("Glassdoor: location not parsed")
             return JobResponse(jobs=[])
         job_list: list[JobPost] = []
         cursor = None
@@ -76,7 +83,7 @@ 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"Glassdoor search page: {page}")
+            log.info(f"search page: {page} / {range_end - 1}")
             try:
                 jobs, cursor = self._fetch_jobs_page(
                     scraper_input, location_id, location_type, page, cursor
@@ -86,7 +93,7 @@ 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)
 
@@ -107,7 +114,6 @@ class GlassdoorScraper(Scraper):
             payload = self._add_payload(location_id, location_type, page_num, cursor)
             response = self.session.post(
                 f"{self.base_url}/graph",
-                headers=self.headers,
                 timeout_seconds=15,
                 data=payload,
             )
@@ -123,7 +129,7 @@ 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"]
@@ -148,9 +154,7 @@ class GlassdoorScraper(Scraper):
         """
         Fetches csrf token needed for API by visiting a generic page
         """
-        res = self.session.get(
-            f"{self.base_url}/Job/computer-science-jobs.htm", headers=self.headers
-        )
+        res = self.session.get(f"{self.base_url}/Job/computer-science-jobs.htm")
         pattern = r'"token":\s*"([^"]+)"'
         matches = re.findall(pattern, res.text)
         token = None
@@ -199,7 +203,7 @@ class GlassdoorScraper(Scraper):
             .lower()
         )
         return JobPost(
-            id=str(job_id),
+            id=f"gd-{job_id}",
             title=title,
             company_url=company_url if company_id else None,
             company_name=company_name,
@@ -210,7 +214,7 @@ class GlassdoorScraper(Scraper):
             is_remote=is_remote,
             description=description,
             emails=extract_emails_from_text(description) if description else None,
-            logo_photo_url=company_logo,
+            company_logo=company_logo,
             listing_type=listing_type,
         )
 
@@ -243,7 +247,7 @@ class GlassdoorScraper(Scraper):
                 """,
             }
         ]
-        res = requests.post(url, json=body, headers=self.headers)
+        res = requests.post(url, json=body, headers=headers)
         if res.status_code != 200:
             return None
         data = res.json()[0]
@@ -256,16 +260,16 @@ class GlassdoorScraper(Scraper):
         if not location or is_remote:
             return "11047", "STATE"  # remote options
         url = f"{self.base_url}/findPopularLocationAjax.htm?maxLocationsToReturn=10&term={location}"
-        res = self.session.get(url, headers=self.headers)
+        res = self.session.get(url)
         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()
 
@@ -310,7 +314,7 @@ class GlassdoorScraper(Scraper):
                 "fromage": fromage,
                 "sort": "date",
             },
-            "query": self.query_template,
+            "query": query_template,
         }
         if self.scraper_input.job_type:
             payload["variables"]["filterParams"].append(
@@ -358,188 +362,3 @@ class GlassdoorScraper(Scraper):
         for cursor_data in pagination_cursors:
             if cursor_data["pageNumber"] == page_num:
                 return cursor_data["cursor"]
-
-    fallback_token = "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok"
-    headers = {
-        "authority": "www.glassdoor.com",
-        "accept": "*/*",
-        "accept-language": "en-US,en;q=0.9",
-        "apollographql-client-name": "job-search-next",
-        "apollographql-client-version": "4.65.5",
-        "content-type": "application/json",
-        "origin": "https://www.glassdoor.com",
-        "referer": "https://www.glassdoor.com/",
-        "sec-ch-ua": '"Chromium";v="118", "Google Chrome";v="118", "Not=A?Brand";v="99"',
-        "sec-ch-ua-mobile": "?0",
-        "sec-ch-ua-platform": '"macOS"',
-        "sec-fetch-dest": "empty",
-        "sec-fetch-mode": "cors",
-        "sec-fetch-site": "same-origin",
-        "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
-    }
-    query_template = """
-            query JobSearchResultsQuery(
-                $excludeJobListingIds: [Long!], 
-                $keyword: String, 
-                $locationId: Int, 
-                $locationType: LocationTypeEnum, 
-                $numJobsToShow: Int!, 
-                $pageCursor: String, 
-                $pageNumber: Int, 
-                $filterParams: [FilterParams], 
-                $originalPageUrl: String, 
-                $seoFriendlyUrlInput: String, 
-                $parameterUrlInput: String, 
-                $seoUrl: Boolean
-            ) {
-                jobListings(
-                    contextHolder: {
-                        searchParams: {
-                            excludeJobListingIds: $excludeJobListingIds, 
-                            keyword: $keyword, 
-                            locationId: $locationId, 
-                            locationType: $locationType, 
-                            numPerPage: $numJobsToShow, 
-                            pageCursor: $pageCursor, 
-                            pageNumber: $pageNumber, 
-                            filterParams: $filterParams, 
-                            originalPageUrl: $originalPageUrl, 
-                            seoFriendlyUrlInput: $seoFriendlyUrlInput, 
-                            parameterUrlInput: $parameterUrlInput, 
-                            seoUrl: $seoUrl, 
-                            searchType: SR
-                        }
-                    }
-                ) {
-                    companyFilterOptions {
-                        id
-                        shortName
-                        __typename
-                    }
-                    filterOptions
-                    indeedCtk
-                    jobListings {
-                        ...JobView
-                        __typename
-                    }
-                    jobListingSeoLinks {
-                        linkItems {
-                            position
-                            url
-                            __typename
-                        }
-                        __typename
-                    }
-                    jobSearchTrackingKey
-                    jobsPageSeoData {
-                        pageMetaDescription
-                        pageTitle
-                        __typename
-                    }
-                    paginationCursors {
-                        cursor
-                        pageNumber
-                        __typename
-                    }
-                    indexablePageForSeo
-                    searchResultsMetadata {
-                        searchCriteria {
-                            implicitLocation {
-                                id
-                                localizedDisplayName
-                                type
-                                __typename
-                            }
-                            keyword
-                            location {
-                                id
-                                shortName
-                                localizedShortName
-                                localizedDisplayName
-                                type
-                                __typename
-                            }
-                            __typename
-                        }
-                        helpCenterDomain
-                        helpCenterLocale
-                        jobSerpJobOutlook {
-                            occupation
-                            paragraph
-                            __typename
-                        }
-                        showMachineReadableJobs
-                        __typename
-                    }
-                    totalJobsCount
-                    __typename
-                }
-            }
-
-            fragment JobView on JobListingSearchResult {
-                jobview {
-                    header {
-                        adOrderId
-                        advertiserType
-                        adOrderSponsorshipLevel
-                        ageInDays
-                        divisionEmployerName
-                        easyApply
-                        employer {
-                            id
-                            name
-                            shortName
-                            __typename
-                        }
-                        employerNameFromSearch
-                        goc
-                        gocConfidence
-                        gocId
-                        jobCountryId
-                        jobLink
-                        jobResultTrackingKey
-                        jobTitleText
-                        locationName
-                        locationType
-                        locId
-                        needsCommission
-                        payCurrency
-                        payPeriod
-                        payPeriodAdjustedPay {
-                            p10
-                            p50
-                            p90
-                            __typename
-                        }
-                        rating
-                        salarySource
-                        savedJobId
-                        sponsored
-                        __typename
-                    }
-                    job {
-                        description
-                        importConfigId
-                        jobTitleId
-                        jobTitleText
-                        listingId
-                        __typename
-                    }
-                    jobListingAdminDetails {
-                        cpcVal
-                        importConfigId
-                        jobListingId
-                        jobSourceId
-                        userEligibleForAdminJobDetails
-                        __typename
-                    }
-                    overview {
-                        shortName
-                        squareLogoUrl
-                        __typename
-                    }
-                    __typename
-                }
-                __typename
-            }
-    """

src/jobspy/scrapers/glassdoor/constants.py

@@ -0,0 +1,184 @@
+headers = {
+    "authority": "www.glassdoor.com",
+    "accept": "*/*",
+    "accept-language": "en-US,en;q=0.9",
+    "apollographql-client-name": "job-search-next",
+    "apollographql-client-version": "4.65.5",
+    "content-type": "application/json",
+    "origin": "https://www.glassdoor.com",
+    "referer": "https://www.glassdoor.com/",
+    "sec-ch-ua": '"Chromium";v="118", "Google Chrome";v="118", "Not=A?Brand";v="99"',
+    "sec-ch-ua-mobile": "?0",
+    "sec-ch-ua-platform": '"macOS"',
+    "sec-fetch-dest": "empty",
+    "sec-fetch-mode": "cors",
+    "sec-fetch-site": "same-origin",
+    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
+}
+query_template = """
+        query JobSearchResultsQuery(
+            $excludeJobListingIds: [Long!], 
+            $keyword: String, 
+            $locationId: Int, 
+            $locationType: LocationTypeEnum, 
+            $numJobsToShow: Int!, 
+            $pageCursor: String, 
+            $pageNumber: Int, 
+            $filterParams: [FilterParams], 
+            $originalPageUrl: String, 
+            $seoFriendlyUrlInput: String, 
+            $parameterUrlInput: String, 
+            $seoUrl: Boolean
+        ) {
+            jobListings(
+                contextHolder: {
+                    searchParams: {
+                        excludeJobListingIds: $excludeJobListingIds, 
+                        keyword: $keyword, 
+                        locationId: $locationId, 
+                        locationType: $locationType, 
+                        numPerPage: $numJobsToShow, 
+                        pageCursor: $pageCursor, 
+                        pageNumber: $pageNumber, 
+                        filterParams: $filterParams, 
+                        originalPageUrl: $originalPageUrl, 
+                        seoFriendlyUrlInput: $seoFriendlyUrlInput, 
+                        parameterUrlInput: $parameterUrlInput, 
+                        seoUrl: $seoUrl, 
+                        searchType: SR
+                    }
+                }
+            ) {
+                companyFilterOptions {
+                    id
+                    shortName
+                    __typename
+                }
+                filterOptions
+                indeedCtk
+                jobListings {
+                    ...JobView
+                    __typename
+                }
+                jobListingSeoLinks {
+                    linkItems {
+                        position
+                        url
+                        __typename
+                    }
+                    __typename
+                }
+                jobSearchTrackingKey
+                jobsPageSeoData {
+                    pageMetaDescription
+                    pageTitle
+                    __typename
+                }
+                paginationCursors {
+                    cursor
+                    pageNumber
+                    __typename
+                }
+                indexablePageForSeo
+                searchResultsMetadata {
+                    searchCriteria {
+                        implicitLocation {
+                            id
+                            localizedDisplayName
+                            type
+                            __typename
+                        }
+                        keyword
+                        location {
+                            id
+                            shortName
+                            localizedShortName
+                            localizedDisplayName
+                            type
+                            __typename
+                        }
+                        __typename
+                    }
+                    helpCenterDomain
+                    helpCenterLocale
+                    jobSerpJobOutlook {
+                        occupation
+                        paragraph
+                        __typename
+                    }
+                    showMachineReadableJobs
+                    __typename
+                }
+                totalJobsCount
+                __typename
+            }
+        }
+
+        fragment JobView on JobListingSearchResult {
+            jobview {
+                header {
+                    adOrderId
+                    advertiserType
+                    adOrderSponsorshipLevel
+                    ageInDays
+                    divisionEmployerName
+                    easyApply
+                    employer {
+                        id
+                        name
+                        shortName
+                        __typename
+                    }
+                    employerNameFromSearch
+                    goc
+                    gocConfidence
+                    gocId
+                    jobCountryId
+                    jobLink
+                    jobResultTrackingKey
+                    jobTitleText
+                    locationName
+                    locationType
+                    locId
+                    needsCommission
+                    payCurrency
+                    payPeriod
+                    payPeriodAdjustedPay {
+                        p10
+                        p50
+                        p90
+                        __typename
+                    }
+                    rating
+                    salarySource
+                    savedJobId
+                    sponsored
+                    __typename
+                }
+                job {
+                    description
+                    importConfigId
+                    jobTitleId
+                    jobTitleText
+                    listingId
+                    __typename
+                }
+                jobListingAdminDetails {
+                    cpcVal
+                    importConfigId
+                    jobListingId
+                    jobSourceId
+                    userEligibleForAdminJobDetails
+                    __typename
+                }
+                overview {
+                    shortName
+                    squareLogoUrl
+                    __typename
+                }
+                __typename
+            }
+            __typename
+        }
+"""
+fallback_token = "Ft6oHEWlRZrxDww95Cpazw:0pGUrkb2y3TyOpAIqF2vbPmUXoXVkD3oEGDVkvfeCerceQ5-n8mBg3BovySUIjmCPHCaW0H2nQVdqzbtsYqf4Q:wcqRqeegRUa9MVLJGyujVXB7vWFPjdaS1CtrrzJq-ok"

src/jobspy/scrapers/google/__init__.py

@@ -0,0 +1,247 @@
+"""
+jobspy.scrapers.google
+~~~~~~~~~~~~~~~~~~~
+
+This module contains routines to scrape Google.
+"""
+
+from __future__ import annotations
+
+import math
+import re
+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 (
+    JobPost,
+    JobResponse,
+    Location,
+    JobType,
+)
+
+log = create_logger("Google")
+
+
+class GoogleJobsScraper(Scraper):
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+    ):
+        """
+        Initializes Google Scraper with the Goodle jobs search url
+        """
+        site = Site(Site.GOOGLE)
+        super().__init__(site, proxies=proxies, ca_cert=ca_cert)
+
+        self.country = None
+        self.session = None
+        self.scraper_input = None
+        self.jobs_per_page = 10
+        self.seen_urls = set()
+        self.url = "https://www.google.com/search"
+        self.jobs_url = "https://www.google.com/async/callback:550"
+
+    def scrape(self, scraper_input: ScraperInput) -> JobResponse:
+        """
+        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.session = create_session(
+            proxies=self.proxies, ca_cert=self.ca_cert, is_tls=False, has_retry=True
+        )
+        forward_cursor, job_list = self._get_initial_cursor_and_jobs()
+        if forward_cursor is None:
+            log.warning(
+                "initial cursor not found, try changing your query or there was at most 10 results"
+            )
+            return JobResponse(jobs=job_list)
+
+        page = 1
+
+        while (
+            len(self.seen_urls) < scraper_input.results_wanted + scraper_input.offset
+            and forward_cursor
+        ):
+            log.info(
+                f"search page: {page} / {math.ceil(scraper_input.results_wanted / self.jobs_per_page)}"
+            )
+            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:
+                log.info(f"found no jobs on page: {page}")
+                break
+            job_list += jobs
+            page += 1
+        return JobResponse(
+            jobs=job_list[
+                scraper_input.offset : scraper_input.offset
+                + scraper_input.results_wanted
+            ]
+        )
+
+    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):
+            if hours_old <= 24:
+                return "since yesterday"
+            elif hours_old <= 72:
+                return "in the last 3 days"
+            elif hours_old <= 168:
+                return "in the last week"
+            else:
+                return "in the last month"
+
+        job_type_mapping = {
+            JobType.FULL_TIME: "Full time",
+            JobType.PART_TIME: "Part time",
+            JobType.INTERNSHIP: "Internship",
+            JobType.CONTRACT: "Contract",
+        }
+
+        if self.scraper_input.job_type in job_type_mapping:
+            query += f" {job_type_mapping[self.scraper_input.job_type]}"
+
+        if self.scraper_input.location:
+            query += f" near {self.scraper_input.location}"
+
+        if self.scraper_input.hours_old:
+            time_filter = get_time_range(self.scraper_input.hours_old)
+            query += f" {time_filter}"
+
+        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
+        jobs_raw = self._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]}
+        response = self.session.get(self.jobs_url, headers=headers_jobs, params=params)
+        return self._parse_jobs(response.text)
+
+    def _parse_jobs(self, job_data: str) -> Tuple[list[JobPost], str]:
+        """
+        Parses jobs on a page with next page cursor
+        """
+        start_idx = job_data.find("[[[")
+        end_idx = job_data.rindex("]]]") + 3
+        s = job_data[start_idx:end_idx]
+        parsed = json.loads(s)[0]
+
+        pattern_fc = r'data-async-fc="([^"]+)"'
+        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_post = self._parse_job(job_info)
+            if job_post:
+                jobs_on_page.append(job_post)
+        return jobs_on_page, data_async_fc
+
+    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
+
+    @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
+
+    @staticmethod
+    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

src/jobspy/scrapers/google/constants.py

@@ -0,0 +1,52 @@
+headers_initial = {
+    "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",
+    "priority": "u=0, i",
+    "referer": "https://www.google.com/",
+    "sec-ch-prefers-color-scheme": "dark",
+    "sec-ch-ua": '"Chromium";v="130", "Google Chrome";v="130", "Not?A_Brand";v="99"',
+    "sec-ch-ua-arch": '"arm"',
+    "sec-ch-ua-bitness": '"64"',
+    "sec-ch-ua-form-factors": '"Desktop"',
+    "sec-ch-ua-full-version": '"130.0.6723.58"',
+    "sec-ch-ua-full-version-list": '"Chromium";v="130.0.6723.58", "Google Chrome";v="130.0.6723.58", "Not?A_Brand";v="99.0.0.0"',
+    "sec-ch-ua-mobile": "?0",
+    "sec-ch-ua-model": '""',
+    "sec-ch-ua-platform": '"macOS"',
+    "sec-ch-ua-platform-version": '"15.0.1"',
+    "sec-ch-ua-wow64": "?0",
+    "sec-fetch-dest": "document",
+    "sec-fetch-mode": "navigate",
+    "sec-fetch-site": "same-origin",
+    "sec-fetch-user": "?1",
+    "upgrade-insecure-requests": "1",
+    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
+    "x-browser-channel": "stable",
+    "x-browser-copyright": "Copyright 2024 Google LLC. All rights reserved.",
+    "x-browser-year": "2024",
+}
+
+headers_jobs = {
+    "accept": "*/*",
+    "accept-language": "en-US,en;q=0.9",
+    "priority": "u=1, i",
+    "referer": "https://www.google.com/",
+    "sec-ch-prefers-color-scheme": "dark",
+    "sec-ch-ua": '"Chromium";v="130", "Google Chrome";v="130", "Not?A_Brand";v="99"',
+    "sec-ch-ua-arch": '"arm"',
+    "sec-ch-ua-bitness": '"64"',
+    "sec-ch-ua-form-factors": '"Desktop"',
+    "sec-ch-ua-full-version": '"130.0.6723.58"',
+    "sec-ch-ua-full-version-list": '"Chromium";v="130.0.6723.58", "Google Chrome";v="130.0.6723.58", "Not?A_Brand";v="99.0.0.0"',
+    "sec-ch-ua-mobile": "?0",
+    "sec-ch-ua-model": '""',
+    "sec-ch-ua-platform": '"macOS"',
+    "sec-ch-ua-platform-version": '"15.0.1"',
+    "sec-ch-ua-wow64": "?0",
+    "sec-fetch-dest": "empty",
+    "sec-fetch-mode": "cors",
+    "sec-fetch-site": "same-origin",
+    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
+}
+
+async_param = "_basejs:/xjs/_/js/k=xjs.s.en_US.JwveA-JiKmg.2018.O/am=AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIAAAAAAAAACAAAoICAAAAAAAKMAfAAAAIAQAAAAAAAAAAAAACCAAAEJDAAACAAAAAGABAIAAARBAAABAAAAAgAgQAABAASKAfv8JAAABAAAAAAwAQAQACQAAAAAAcAEAQABoCAAAABAAAIABAACAAAAEAAAAFAAAAAAAAAAAAAAAAAAAAAAAAACAQADoBwAAAAAAAAAAAAAQBAAAAATQAAoACOAHAAAAAAAAAQAAAIIAAAA_ZAACAAAAAAAAcB8APB4wHFJ4AAAAAAAAAAAAAAAACECCYA5If0EACAAAAAAAAAAAAAAAAAAAUgRNXG4AMAE/dg=0/br=1/rs=ACT90oGxMeaFMCopIHq5tuQM-6_3M_VMjQ,_basecss:/xjs/_/ss/k=xjs.s.IwsGu62EDtU.L.B1.O/am=QOoQIAQAAAQAREADEBAAAAAAAAAAAAAAAAAAAAAgAQAAIAAAgAQAAAIAIAIAoEwCAADIC8AfsgEAawwAPkAAjgoAGAAAAAAAAEADAAAAAAIgAECHAAAAAAAAAAABAQAggAARQAAAQCEAAAAAIAAAABgAAAAAIAQIACCAAfB-AAFIQABoCEA_CgEAAIABAACEgHAEwwAEFQAM4CgAAAAAAAAAAAAACABCAAAAQEAAABAgAMCPAAA4AoE2BAEAggSAAIoAQAAAAAgAAAAACCAQAAAxEwA_ZAACAAAAAAAAAAkAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAQAEAAAAAAAAAAAAAAAAAAAAAQA/br=1/rs=ACT90oGZc36t3uUQkj0srnIvvbHjO2hgyg,_basecomb:/xjs/_/js/k=xjs.s.en_US.JwveA-JiKmg.2018.O/ck=xjs.s.IwsGu62EDtU.L.B1.O/am=QOoQIAQAAAQAREADEBAAAAAAAAAAAAAAAAAAAAAgAQAAIAAAgAQAAAKAIAoIqEwCAADIK8AfsgEAawwAPkAAjgoAGAAACCAAAEJDAAACAAIgAGCHAIAAARBAAABBAQAggAgRQABAQSOAfv8JIAABABgAAAwAYAQICSCAAfB-cAFIQABoCEA_ChEAAIABAACEgHAEwwAEFQAM4CgAAAAAAAAAAAAACABCAACAQEDoBxAgAMCPAAA4AoE2BAEAggTQAIoASOAHAAgAAAAACSAQAIIxEwA_ZAACAAAAAAAAcB8APB4wHFJ4AAAAAAAAAAAAAAAACECCYA5If0EACAAAAAAAAAAAAAAAAAAAUgRNXG4AMAE/d=1/ed=1/dg=0/br=1/ujg=1/rs=ACT90oFNLTjPzD_OAqhhtXwe2pg1T3WpBg,_fmt:prog,_id:fc_5FwaZ86OKsfdwN4P4La3yA4_2"

src/jobspy/scrapers/indeed/__init__.py

@@ -10,15 +10,15 @@ from __future__ import annotations
 import math
 from typing import Tuple
 from datetime import datetime
-from concurrent.futures import ThreadPoolExecutor, Future
 
+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,
-    logger,
     create_session,
+    create_logger,
 )
 from ...jobs import (
     JobPost,
@@ -30,15 +30,21 @@ from ...jobs import (
     DescriptionFormat,
 )
 
+log = create_logger("Indeed")
+
 
 class IndeedScraper(Scraper):
-    def __init__(self, proxies: list[str] | str | None = None):
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+    ):
         """
         Initializes IndeedScraper with the Indeed API url
         """
         super().__init__(Site.INDEED, proxies=proxies)
 
-        self.session = create_session(proxies=self.proxies, is_tls=False)
+        self.session = create_session(
+            proxies=self.proxies, ca_cert=ca_cert, is_tls=False
+        )
         self.scraper_input = None
         self.jobs_per_page = 100
         self.num_workers = 10
@@ -57,29 +63,29 @@ class IndeedScraper(Scraper):
         self.scraper_input = scraper_input
         domain, self.api_country_code = self.scraper_input.country.indeed_domain_value
         self.base_url = f"https://{domain}.indeed.com"
-        self.headers = self.api_headers.copy()
+        self.headers = api_headers.copy()
         self.headers["indeed-co"] = self.scraper_input.country.indeed_domain_value
         job_list = []
         page = 1
 
         cursor = None
-        offset_pages = math.ceil(self.scraper_input.offset / 100)
-        for _ in range(offset_pages):
-            logger.info(f"Indeed skipping search page: {page}")
-            __, cursor = self._scrape_page(cursor)
-            if not __:
-                logger.info(f"Indeed found no jobs on page: {page}")
-                break
 
-        while len(self.seen_urls) < scraper_input.results_wanted:
-            logger.info(f"Indeed search page: {page}")
+        while len(self.seen_urls) < scraper_input.results_wanted + scraper_input.offset:
+            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"Indeed found no jobs on page: {page}")
+                log.info(f"found no jobs on page: {page}")
                 break
             job_list += jobs
             page += 1
-        return JobResponse(jobs=job_list[: scraper_input.results_wanted])
+        return JobResponse(
+            jobs=job_list[
+                scraper_input.offset : scraper_input.offset
+                + scraper_input.results_wanted
+            ]
+        )
 
     def _scrape_page(self, cursor: str | None) -> Tuple[list[JobPost], str | None]:
         """
@@ -95,7 +101,7 @@ class IndeedScraper(Scraper):
             if self.scraper_input.search_term
             else ""
         )
-        query = self.job_search_query.format(
+        query = job_search_query.format(
             what=(f'what: "{search_term}"' if search_term else ""),
             location=(
                 f'location: {{where: "{self.scraper_input.location}", radius: {self.scraper_input.distance}, radiusUnit: MILES}}'
@@ -109,28 +115,30 @@ class IndeedScraper(Scraper):
         payload = {
             "query": query,
         }
-        api_headers = self.api_headers.copy()
-        api_headers["indeed-co"] = self.api_country_code
+        api_headers_temp = api_headers.copy()
+        api_headers_temp["indeed-co"] = self.api_country_code
         response = self.session.post(
             self.api_url,
-            headers=api_headers,
+            headers=api_headers_temp,
             json=payload,
             timeout=10,
+            verify=False,
         )
-        if response.status_code != 200:
-            logger.info(
-                f"Indeed responded with status code: {response.status_code} (submit GitHub issue if this appears to be a bug)"
+        if not response.ok:
+            log.info(
+                f"responded with status code: {response.status_code} (submit GitHub issue if this appears to be a bug)"
             )
             return jobs, new_cursor
         data = response.json()
         jobs = data["data"]["jobSearch"]["results"]
         new_cursor = data["data"]["jobSearch"]["pageInfo"]["nextCursor"]
 
-        with ThreadPoolExecutor(max_workers=self.num_workers) as executor:
-            job_results: list[Future] = [
-                executor.submit(self._process_job, job["job"]) for job in jobs
-            ]
-        job_list = [result.result() for result in job_results if result.result()]
+        job_list = []
+        for job in jobs:
+            processed_job = self._process_job(job["job"])
+            if processed_job:
+                job_list.append(processed_job)
+
         return job_list, new_cursor
 
     def _build_filters(self):
@@ -212,7 +220,7 @@ class IndeedScraper(Scraper):
         employer_details = employer.get("employerDetails", {}) if employer else {}
         rel_url = job["employer"]["relativeCompanyPageUrl"] if job["employer"] else None
         return JobPost(
-            id=str(job["key"]),
+            id=f'in-{job["key"]}',
             title=job["title"],
             description=description,
             company_name=job["employer"].get("name") if job.get("employer") else None,
@@ -251,18 +259,11 @@ class IndeedScraper(Scraper):
             company_num_employees=employer_details.get("employeesLocalizedLabel"),
             company_revenue=employer_details.get("revenueLocalizedLabel"),
             company_description=employer_details.get("briefDescription"),
-            ceo_name=employer_details.get("ceoName"),
-            ceo_photo_url=employer_details.get("ceoPhotoUrl"),
-            logo_photo_url=(
+            company_logo=(
                 employer["images"].get("squareLogoUrl")
                 if employer and employer.get("images")
                 else None
             ),
-            banner_photo_url=(
-                employer["images"].get("headerImageUrl")
-                if employer and employer.get("images")
-                else None
-            ),
         )
 
     @staticmethod
@@ -347,112 +348,3 @@ class IndeedScraper(Scraper):
             return CompensationInterval[mapped_interval]
         else:
             raise ValueError(f"Unsupported interval: {interval}")
-
-    api_headers = {
-        "Host": "apis.indeed.com",
-        "content-type": "application/json",
-        "indeed-api-key": "161092c2017b5bbab13edb12461a62d5a833871e7cad6d9d475304573de67ac8",
-        "accept": "application/json",
-        "indeed-locale": "en-US",
-        "accept-language": "en-US,en;q=0.9",
-        "user-agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 Indeed App 193.1",
-        "indeed-app-info": "appv=193.1; appid=com.indeed.jobsearch; osv=16.6.1; os=ios; dtype=phone",
-    }
-    job_search_query = """
-        query GetJobData {{
-          jobSearch(
-            {what}
-            {location}
-            limit: 100
-            sort: DATE
-            {cursor}
-            {filters}
-          ) {{
-            pageInfo {{
-              nextCursor
-            }}
-            results {{
-              trackingKey
-              job {{
-                source {{
-                  name
-                }}
-                key
-                title
-                datePublished
-                dateOnIndeed
-                description {{
-                  html
-                }}
-                location {{
-                  countryName
-                  countryCode
-                  admin1Code
-                  city
-                  postalCode
-                  streetAddress
-                  formatted {{
-                    short
-                    long
-                  }}
-                }}
-                compensation {{
-                  estimated {{
-                    currencyCode
-                    baseSalary {{
-                      unitOfWork
-                      range {{
-                        ... on Range {{
-                          min
-                          max
-                        }}
-                      }}
-                    }}
-                  }}
-                  baseSalary {{
-                    unitOfWork
-                    range {{
-                      ... on Range {{
-                        min
-                        max
-                      }}
-                    }}
-                  }}
-                  currencyCode
-                }}
-                attributes {{
-                  key
-                  label
-                }}
-                employer {{
-                  relativeCompanyPageUrl
-                  name
-                  dossier {{
-                      employerDetails {{
-                        addresses
-                        industry
-                        employeesLocalizedLabel
-                        revenueLocalizedLabel
-                        briefDescription
-                        ceoName
-                        ceoPhotoUrl
-                      }}
-                      images {{
-                            headerImageUrl
-                            squareLogoUrl
-                      }}
-                      links {{
-                        corporateWebsite
-                    }}
-                  }}
-                }}
-                recruit {{
-                  viewJobUrl
-                  detailedSalary
-                  workSchedule
-                }}
-              }}
-            }}
-          }}
-        }}
-        """

src/jobspy/scrapers/indeed/constants.py

@@ -0,0 +1,109 @@
+job_search_query = """
+    query GetJobData {{
+        jobSearch(
+        {what}
+        {location}
+        limit: 100
+        {cursor}
+        sort: RELEVANCE
+        {filters}
+        ) {{
+        pageInfo {{
+            nextCursor
+        }}
+        results {{
+            trackingKey
+            job {{
+            source {{
+                name
+            }}
+            key
+            title
+            datePublished
+            dateOnIndeed
+            description {{
+                html
+            }}
+            location {{
+                countryName
+                countryCode
+                admin1Code
+                city
+                postalCode
+                streetAddress
+                formatted {{
+                short
+                long
+                }}
+            }}
+            compensation {{
+                estimated {{
+                currencyCode
+                baseSalary {{
+                    unitOfWork
+                    range {{
+                    ... on Range {{
+                        min
+                        max
+                    }}
+                    }}
+                }}
+                }}
+                baseSalary {{
+                unitOfWork
+                range {{
+                    ... on Range {{
+                    min
+                    max
+                    }}
+                }}
+                }}
+                currencyCode
+            }}
+            attributes {{
+                key
+                label
+            }}
+            employer {{
+                relativeCompanyPageUrl
+                name
+                dossier {{
+                    employerDetails {{
+                    addresses
+                    industry
+                    employeesLocalizedLabel
+                    revenueLocalizedLabel
+                    briefDescription
+                    ceoName
+                    ceoPhotoUrl
+                    }}
+                    images {{
+                        headerImageUrl
+                        squareLogoUrl
+                    }}
+                    links {{
+                    corporateWebsite
+                }}
+                }}
+            }}
+            recruit {{
+                viewJobUrl
+                detailedSalary
+                workSchedule
+            }}
+            }}
+        }}
+        }}
+    }}
+    """
+
+api_headers = {
+    "Host": "apis.indeed.com",
+    "content-type": "application/json",
+    "indeed-api-key": "161092c2017b5bbab13edb12461a62d5a833871e7cad6d9d475304573de67ac8",
+    "accept": "application/json",
+    "indeed-locale": "en-US",
+    "accept-language": "en-US,en;q=0.9",
+    "user-agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148 Indeed App 193.1",
+    "indeed-app-info": "appv=193.1; appid=com.indeed.jobsearch; osv=16.6.1; os=ios; dtype=phone",
+}

src/jobspy/scrapers/linkedin/__init__.py

@@ -7,6 +7,7 @@ This module contains routines to scrape LinkedIn.
 
 from __future__ import annotations
 
+import math
 import time
 import random
 import regex as re
@@ -17,9 +18,10 @@ from bs4.element import Tag
 from bs4 import BeautifulSoup
 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
+from ..utils import create_session, remove_attributes, create_logger
 from ...jobs import (
     JobPost,
     Location,
@@ -30,13 +32,14 @@ from ...jobs import (
     DescriptionFormat,
 )
 from ..utils import (
-    logger,
     extract_emails_from_text,
     get_enum_from_job_type,
     currency_parser,
     markdown_converter,
 )
 
+log = create_logger("LinkedIn")
+
 
 class LinkedInScraper(Scraper):
     base_url = "https://www.linkedin.com"
@@ -44,19 +47,22 @@ class LinkedInScraper(Scraper):
     band_delay = 4
     jobs_per_page = 25
 
-    def __init__(self, proxies: list[str] | str | None = None):
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+    ):
         """
         Initializes LinkedInScraper with the LinkedIn job search url
         """
-        super().__init__(Site.LINKEDIN, proxies=proxies)
+        super().__init__(Site.LINKEDIN, 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(self.headers)
+        self.session.headers.update(headers)
         self.scraper_input = None
         self.country = "worldwide"
         self.job_url_direct_regex = re.compile(r'(?<=\?url=)[^"]+')
@@ -70,17 +76,19 @@ class LinkedInScraper(Scraper):
         self.scraper_input = scraper_input
         job_list: list[JobPost] = []
         seen_ids = set()
-        page = scraper_input.offset // 10 * 10 if scraper_input.offset else 0
+        start = scraper_input.offset // 10 * 10 if scraper_input.offset else 0
         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 < 1000
+            lambda: len(job_list) < scraper_input.results_wanted and start < 1000
         )
         while continue_search():
             request_count += 1
-            logger.info(f"LinkedIn search page: {request_count}")
+            log.info(
+                f"search page: {request_count} / {math.ceil(scraper_input.results_wanted / 10)}"
+            )
             params = {
                 "keywords": scraper_input.search_term,
                 "location": scraper_input.location,
@@ -92,7 +100,7 @@ class LinkedInScraper(Scraper):
                     else None
                 ),
                 "pageNum": 0,
-                "start": page,
+                "start": start,
                 "f_AL": "true" if scraper_input.easy_apply else None,
                 "f_C": (
                     ",".join(map(str, scraper_input.linkedin_company_ids))
@@ -118,13 +126,13 @@ 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")
@@ -154,7 +162,7 @@ class LinkedInScraper(Scraper):
 
             if continue_search():
                 time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
-                page += len(job_list)
+                start += len(job_list)
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
@@ -210,7 +218,7 @@ class LinkedInScraper(Scraper):
             job_details = self._get_job_details(job_id)
 
         return JobPost(
-            id=job_id,
+            id=f"li-{job_id}",
             title=title,
             company_name=company,
             company_url=company_url,
@@ -224,7 +232,7 @@ class LinkedInScraper(Scraper):
             description=job_details.get("description"),
             job_url_direct=job_details.get("job_url_direct"),
             emails=extract_emails_from_text(job_details.get("description")),
-            logo_photo_url=job_details.get("logo_photo_url"),
+            company_logo=job_details.get("company_logo"),
             job_function=job_details.get("job_function"),
         )
 
@@ -236,7 +244,7 @@ class LinkedInScraper(Scraper):
         """
         try:
             response = self.session.get(
-                f"{self.base_url}/jobs-guest/jobs/api/jobPosting/{job_id}", timeout=5
+                f"{self.base_url}/jobs/view/{job_id}", timeout=5
             )
             response.raise_for_status()
         except:
@@ -266,15 +274,19 @@ class LinkedInScraper(Scraper):
             )
             if job_function_span:
                 job_function = job_function_span.text.strip()
+
+        company_logo = (
+            logo_image.get("data-delayed-url")
+            if (logo_image := soup.find("img", {"class": "artdeco-entity-image"}))
+            else None
+        )
         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_url_direct": self._parse_job_url_direct(soup),
-            "logo_photo_url": soup.find("img", {"class": "artdeco-entity-image"}).get(
-                "data-delayed-url"
-            ),
+            "company_logo": company_logo,
             "job_function": job_function,
         }
 
@@ -401,12 +413,3 @@ class LinkedInScraper(Scraper):
             JobType.CONTRACT: "C",
             JobType.TEMPORARY: "T",
         }.get(job_type_enum, "")
-
-    headers = {
-        "authority": "www.linkedin.com",
-        "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-        "accept-language": "en-US,en;q=0.9",
-        "cache-control": "max-age=0",
-        "upgrade-insecure-requests": "1",
-        "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
-    }

src/jobspy/scrapers/linkedin/constants.py

@@ -0,0 +1,8 @@
+headers = {
+    "authority": "www.linkedin.com",
+    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+    "accept-language": "en-US,en;q=0.9",
+    "cache-control": "max-age=0",
+    "upgrade-insecure-requests": "1",
+    "user-agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+}

src/jobspy/scrapers/utils.py

@@ -1,26 +1,32 @@
 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 JobType
+from ..jobs import CompensationInterval, JobType
 
-logger = logging.getLogger("JobSpy")
-logger.propagate = False
-if not logger.handlers:
-    logger.setLevel(logging.INFO)
-    console_handler = logging.StreamHandler()
-    format = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-    formatter = logging.Formatter(format)
-    console_handler.setFormatter(formatter)
-    logger.addHandler(console_handler)
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+
+def create_logger(name: str):
+    logger = logging.getLogger(f"JobSpy:{name}")
+    logger.propagate = False
+    if not logger.handlers:
+        logger.setLevel(logging.INFO)
+        console_handler = logging.StreamHandler()
+        format = "%(asctime)s - %(levelname)s - %(name)s - %(message)s"
+        formatter = logging.Formatter(format)
+        console_handler.setFormatter(formatter)
+        logger.addHandler(console_handler)
+    return logger
 
 
 class RotatingProxySession:
@@ -100,6 +106,7 @@ class TLSRotating(RotatingProxySession, tls_client.Session):
 def create_session(
     *,
     proxies: dict | str | None = None,
+    ca_cert: str | None = None,
     is_tls: bool = True,
     has_retry: bool = False,
     delay: int = 1,
@@ -119,10 +126,13 @@ def create_session(
             clear_cookies=clear_cookies,
         )
 
+    if ca_cert:
+        session.verify = ca_cert
+
     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.
 
@@ -134,7 +144,9 @@ def set_logger_level(verbose: int = 2):
     level_name = {2: "INFO", 1: "WARNING", 0: "ERROR"}.get(verbose, "INFO")
     level = getattr(logging, level_name.upper(), None)
     if level is not None:
-        logger.setLevel(level)
+        for logger_name in logging.root.manager.loggerDict:
+            if logger_name.startswith("JobSpy:"):
+                logging.getLogger(logger_name).setLevel(level)
     else:
         raise ValueError(f"Invalid log level: {level_name}")
 
@@ -193,10 +205,16 @@ def extract_salary(
     upper_limit=700000,
     hourly_threshold=350,
     monthly_threshold=30000,
+    enforce_annual_salary=False,
 ):
+    """
+    Extracts salary information from a string and returns the salary interval, min and max salary values, and currency.
+    (TODO: Needs test cases as the regex is complicated and may not cover all edge cases)
+    """
     if not salary_str:
         return None, None, None, None
 
+    annual_max_salary = None
     min_max_pattern = r"\$(\d+(?:,\d+)?(?:\.\d+)?)([kK]?)\s*[-—–]\s*(?:\$)?(\d+(?:,\d+)?(?:\.\d+)?)([kK]?)"
 
     def to_int(s):
@@ -220,20 +238,51 @@ def extract_salary(
 
         # Convert to annual if less than the hourly threshold
         if min_salary < hourly_threshold:
-            min_salary = convert_hourly_to_annual(min_salary)
+            interval = CompensationInterval.HOURLY.value
+            annual_min_salary = convert_hourly_to_annual(min_salary)
             if max_salary < hourly_threshold:
-                max_salary = convert_hourly_to_annual(max_salary)
+                annual_max_salary = convert_hourly_to_annual(max_salary)
 
         elif min_salary < monthly_threshold:
-            min_salary = convert_monthly_to_annual(min_salary)
+            interval = CompensationInterval.MONTHLY.value
+            annual_min_salary = convert_monthly_to_annual(min_salary)
             if max_salary < monthly_threshold:
-                max_salary = convert_monthly_to_annual(max_salary)
+                annual_max_salary = convert_monthly_to_annual(max_salary)
+
+        else:
+            interval = CompensationInterval.YEARLY.value
+            annual_min_salary = min_salary
+            annual_max_salary = max_salary
 
         # Ensure salary range is within specified limits
+        if not annual_max_salary:
+            return None, None, None, None
         if (
-            lower_limit <= min_salary <= upper_limit
-            and lower_limit <= max_salary <= upper_limit
-            and min_salary < max_salary
+            lower_limit <= annual_min_salary <= upper_limit
+            and lower_limit <= annual_max_salary <= upper_limit
+            and annual_min_salary < annual_max_salary
         ):
-            return "yearly", min_salary, max_salary, "USD"
+            if enforce_annual_salary:
+                return interval, annual_min_salary, annual_max_salary, "USD"
+            else:
+                return interval, min_salary, max_salary, "USD"
     return None, None, None, None
+
+
+def extract_job_type(description: str):
+    if not description:
+        return []
+
+    keywords = {
+        JobType.FULL_TIME: r"full\s?time",
+        JobType.PART_TIME: r"part\s?time",
+        JobType.INTERNSHIP: r"internship",
+        JobType.CONTRACT: r"contract",
+    }
+
+    listing_types = []
+    for key, pattern in keywords.items():
+        if re.search(pattern, description, re.IGNORECASE):
+            listing_types.append(key)
+
+    return listing_types if listing_types else None

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -11,20 +11,20 @@ import json
 import math
 import re
 import time
+from concurrent.futures import ThreadPoolExecutor
 from datetime import datetime
 from typing import Optional, Tuple, Any
 
-from concurrent.futures import ThreadPoolExecutor
-
 from bs4 import BeautifulSoup
 
+from .constants import headers
 from .. import Scraper, ScraperInput, Site
 from ..utils import (
-    logger,
     extract_emails_from_text,
     create_session,
     markdown_converter,
     remove_attributes,
+    create_logger,
 )
 from ...jobs import (
     JobPost,
@@ -36,19 +36,24 @@ from ...jobs import (
     DescriptionFormat,
 )
 
+log = create_logger("ZipRecruiter")
+
 
 class ZipRecruiterScraper(Scraper):
     base_url = "https://www.ziprecruiter.com"
     api_url = "https://api.ziprecruiter.com"
 
-    def __init__(self, proxies: list[str] | str | None = None):
+    def __init__(
+        self, proxies: list[str] | str | None = None, ca_cert: str | None = None
+    ):
         """
         Initializes ZipRecruiterScraper with the ZipRecruiter job search url
         """
         super().__init__(Site.ZIP_RECRUITER, proxies=proxies)
 
         self.scraper_input = None
-        self.session = create_session(proxies=proxies)
+        self.session = create_session(proxies=proxies, ca_cert=ca_cert)
+        self.session.headers.update(headers)
         self._get_cookies()
 
         self.delay = 5
@@ -71,7 +76,7 @@ class ZipRecruiterScraper(Scraper):
                 break
             if page > 1:
                 time.sleep(self.delay)
-            logger.info(f"ZipRecruiter search page: {page}")
+            log.info(f"search page: {page} / {max_pages}")
             jobs_on_page, continue_token = self._find_jobs_in_page(
                 scraper_input, continue_token
             )
@@ -97,22 +102,20 @@ class ZipRecruiterScraper(Scraper):
         if continue_token:
             params["continue_from"] = continue_token
         try:
-            res = self.session.get(
-                f"{self.api_url}/jobs-app/jobs", headers=self.headers, params=params
-            )
+            res = self.session.get(f"{self.api_url}/jobs-app/jobs", params=params)
             if res.status_code not in range(200, 400):
                 if res.status_code == 429:
                     err = "429 Response - Blocked by ZipRecruiter for too many requests"
                 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()
@@ -160,7 +163,7 @@ class ZipRecruiterScraper(Scraper):
         description_full, job_url_direct = self._get_descr(job_url)
 
         return JobPost(
-            id=str(job["listing_key"]),
+            id=f'zr-{job["listing_key"]}',
             title=title,
             company_name=company,
             location=location,
@@ -180,7 +183,7 @@ class ZipRecruiterScraper(Scraper):
         )
 
     def _get_descr(self, job_url):
-        res = self.session.get(job_url, headers=self.headers, allow_redirects=True)
+        res = self.session.get(job_url, allow_redirects=True)
         description_full = job_url_direct = None
         if res.ok:
             soup = BeautifulSoup(res.text, "html.parser")
@@ -200,7 +203,7 @@ class ZipRecruiterScraper(Scraper):
             script_tag = soup.find("script", type="application/json")
             if script_tag:
                 job_json = json.loads(script_tag.string)
-                job_url_val = job_json["model"]["saveJobURL"]
+                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)
@@ -211,9 +214,30 @@ 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.
+        """
+        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"),
+        ]
+
         url = f"{self.api_url}/jobs-app/event"
-        self.session.post(url, data=data, headers=self.headers)
+        self.session.post(url, data=data)
 
     @staticmethod
     def _get_job_type_enum(job_type_str: str) -> list[JobType] | None:
@@ -241,14 +265,3 @@ class ZipRecruiterScraper(Scraper):
         if scraper_input.distance:
             params["radius"] = scraper_input.distance
         return {k: v for k, v in params.items() if v is not None}
-
-    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",
-    }

src/jobspy/scrapers/ziprecruiter/constants.py

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

src/tests/test_all.py

@@ -1,14 +0,0 @@
-from ..jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_all():
-    result = scrape_jobs(
-        site_name=["linkedin", "indeed", "zip_recruiter", "glassdoor"],
-        search_term="software engineer",
-        results_wanted=5,
-    )
-
-    assert (
-        isinstance(result, pd.DataFrame) and not result.empty
-    ), "Result should be a non-empty DataFrame"

src/tests/test_glassdoor.py

@@ -1,11 +0,0 @@
-from ..jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_indeed():
-    result = scrape_jobs(
-        site_name="glassdoor", search_term="software engineer", country_indeed="USA"
-    )
-    assert (
-        isinstance(result, pd.DataFrame) and not result.empty
-    ), "Result should be a non-empty DataFrame"

src/tests/test_indeed.py

@@ -1,11 +0,0 @@
-from ..jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_indeed():
-    result = scrape_jobs(
-        site_name="indeed", search_term="software engineer", country_indeed="usa"
-    )
-    assert (
-        isinstance(result, pd.DataFrame) and not result.empty
-    ), "Result should be a non-empty DataFrame"

src/tests/test_linkedin.py

@@ -1,12 +0,0 @@
-from ..jobspy import scrape_jobs
-import pandas as pd
-
-
-def test_linkedin():
-    result = scrape_jobs(
-        site_name="linkedin",
-        search_term="software engineer",
-    )
-    assert (
-        isinstance(result, pd.DataFrame) and not result.empty
-    ), "Result should be a non-empty DataFrame"

src/tests/test_ziprecruiter.py

@@ -1,13 +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",
-    )
-
-    assert (
-        isinstance(result, pd.DataFrame) and not result.empty
-    ), "Result should be a non-empty DataFrame"