Fix Indeed exceptions on parsing description

* enh(indeed): mult job types

* feat(jobs):  urgent kws

* fix(indeed): use new session obj per request

* fix: emails as comma separated in output

* fix: put num urgent words in output

* chore: readme

README.md

@@ -4,10 +4,10 @@
 
 **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://calendly.com/zachary-products/15min)** *to
+*Looking to build a data-focused software product?* **[Book a call](https://calendly.com/bunsly/15min)** *to
 work with us.*  
 \
-Check out another project we wrote: ***[HomeHarvest](https://github.com/ZacharyHampton/HomeHarvest)** – a Python package
+Check out another project we wrote: ***[HomeHarvest](https://github.com/Bunsly/HomeHarvest)** – a Python package
 for real estate scraping*
 
 ## Features
@@ -24,7 +24,7 @@ Updated for release v1.1.3
 ### Installation
 
 ```
-pip install --upgrade python-jobspy
+pip install python-jobspy
 ```
 
 _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/) required_
@@ -33,37 +33,19 @@ _Python version >= [3.10](https://www.python.org/downloads/release/python-3100/)
 
 ```python
 from jobspy import scrape_jobs
-import pandas as pd
 
-jobs: pd.DataFrame = scrape_jobs(
+jobs = scrape_jobs(
     site_name=["indeed", "linkedin", "zip_recruiter"],
     search_term="software engineer",
     location="Dallas, TX",
     results_wanted=10,
-
     country_indeed='USA'  # only needed for indeed
-
-    # use if you want to use a proxy
-    # proxy="http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
-    # offset=25 # use if you want to start at a specific offset
 )
+print(f"Found {len(jobs)} jobs")
+print(jobs.head())
+jobs.to_csv("jobs.csv", index=False)
 
-# formatting for pandas
-pd.set_option('display.max_columns', None)
-pd.set_option('display.max_rows', None)
-pd.set_option('display.width', None)
-pd.set_option('display.max_colwidth', 50)  # set to 0 to see full job url / desc
-
-# 1 output to console
-print(jobs)
-
-# 2 display in Jupyter Notebook (1. pip install jupyter 2. jupyter notebook)
-# display(jobs)
-
-# 3 output to .csv
-# jobs.to_csv('jobs.csv', index=False)
-
-# 4 output to .xlsx
+# output to Excel
 # jobs.to_xlsx('jobs.xlsx', index=False)
 
 ```
@@ -95,7 +77,7 @@ Optional
 ├── results_wanted (int): number of job results to retrieve for each site specified in 'site_type'
 ├── easy_apply (bool): filters for jobs that are hosted on LinkedIn
 ├── country_indeed (enum): filters the country on Indeed (see below for correct spelling)
-├── offset (enum): starts the search from an offset (e.g. 25 will start the search from the 25th result)
+├── offset (num): starts the search from an offset (e.g. 25 will start the search from the 25th result)
 ```
 
 ### JobPost Schema
@@ -110,13 +92,16 @@ JobPost
 │   ├── city (str)
 │   ├── state (str)
 ├── description (str)
-├── job_type (enum): fulltime, parttime, internship, contract
+├── job_type (str): fulltime, parttime, internship, contract
 ├── compensation (object)
-│   ├── interval (enum): yearly, monthly, weekly, daily, hourly
+│   ├── interval (str): yearly, monthly, weekly, daily, hourly
 │   ├── min_amount (int)
 │   ├── max_amount (int)
 │   └── currency (enum)
 └── date_posted (date)
+└── emails (str)
+└── num_urgent_words (int)
+└── is_remote (bool) - just for Indeed at the momen
 ```
 
 ### Exceptions
@@ -174,8 +159,7 @@ persist, [submit an issue](https://github.com/cullenwatson/JobSpy/issues).
 ---
 
 **Q: Received a response code 429?**  
-**A:** This indicates that you have been blocked by the job board site for sending too many requests. Currently, *
-*LinkedIn** is particularly aggressive with blocking. We recommend:
+**A:** This indicates that you have been blocked by the job board site for sending too many requests. All of the job board sites are aggressive with blocking. We recommend:
 
 - Waiting a few seconds between requests.
 - Trying a VPN or proxy to change your IP address.

examples/JobSpy_Demo.py

@@ -6,23 +6,23 @@ jobs: pd.DataFrame = scrape_jobs(
     search_term="software engineer",
     location="Dallas, TX",
     results_wanted=50,  # be wary the higher it is, the more likey you'll get blocked (rotating proxy should work tho)
-    country_indeed='USA',
+    country_indeed="USA",
     offset=25  # start jobs from an offset (use if search failed and want to continue)
     # proxy="http://jobspy:5a4vpWtj8EeJ2hoYzk@ca.smartproxy.com:20001",
 )
 
 # formatting for pandas
-pd.set_option('display.max_columns', None)
-pd.set_option('display.max_rows', None)
-pd.set_option('display.width', None)
-pd.set_option('display.max_colwidth', 50)  # set to 0 to see full job url / desc
+pd.set_option("display.max_columns", None)
+pd.set_option("display.max_rows", None)
+pd.set_option("display.width", None)
+pd.set_option("display.max_colwidth", 50)  # set to 0 to see full job url / desc
 
 # 1: output to console
 print(jobs)
 
 # 2: output to .csv
-jobs.to_csv('./jobs.csv', index=False)
-print('outputted to jobs.csv')
+jobs.to_csv("./jobs.csv", index=False)
+print("outputted to jobs.csv")
 
 # 3: output to .xlsx
 # jobs.to_xlsx('jobs.xlsx', index=False)

pyproject.toml

@@ -1,9 +1,9 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.9"
+version = "1.1.14"
 description = "Job scraper for LinkedIn, Indeed & ZipRecruiter"
-authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
-homepage = "https://github.com/cullenwatson/JobSpy"
+authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
+homepage = "https://github.com/Bunsly/JobSpy"
 readme = "README.md"
 
 packages = [
@@ -16,6 +16,7 @@ requests = "^2.31.0"
 tls-client = "^0.2.1"
 beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"
+NUMPY = "1.24.2"
 pydantic = "^2.3.0"
 
 

src/jobspy/__init__.py

@@ -1,7 +1,7 @@
 import pandas as pd
 import concurrent.futures
 from concurrent.futures import ThreadPoolExecutor
-from typing import List, Tuple, Optional
+from typing import Tuple, Optional
 
 from .jobs import JobType, Location
 from .scrapers.indeed import IndeedScraper
@@ -26,7 +26,7 @@ def _map_str_to_site(site_name: str) -> Site:
 
 
 def scrape_jobs(
-        site_name: str | List[str] | Site | List[Site],
+    site_name: str | list[str] | Site | list[Site],
     search_term: str,
     location: str = "",
     distance: int = None,
@@ -37,7 +37,7 @@ def scrape_jobs(
     country_indeed: str = "usa",
     hyperlinks: bool = False,
     proxy: Optional[str] = None,
-        offset: Optional[int] = 0
+    offset: Optional[int] = 0,
 ) -> pd.DataFrame:
     """
     Simultaneously scrapes job data from multiple job sites.
@@ -72,7 +72,7 @@ def scrape_jobs(
         job_type=job_type,
         easy_apply=easy_apply,
         results_wanted=results_wanted,
-        offset=offset
+        offset=offset,
     )
 
     def scrape_site(site: Site) -> Tuple[str, JobResponse]:
@@ -84,13 +84,12 @@ def scrape_jobs(
         except (LinkedInException, IndeedException, ZipRecruiterException) as lie:
             raise lie
         except Exception as e:
-            # unhandled exceptions
             if site == Site.LINKEDIN:
-                raise LinkedInException()
+                raise LinkedInException(str(e))
             if site == Site.INDEED:
-                raise IndeedException()
+                raise IndeedException(str(e))
             if site == Site.ZIP_RECRUITER:
-                raise ZipRecruiterException()
+                raise ZipRecruiterException(str(e))
             else:
                 raise e
         return site.value, scraped_data
@@ -98,8 +97,8 @@ def scrape_jobs(
     site_to_jobs_dict = {}
 
     def worker(site):
-        site_value, scraped_data = scrape_site(site)
-        return site_value, scraped_data
+        site_val, scraped_info = scrape_site(site)
+        return site_val, scraped_info
 
     with ThreadPoolExecutor() as executor:
         future_to_site = {
@@ -110,7 +109,7 @@ def scrape_jobs(
             site_value, scraped_data = future.result()
             site_to_jobs_dict[site_value] = scraped_data
 
-    jobs_dfs: List[pd.DataFrame] = []
+    jobs_dfs: list[pd.DataFrame] = []
 
     for site, job_response in site_to_jobs_dict.items():
         for job in job_response.jobs:
@@ -120,12 +119,14 @@ def scrape_jobs(
             ] = f'<a href="{job_data["job_url"]}">{job_data["job_url"]}</a>'
             job_data["site"] = site
             job_data["company"] = job_data["company_name"]
-            if job_data["job_type"]:
-                # Take the first value from the job type tuple
-                job_data["job_type"] = job_data["job_type"].value[0]
-            else:
-                job_data["job_type"] = None
-
+            job_data["job_type"] = (
+                ", ".join(job_type.value[0] for job_type in job_data["job_type"])
+                if job_data["job_type"]
+                else None
+            )
+            job_data["emails"] = (
+                ", ".join(job_data["emails"]) if job_data["emails"] else None
+            )
             job_data["location"] = Location(**job_data["location"]).display_location()
 
             compensation_obj = job_data.get("compensation")
@@ -149,7 +150,7 @@ def scrape_jobs(
 
     if jobs_dfs:
         jobs_df = pd.concat(jobs_dfs, ignore_index=True)
-        desired_order: List[str] = [
+        desired_order: list[str] = [
             "job_url_hyper" if hyperlinks else "job_url",
             "site",
             "title",
@@ -158,10 +159,12 @@ def scrape_jobs(
             "job_type",
             "date_posted",
             "interval",
-            "benefits",
             "min_amount",
             "max_amount",
             "currency",
+            "is_remote",
+            "num_urgent_words",
+            "benefits",
             "emails",
             "description",
         ]

src/jobspy/jobs/__init__.py

@@ -37,10 +37,16 @@ class JobType(Enum):
         "повназайнятість",
         "toànthờigian",
     )
-    PART_TIME = ("parttime", "teilzeit")
+    PART_TIME = ("parttime", "teilzeit", "částečnýúvazek", "deltid")
     CONTRACT = ("contract", "contractor")
     TEMPORARY = ("temporary",)
-    INTERNSHIP = ("internship", "prácticas", "ojt(onthejobtraining)", "praktikum")
+    INTERNSHIP = (
+        "internship",
+        "prácticas",
+        "ojt(onthejobtraining)",
+        "praktikum",
+        "praktik",
+    )
 
     PER_DIEM = ("perdiem",)
     NIGHTS = ("nights",)
@@ -182,12 +188,15 @@ class JobPost(BaseModel):
     job_url: str
     location: Optional[Location]
 
-    description: Optional[str] = None
-    job_type: Optional[JobType] = None
-    compensation: Optional[Compensation] = None
-    date_posted: Optional[date] = None
-    benefits: Optional[str] = None
-    emails: Optional[list[str]] = None
+    description: str | None = None
+    job_type: list[JobType] | None = None
+    compensation: Compensation | None = None
+    date_posted: date | None = None
+    benefits: str | None = None
+    emails: list[str] | None = None
+    num_urgent_words: int | None = None
+    is_remote: bool | None = None
+    # company_industry: str | None = None
 
 
 class JobResponse(BaseModel):

src/jobspy/scrapers/exceptions.py

@@ -7,12 +7,15 @@ This module contains the set of Scrapers' exceptions.
 
 
 class LinkedInException(Exception):
-    """Failed to scrape LinkedIn"""
+    def __init__(self, message=None):
+        super().__init__(message or "An error occurred with LinkedIn")
 
 
 class IndeedException(Exception):
-    """Failed to scrape Indeed"""
+    def __init__(self, message=None):
+        super().__init__(message or "An error occurred with Indeed")
 
 
 class ZipRecruiterException(Exception):
-    """Failed to scrape ZipRecruiter"""
+    def __init__(self, message=None):
+        super().__init__(message or "An error occurred with ZipRecruiter")

src/jobspy/scrapers/indeed/__init__.py

@@ -9,15 +9,19 @@ import math
 import io
 import json
 from datetime import datetime
-from typing import Optional
 
-import tls_client
 import urllib.parse
 from bs4 import BeautifulSoup
 from bs4.element import Tag
 from concurrent.futures import ThreadPoolExecutor, Future
 
 from ..exceptions import IndeedException
+from ..utils import (
+    count_urgent_words,
+    extract_emails_from_text,
+    create_session,
+    get_enum_from_job_type,
+)
 from ...jobs import (
     JobPost,
     Compensation,
@@ -27,11 +31,10 @@ from ...jobs import (
     JobType,
 )
 from .. import Scraper, ScraperInput, Site
-from ...utils import extract_emails_from_text
 
 
 class IndeedScraper(Scraper):
-    def __init__(self, proxy: Optional[str] = None):
+    def __init__(self, proxy: str | None = None):
         """
         Initializes IndeedScraper with the Indeed job search url
         """
@@ -44,20 +47,18 @@ class IndeedScraper(Scraper):
         self.seen_urls = set()
 
     def scrape_page(
-            self, scraper_input: ScraperInput, page: int, session: tls_client.Session
+        self, scraper_input: ScraperInput, page: int
     ) -> tuple[list[JobPost], int]:
         """
         Scrapes a page of Indeed for jobs with scraper_input criteria
         :param scraper_input:
         :param page:
-        :param session:
         :return: jobs found on page, total number of jobs found for search
         """
         self.country = scraper_input.country
         domain = self.country.domain_value
         self.url = f"https://{domain}.indeed.com"
-
-        job_list: list[JobPost] = []
+        session = create_session(self.proxy)
 
         params = {
             "q": scraper_input.search_term,
@@ -79,9 +80,9 @@ class IndeedScraper(Scraper):
         try:
             response = session.get(
                 f"{self.url}/jobs",
+                headers=self.get_headers(),
                 params=params,
                 allow_redirects=True,
-                proxy=self.proxy,
                 timeout_seconds=10,
             )
             if response.status_code not in range(200, 400):
@@ -109,7 +110,7 @@ class IndeedScraper(Scraper):
         ):
             raise IndeedException("No jobs found.")
 
-        def process_job(job) -> Optional[JobPost]:
+        def process_job(job) -> JobPost | None:
             job_url = f'{self.url}/jobs/viewjob?jk={job["jobkey"]}'
             job_url_client = f'{self.url}/viewjob?jk={job["jobkey"]}'
             if job_url in self.seen_urls:
@@ -128,8 +129,8 @@ class IndeedScraper(Scraper):
                 if interval in CompensationInterval.__members__:
                     compensation = Compensation(
                         interval=CompensationInterval[interval],
-                        min_amount=int(extracted_salary.get("max")),
-                        max_amount=int(extracted_salary.get("min")),
+                        min_amount=int(extracted_salary.get("min")),
+                        max_amount=int(extracted_salary.get("max")),
                         currency=currency,
                     )
 
@@ -138,8 +139,7 @@ class IndeedScraper(Scraper):
             date_posted = datetime.fromtimestamp(timestamp_seconds)
             date_posted = date_posted.strftime("%Y-%m-%d")
 
-            description = self.get_description(job_url, session)
-            emails = extract_emails_from_text(description)
+            description = self.get_description(job_url)
             with io.StringIO(job["snippet"]) as f:
                 soup_io = BeautifulSoup(f, "html.parser")
                 li_elements = soup_io.find_all("li")
@@ -155,18 +155,22 @@ class IndeedScraper(Scraper):
                     state=job.get("jobLocationState"),
                     country=self.country,
                 ),
-                emails=extract_emails_from_text(description),
                 job_type=job_type,
                 compensation=compensation,
                 date_posted=date_posted,
                 job_url=job_url_client,
+                emails=extract_emails_from_text(description) if description else None,
+                num_urgent_words=count_urgent_words(description)
+                if description
+                else None,
+                is_remote=self.is_remote_job(job),
             )
             return job_post
 
+        jobs = jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]
         with ThreadPoolExecutor(max_workers=1) as executor:
             job_results: list[Future] = [
-                executor.submit(process_job, job)
-                for job in jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]
+                executor.submit(process_job, job) for job in jobs
             ]
 
         job_list = [result.result() for result in job_results if result.result()]
@@ -179,20 +183,16 @@ class IndeedScraper(Scraper):
         :param scraper_input:
         :return: job_response
         """
-        session = tls_client.Session(
-            client_identifier="chrome112", random_tls_extension_order=True
-        )
-
         pages_to_process = (
             math.ceil(scraper_input.results_wanted / self.jobs_per_page) - 1
         )
 
         #: get first page to initialize session
-        job_list, total_results = self.scrape_page(scraper_input, 0, session)
+        job_list, total_results = self.scrape_page(scraper_input, 0)
 
         with ThreadPoolExecutor(max_workers=1) as executor:
             futures: list[Future] = [
-                executor.submit(self.scrape_page, scraper_input, page, session)
+                executor.submit(self.scrape_page, scraper_input, page)
                 for page in range(1, pages_to_process + 1)
             ]
 
@@ -210,21 +210,24 @@ class IndeedScraper(Scraper):
         )
         return job_response
 
-    def get_description(self, job_page_url: str, session: tls_client.Session) -> Optional[str]:
+    def get_description(self, job_page_url: str) -> str | None:
         """
         Retrieves job description by going to the job page url
         :param job_page_url:
-        :param session:
         :return: description
         """
         parsed_url = urllib.parse.urlparse(job_page_url)
         params = urllib.parse.parse_qs(parsed_url.query)
         jk_value = params.get("jk", [None])[0]
         formatted_url = f"{self.url}/viewjob?jk={jk_value}&spa=1"
+        session = create_session(self.proxy)
 
         try:
             response = session.get(
-                formatted_url, allow_redirects=True, timeout_seconds=5, proxy=self.proxy
+                formatted_url,
+                headers=self.get_headers(),
+                allow_redirects=True,
+                timeout_seconds=5,
             )
         except Exception as e:
             return None
@@ -232,40 +235,56 @@ class IndeedScraper(Scraper):
         if response.status_code not in range(200, 400):
             return None
 
-        raw_description = response.json()["body"]["jobInfoWrapperModel"][
-            "jobInfoModel"
-        ]["sanitizedJobDescription"]
-        with io.StringIO(raw_description) as f:
-            soup = BeautifulSoup(f, "html.parser")
-            text_content = " ".join(soup.get_text().split()).strip()
+        soup = BeautifulSoup(response.text, "html.parser")
+        script_tag = soup.find(
+            "script", text=lambda x: x and "window._initialData" in x
+        )
+
+        if not script_tag:
+            return None
+
+        script_code = script_tag.string
+        match = re.search(r"window\._initialData\s*=\s*({.*?})\s*;", script_code, re.S)
+
+        if not match:
+            return None
+
+        json_string = match.group(1)
+        data = json.loads(json_string)
+        try:
+            job_description = data["jobInfoWrapperModel"]["jobInfoModel"][
+                "sanitizedJobDescription"
+            ]
+        except (KeyError, TypeError, IndexError):
+            return None
+
+        soup = BeautifulSoup(
+            job_description, "html.parser"
+        )
+        text_content = " ".join(
+            soup.get_text(separator=" ").split()
+        ).strip()
+
         return text_content
 
     @staticmethod
-    def get_job_type(job: dict) -> Optional[JobType]:
+    def get_job_type(job: dict) -> list[JobType] | None:
         """
-        Parses the job to get JobTypeIndeed
+        Parses the job to get list of job types
         :param job:
         :return:
         """
+        job_types: list[JobType] = []
         for taxonomy in job["taxonomyAttributes"]:
             if taxonomy["label"] == "job-types":
-                if len(taxonomy["attributes"]) > 0:
-                    label = taxonomy["attributes"][0].get("label")
+                for i in range(len(taxonomy["attributes"])):
+                    label = taxonomy["attributes"][i].get("label")
                     if label:
                         job_type_str = label.replace("-", "").replace(" ", "").lower()
-                        return IndeedScraper.get_enum_from_job_type(job_type_str)
-        return None
-
-    @staticmethod
-    def get_enum_from_job_type(job_type_str):
-        """
-        Given a string, returns the corresponding JobType enum member if a match is found.
-        for job_type in JobType:
-        """
-        for job_type in JobType:
-            if job_type_str in job_type.value:
-                return job_type
-        return None
+                        job_type = get_enum_from_job_type(job_type_str)
+                        if job_type:
+                            job_types.append(job_type)
+        return job_types
 
     @staticmethod
     def parse_jobs(soup: BeautifulSoup) -> dict:
@@ -275,7 +294,7 @@ class IndeedScraper(Scraper):
         :return: jobs
         """
 
-        def find_mosaic_script() -> Optional[Tag]:
+        def find_mosaic_script() -> Tag | None:
             """
             Finds jobcards script tag
             :return: script_tag
@@ -325,3 +344,30 @@ class IndeedScraper(Scraper):
             data = json.loads(json_str)
             total_num_jobs = int(data["searchTitleBarModel"]["totalNumResults"])
         return total_num_jobs
+
+    @staticmethod
+    def get_headers():
+        return {
+            "authority": "www.indeed.com",
+            "accept": "*/*",
+            "accept-language": "en-US,en;q=0.9",
+            "referer": "https://www.indeed.com/viewjob?jk=fe6182337d72c7b1&tk=1hcbfcmd0k62t802&from=serp&vjs=3&advn=8132938064490989&adid=408692607&ad=-6NYlbfkN0A3Osc99MJFDKjquSk4WOGT28ALb_ad4QMtrHreCb9ICg6MiSVy9oDAp3evvOrI7Q-O9qOtQTg1EPbthP9xWtBN2cOuVeHQijxHjHpJC65TjDtftH3AXeINjBvAyDrE8DrRaAXl8LD3Fs1e_xuDHQIssdZ2Mlzcav8m5jHrA0fA64ZaqJV77myldaNlM7-qyQpy4AsJQfvg9iR2MY7qeC5_FnjIgjKIy_lNi9OPMOjGRWXA94CuvC7zC6WeiJmBQCHISl8IOBxf7EdJZlYdtzgae3593TFxbkd6LUwbijAfjax39aAuuCXy3s9C4YgcEP3TwEFGQoTpYu9Pmle-Ae1tHGPgsjxwXkgMm7Cz5mBBdJioglRCj9pssn-1u1blHZM4uL1nK9p1Y6HoFgPUU9xvKQTHjKGdH8d4y4ETyCMoNF4hAIyUaysCKdJKitC8PXoYaWhDqFtSMR4Jys8UPqUV&xkcb=SoDD-_M3JLQfWnQTDh0LbzkdCdPP&xpse=SoBa6_I3JLW9FlWZlB0PbzkdCdPP&sjdu=i6xVERweJM_pVUvgf-MzuaunBTY7G71J5eEX6t4DrDs5EMPQdODrX7Nn-WIPMezoqr5wA_l7Of-3CtoiUawcHw",
+            "sec-ch-ua": '"Google Chrome";v="119", "Chromium";v="119", "Not?A_Brand";v="24"',
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": '"Windows"',
+            "sec-fetch-dest": "empty",
+            "sec-fetch-mode": "cors",
+            "sec-fetch-site": "same-origin",
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+        }
+
+    @staticmethod
+    def is_remote_job(job: dict) -> bool:
+        """
+        :param job:
+        :return: bool
+        """
+        for taxonomy in job.get("taxonomyAttributes", []):
+            if taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0:
+                return True
+        return False

src/jobspy/scrapers/linkedin/__init__.py

@@ -16,6 +16,7 @@ from bs4.element import Tag
 from threading import Lock
 
 from .. import Scraper, ScraperInput, Site
+from ..utils import count_urgent_words, extract_emails_from_text, get_enum_from_job_type
 from ..exceptions import LinkedInException
 from ...jobs import (
     JobPost,
@@ -23,7 +24,6 @@ from ...jobs import (
     JobResponse,
     JobType,
 )
-from ...utils import extract_emails_from_text
 
 
 class LinkedInScraper(Scraper):
@@ -92,13 +92,15 @@ class LinkedInScraper(Scraper):
 
                     break
                 except requests.HTTPError as e:
-                    if hasattr(e, 'response') and e.response is not None:
+                    if hasattr(e, "response") and e.response is not None:
                         if e.response.status_code == 429:
                             time.sleep(self.DELAY)
                             retries += 1
                             continue
                         else:
-                            raise LinkedInException(f"bad response status code: {e.response.status_code}")
+                            raise LinkedInException(
+                                f"bad response status code: {e.response.status_code}"
+                            )
                     else:
                         raise
                 except ProxyError as e:
@@ -107,7 +109,9 @@ class LinkedInScraper(Scraper):
                     raise LinkedInException(str(e))
             else:
                 # Raise an exception if the maximum number of retries is reached
-                raise LinkedInException("Max retries reached, failed to get a valid response")
+                raise LinkedInException(
+                    "Max retries reached, failed to get a valid response"
+                )
 
             soup = BeautifulSoup(response.text, "html.parser")
 
@@ -134,7 +138,9 @@ class LinkedInScraper(Scraper):
                         if job_post:
                             job_list.append(job_post)
                     except Exception as e:
-                        raise LinkedInException("Exception occurred while processing jobs")
+                        raise LinkedInException(
+                            "Exception occurred while processing jobs"
+                        )
             page += 25
 
         job_list = job_list[: scraper_input.results_wanted]
@@ -151,7 +157,11 @@ class LinkedInScraper(Scraper):
         metadata_card = job_card.find("div", class_="base-search-card__metadata")
         location = self.get_location(metadata_card)
 
-        datetime_tag = metadata_card.find("time", class_="job-search-card__listdate") if metadata_card else None
+        datetime_tag = (
+            metadata_card.find("time", class_="job-search-card__listdate")
+            if metadata_card
+            else None
+        )
         date_posted = None
         if datetime_tag and "datetime" in datetime_tag.attrs:
             datetime_str = datetime_tag["datetime"]
@@ -171,13 +181,16 @@ class LinkedInScraper(Scraper):
             location=location,
             date_posted=date_posted,
             job_url=job_url,
+            # job_type=[JobType.FULL_TIME],
             job_type=job_type,
             benefits=benefits,
-            emails=extract_emails_from_text(description)
+            emails=extract_emails_from_text(description) if description else None,
+            num_urgent_words=count_urgent_words(description) if description else None,
         )
 
-    def get_job_description(self, job_page_url: str) -> tuple[None, None] | tuple[
-        str | None, tuple[str | None, JobType | None]]:
+    def get_job_description(
+        self, job_page_url: str
+    ) -> tuple[None, None] | tuple[str | None, tuple[str | None, JobType | None]]:
         """
         Retrieves job description by going to the job page url
         :param job_page_url:
@@ -200,7 +213,7 @@ class LinkedInScraper(Scraper):
 
         def get_job_type(
             soup_job_type: BeautifulSoup,
-        ) -> JobType | None:
+        ) -> list[JobType] | None:
             """
             Gets the job type from job page
             :param soup_job_type:
@@ -223,17 +236,10 @@ class LinkedInScraper(Scraper):
                     employment_type = employment_type.lower()
                     employment_type = employment_type.replace("-", "")
 
-            return LinkedInScraper.get_enum_from_value(employment_type)
+            return [get_enum_from_job_type(employment_type)]
 
         return description, get_job_type(soup)
 
-    @staticmethod
-    def get_enum_from_value(value_str):
-        for job_type in JobType:
-            if value_str in job_type.value:
-                return job_type
-        return None
-
     def get_location(self, metadata_card: Optional[Tag]) -> Location:
         """
         Extracts the location data from the job metadata card.

src/jobspy/scrapers/utils.py

@@ -0,0 +1,56 @@
+import re
+import tls_client
+from ..jobs import JobType
+
+
+def count_urgent_words(description: str) -> int:
+    """
+    Count the number of urgent words or phrases in a job description.
+    """
+    urgent_patterns = re.compile(
+        r"\burgen(t|cy)|\bimmediate(ly)?\b|start asap|\bhiring (now|immediate(ly)?)\b",
+        re.IGNORECASE,
+    )
+    matches = re.findall(urgent_patterns, description)
+    count = len(matches)
+
+    return count
+
+
+def extract_emails_from_text(text: str) -> list[str] | None:
+    if not text:
+        return None
+    email_regex = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")
+    return email_regex.findall(text)
+
+
+def create_session(proxy: str | None = None):
+    """
+    Creates a tls client session
+
+    :return: A session object with or without proxies.
+    """
+    session = tls_client.Session(
+        client_identifier="chrome112",
+        random_tls_extension_order=True,
+    )
+    session.proxies = proxy
+    # TODO multiple proxies
+    # if self.proxies:
+    #     session.proxies = {
+    #         "http": random.choice(self.proxies),
+    #         "https": random.choice(self.proxies),
+    #     }
+
+    return session
+
+
+def get_enum_from_job_type(job_type_str: str) -> JobType | None:
+    """
+    Given a string, returns the corresponding JobType enum member if a match is found.
+    """
+    res = None
+    for job_type in JobType:
+        if job_type_str in job_type.value:
+            res = job_type
+    return res

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -11,7 +11,6 @@ from datetime import datetime, date
 from typing import Optional, Tuple, Any
 from urllib.parse import urlparse, parse_qs, urlunparse
 
-import tls_client
 import requests
 from bs4 import BeautifulSoup
 from bs4.element import Tag
@@ -19,6 +18,7 @@ from concurrent.futures import ThreadPoolExecutor, Future
 
 from .. import Scraper, ScraperInput, Site
 from ..exceptions import ZipRecruiterException
+from ..utils import count_urgent_words, extract_emails_from_text, create_session
 from ...jobs import (
     JobPost,
     Compensation,
@@ -28,7 +28,6 @@ from ...jobs import (
     JobType,
     Country,
 )
-from ...utils import extract_emails_from_text
 
 
 class ZipRecruiterScraper(Scraper):
@@ -42,9 +41,6 @@ class ZipRecruiterScraper(Scraper):
 
         self.jobs_per_page = 20
         self.seen_urls = set()
-        self.session = tls_client.Session(
-            client_identifier="chrome112", random_tls_extension_order=True
-        )
 
     def find_jobs_in_page(
         self, scraper_input: ScraperInput, page: int
@@ -55,14 +51,13 @@ class ZipRecruiterScraper(Scraper):
         :param page:
         :return: jobs found on page
         """
-        job_list: list[JobPost] = []
+        session = create_session(self.proxy)
         try:
-            response = self.session.get(
+            response = session.get(
                 f"{self.url}/jobs-search",
-                headers=ZipRecruiterScraper.headers(),
-                params=ZipRecruiterScraper.add_params(scraper_input, page),
+                headers=self.headers(),
+                params=self.add_params(scraper_input, page),
                 allow_redirects=True,
-                proxy=self.proxy,
                 timeout_seconds=10,
             )
             if response.status_code != 200:
@@ -116,7 +111,11 @@ class ZipRecruiterScraper(Scraper):
         :param scraper_input:
         :return: job_response
         """
-        start_page = (scraper_input.offset // self.jobs_per_page) + 1 if scraper_input.offset else 1
+        start_page = (
+            (scraper_input.offset // self.jobs_per_page) + 1
+            if scraper_input.offset
+            else 1
+        )
         #: get first page to initialize session
         job_list: list[JobPost] = self.find_jobs_in_page(scraper_input, start_page)
         pages_to_process = max(
@@ -137,91 +136,10 @@ class ZipRecruiterScraper(Scraper):
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
 
-    def process_job_html_1(self, job: Tag) -> Optional[JobPost]:
-        """
-        Parses a job from the job content tag
-        :param job: BeautifulSoup Tag for one job post
-        :return JobPost
-        TODO this method isnt finished due to not encountering this type of html often
-        """
-        job_url = self.cleanurl(job.find("a", {"class": "job_link"})["href"])
-        if job_url in self.seen_urls:
-            return None
-
-        title = job.find("h2", {"class": "title"}).text
-        company = job.find("a", {"class": "company_name"}).text.strip()
-
-        description, updated_job_url = self.get_description(job_url)
-        # job_url = updated_job_url if updated_job_url else job_url
-        if description is None:
-            description = job.find("p", {"class": "job_snippet"}).text.strip()
-
-        job_type_element = job.find("li", {"class": "perk_item perk_type"})
-        job_type = None
-        if job_type_element:
-            job_type_text = (
-                job_type_element.text.strip().lower().replace("_", "").replace(" ", "")
-            )
-            job_type = ZipRecruiterScraper.get_job_type_enum(job_type_text)
-
-        date_posted = ZipRecruiterScraper.get_date_posted(job)
-
-        job_post = JobPost(
-            title=title,
-            description=description,
-            company_name=company,
-            location=ZipRecruiterScraper.get_location(job),
-            job_type=job_type,
-            compensation=ZipRecruiterScraper.get_compensation(job),
-            date_posted=date_posted,
-            job_url=job_url,
-            emails=extract_emails_from_text(description),
-        )
-        return job_post
-
-    def process_job_html_2(self, job: Tag) -> Optional[JobPost]:
-        """
-        Parses a job from the job content tag for a second variat of HTML that ZR uses
-        :param job: BeautifulSoup Tag for one job post
-        :return JobPost
-        """
-        job_url = self.cleanurl(job.find("a", class_="job_link")["href"])
-        title = job.find("h2", class_="title").text
-        company = job.find("a", class_="company_name").text.strip()
-
-        description, updated_job_url = self.get_description(job_url)
-        # job_url = updated_job_url if updated_job_url else job_url
-        if description is None:
-            description = job.find("p", class_="job_snippet").get_text().strip()
-
-        job_type_text = job.find("li", class_="perk_item perk_type")
-        job_type = None
-        if job_type_text:
-            job_type_text = (
-                job_type_text.get_text()
-                .strip()
-                .lower()
-                .replace("-", "")
-                .replace(" ", "")
-            )
-            job_type = ZipRecruiterScraper.get_job_type_enum(job_type_text)
-        date_posted = ZipRecruiterScraper.get_date_posted(job)
-
-        job_post = JobPost(
-            title=title,
-            description=description,
-            company_name=company,
-            location=ZipRecruiterScraper.get_location(job),
-            job_type=job_type,
-            compensation=ZipRecruiterScraper.get_compensation(job),
-            date_posted=date_posted,
-            job_url=job_url,
-        )
-        return job_post
-
     def process_job_javascript(self, job: dict) -> JobPost:
+        """the most common type of jobs page on ZR"""
         title = job.get("Title")
-        job_url = self.cleanurl(job.get("JobURL"))
+        job_url = job.get("JobURL")
 
         description, updated_job_url = self.get_description(job_url)
         # job_url = updated_job_url if updated_job_url else job_url
@@ -275,38 +193,126 @@ class ZipRecruiterScraper(Scraper):
 
         return JobPost(
             title=title,
-            description=description,
             company_name=company,
             location=location,
             job_type=job_type,
             compensation=compensation,
             date_posted=date_posted,
             job_url=job_url,
+            description=description,
+            emails=extract_emails_from_text(description) if description else None,
+            num_urgent_words=count_urgent_words(description) if description else None,
+        )
+
+    def process_job_html_2(self, job: Tag) -> Optional[JobPost]:
+        """
+        second most common type of jobs page on ZR after process_job_javascript()
+        Parses a job from the job content tag for a second variat of HTML that ZR uses
+        :param job: BeautifulSoup Tag for one job post
+        :return JobPost
+        """
+        job_url = job.find("a", class_="job_link")["href"]
+        title = job.find("h2", class_="title").text
+        company = job.find("a", class_="company_name").text.strip()
+
+        description, updated_job_url = self.get_description(job_url)
+        # job_url = updated_job_url if updated_job_url else job_url
+        if description is None:
+            description = job.find("p", class_="job_snippet").get_text().strip()
+
+        job_type_text = job.find("li", class_="perk_item perk_type")
+        job_type = None
+        if job_type_text:
+            job_type_text = (
+                job_type_text.get_text()
+                .strip()
+                .lower()
+                .replace("-", "")
+                .replace(" ", "")
+            )
+            job_type = ZipRecruiterScraper.get_job_type_enum(job_type_text)
+        date_posted = ZipRecruiterScraper.get_date_posted(job)
+
+        job_post = JobPost(
+            title=title,
+            company_name=company,
+            location=ZipRecruiterScraper.get_location(job),
+            job_type=job_type,
+            compensation=ZipRecruiterScraper.get_compensation(job),
+            date_posted=date_posted,
+            job_url=job_url,
+            description=description,
+            emails=extract_emails_from_text(description) if description else None,
+            num_urgent_words=count_urgent_words(description) if description else None,
+        )
+        return job_post
+
+    def process_job_html_1(self, job: Tag) -> Optional[JobPost]:
+        """
+        TODO this method isnt finished due to not encountering this type of html often
+        least common type of jobs page on ZR (rarely found)
+        Parses a job from the job content tag
+        :param job: BeautifulSoup Tag for one job post
+        :return JobPost
+        """
+        job_url = job.find("a", {"class": "job_link"})["href"]
+        # job_url = self.cleanurl(job.find("a", {"class": "job_link"})["href"])
+        if job_url in self.seen_urls:
+            return None
+
+        title = job.find("h2", {"class": "title"}).text
+        company = job.find("a", {"class": "company_name"}).text.strip()
+
+        description, _ = self.get_description(job_url)
+        # job_url = updated_job_url if updated_job_url else job_url
+        # get description from jobs listing page if get_description from the specific job page fails
+        if description is None:
+            description = job.find("p", {"class": "job_snippet"}).text.strip()
+
+        job_type_element = job.find("li", {"class": "perk_item perk_type"})
+        job_type = None
+        if job_type_element:
+            job_type_text = (
+                job_type_element.text.strip().lower().replace("_", "").replace(" ", "")
+            )
+            job_type = ZipRecruiterScraper.get_job_type_enum(job_type_text)
+
+        date_posted = ZipRecruiterScraper.get_date_posted(job)
+
+        job_post = JobPost(
+            title=title,
+            description=description,
+            company_name=company,
+            location=ZipRecruiterScraper.get_location(job),
+            job_type=job_type,
+            compensation=ZipRecruiterScraper.get_compensation(job),
+            date_posted=date_posted,
+            job_url=job_url,
+            emails=extract_emails_from_text(description),
+            num_urgent_words=count_urgent_words(description),
         )
         return job_post
 
     @staticmethod
-    def get_job_type_enum(job_type_str: str) -> Optional[JobType]:
+    def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
         for job_type in JobType:
             if job_type_str in job_type.value:
-                a = True
-                return job_type
+                return [job_type]
         return None
 
-    def get_description(self, job_page_url: str) -> Tuple[Optional[str], Optional[str]]:
+    def get_description(self, job_page_url: str) -> Tuple[str | None, str | None]:
         """
         Retrieves job description by going to the job page url
         :param job_page_url:
-        :param session:
         :return: description or None, response url
         """
         try:
-            response = requests.get(
+            session = create_session(self.proxy)
+            response = session.get(
                 job_page_url,
-                headers=ZipRecruiterScraper.headers(),
+                headers=self.headers(),
                 allow_redirects=True,
-                timeout=5,
-                proxies=self.proxy,
+                timeout_seconds=5,
             )
             if response.status_code not in range(200, 400):
                 return None, None
@@ -462,8 +468,8 @@ class ZipRecruiterScraper(Scraper):
             "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.97 Safari/537.36"
         }
 
-    @staticmethod
-    def cleanurl(url):
-        parsed_url = urlparse(url)
-
-        return urlunparse((parsed_url.scheme, parsed_url.netloc, parsed_url.path, parsed_url.params, '', ''))
+    # @staticmethod
+    # def cleanurl(url) -> str:
+    #     parsed_url = urlparse(url)
+    #
+    #     return urlunparse((parsed_url.scheme, parsed_url.netloc, parsed_url.path, parsed_url.params, '', ''))

src/jobspy/utils.py

@@ -1,9 +0,0 @@
-import re
-from typing import Optional
-
-
-def extract_emails_from_text(text: str) -> Optional[list[str]]:
-    if not text:
-        return None
-    email_regex = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")
-    return email_regex.findall(text)

src/tests/test_all.py

@@ -9,4 +9,6 @@ def test_all():
         results_wanted=5,
     )
 
-    assert isinstance(result, pd.DataFrame) and not result.empty, "Result should be a non-empty DataFrame"
+    assert (
+        isinstance(result, pd.DataFrame) and not result.empty
+    ), "Result should be a non-empty DataFrame"

src/tests/test_indeed.py

@@ -7,4 +7,6 @@ def test_indeed():
         site_name="indeed",
         search_term="software engineer",
     )
-    assert isinstance(result, pd.DataFrame) and not result.empty, "Result should be a non-empty DataFrame"
+    assert (
+        isinstance(result, pd.DataFrame) and not result.empty
+    ), "Result should be a non-empty DataFrame"

src/tests/test_linkedin.py

@@ -7,4 +7,6 @@ def test_linkedin():
         site_name="linkedin",
         search_term="software engineer",
     )
-    assert isinstance(result, pd.DataFrame) and not result.empty, "Result should be a non-empty DataFrame"
+    assert (
+        isinstance(result, pd.DataFrame) and not result.empty
+    ), "Result should be a non-empty DataFrame"

src/tests/test_ziprecruiter.py

@@ -8,4 +8,6 @@ def test_ziprecruiter():
         search_term="software engineer",
     )
 
-    assert isinstance(result, pd.DataFrame) and not result.empty, "Result should be a non-empty DataFrame"
+    assert (
+        isinstance(result, pd.DataFrame) and not result.empty
+    ), "Result should be a non-empty DataFrame"