chore: version

README.md

@@ -7,9 +7,6 @@
 *Looking to build a data-focused software product?* **[Book a call](https://bunsly.com/)** *to
 work with us.*
 
-Check out another project we wrote: ***[HomeHarvest](https://github.com/Bunsly/HomeHarvest)** – a Python package
-for real estate scraping*
-
 ## Features
 
 - Scrapes job postings from **LinkedIn**, **Indeed**, **Glassdoor**, & **ZipRecruiter** simultaneously

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.27"
+version = "1.1.32"
 description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/Bunsly/JobSpy"

src/jobspy/jobs/__init__.py

@@ -55,18 +55,24 @@ class JobType(Enum):
 
 
 class Country(Enum):
-    ARGENTINA = ("argentina", "com.ar")
+    """
+    Gets the subdomain for Indeed and Glassdoor.
+    The second item in the tuple is the subdomain for Indeed
+    The third item in the tuple is the subdomain (and tld if there's a ':' separator) for Glassdoor
+    """
+
+    ARGENTINA = ("argentina", "ar", "com.ar")
     AUSTRALIA = ("australia", "au", "com.au")
     AUSTRIA = ("austria", "at", "at")
     BAHRAIN = ("bahrain", "bh")
-    BELGIUM = ("belgium", "be", "nl:be")
+    BELGIUM = ("belgium", "be", "fr:be")
     BRAZIL = ("brazil", "br", "com.br")
     CANADA = ("canada", "ca", "ca")
     CHILE = ("chile", "cl")
     CHINA = ("china", "cn")
     COLOMBIA = ("colombia", "co")
     COSTARICA = ("costa rica", "cr")
-    CZECHREPUBLIC = ("czech republic", "cz")
+    CZECHREPUBLIC = ("czech republic,czechia", "cz")
     DENMARK = ("denmark", "dk")
     ECUADOR = ("ecuador", "ec")
     EGYPT = ("egypt", "eg")
@@ -112,8 +118,8 @@ class Country(Enum):
     TURKEY = ("turkey", "tr")
     UKRAINE = ("ukraine", "ua")
     UNITEDARABEMIRATES = ("united arab emirates", "ae")
-    UK = ("uk", "uk", "co.uk")
+    UK = ("uk,united kingdom", "uk", "co.uk")
-    USA = ("usa", "www", "com")
+    USA = ("usa,us,united states", "www", "com")
     URUGUAY = ("uruguay", "uy")
     VENEZUELA = ("venezuela", "ve")
     VIETNAM = ("vietnam", "vn")
@@ -121,7 +127,7 @@ class Country(Enum):
     # internal for ziprecruiter
     US_CANADA = ("usa/ca", "www")
 
-    # internal for linkeind
+    # internal for linkedin
     WORLDWIDE = ("worldwide", "www")
 
     @property
@@ -147,7 +153,8 @@ class Country(Enum):
         """Convert a string to the corresponding Country enum."""
         country_str = country_str.strip().lower()
         for country in cls:
-            if country.value[0] == country_str:
+            country_names = country.value[0].split(',')
+            if country_str in country_names:
                 return country
         valid_countries = [country.value for country in cls]
         raise ValueError(
@@ -167,10 +174,13 @@ class Location(BaseModel):
         if self.state:
             location_parts.append(self.state)
         if self.country and self.country not in (Country.US_CANADA, Country.WORLDWIDE):
-            if self.country.value[0] in ("usa", "uk"):
+            country_name = self.country.value[0]
-                location_parts.append(self.country.value[0].upper())
+            if "," in country_name:
+                country_name = country_name.split(",")[0]
+            if country_name in ("usa", "uk"):
+                location_parts.append(country_name.upper())
             else:
-                location_parts.append(self.country.value[0].title())
+                location_parts.append(country_name.title())
         return ", ".join(location_parts)
 
 
@@ -181,6 +191,10 @@ class CompensationInterval(Enum):
     DAILY = "daily"
     HOURLY = "hourly"
 
+    @classmethod
+    def get_interval(cls, pay_period):
+        return cls[pay_period].value if pay_period in cls.__members__ else None
+
 
 class Compensation(BaseModel):
     interval: Optional[CompensationInterval] = None

src/jobspy/scrapers/glassdoor/__init__.py

@@ -4,17 +4,13 @@ jobspy.scrapers.glassdoor
 
 This module contains routines to scrape Glassdoor.
 """
-import math
-import time
-import re
 import json
-from datetime import datetime, date
+from typing import Optional, Any
-from typing import Optional, Tuple, Any
+from datetime import datetime, timedelta
-from bs4 import BeautifulSoup
 
 from .. import Scraper, ScraperInput, Site
 from ..exceptions import GlassdoorException
-from ..utils import count_urgent_words, extract_emails_from_text, create_session
+from ..utils import create_session
 from ...jobs import (
     JobPost,
     Compensation,
@@ -22,7 +18,6 @@ from ...jobs import (
     Location,
     JobResponse,
     JobType,
-    Country,
 )
 
 
@@ -31,7 +26,7 @@ class GlassdoorScraper(Scraper):
         """
         Initializes GlassdoorScraper with the Glassdoor job search url
         """
-        site = Site(Site.ZIP_RECRUITER)
+        site = Site(Site.GLASSDOOR)
         super().__init__(site, proxy=proxy)
 
         self.url = None
@@ -49,15 +44,12 @@ class GlassdoorScraper(Scraper):
     ) -> (list[JobPost], str | None):
         """
         Scrapes a page of Glassdoor for jobs with scraper_input criteria
-        :param scraper_input:
-        :return: jobs found on page
-        :return: cursor for next page
         """
         try:
             payload = self.add_payload(
                 scraper_input, location_id, location_type, page_num, cursor
             )
-            session = create_session(self.proxy, is_tls=False)
+            session = create_session(self.proxy, is_tls=False, has_retry=True)
             response = session.post(
                 f"{self.url}/graph", headers=self.headers(), timeout=10, data=payload
             )
@@ -86,8 +78,9 @@ class GlassdoorScraper(Scraper):
             company_name = job["header"]["employerNameFromSearch"]
             location_name = job["header"].get("locationName", "")
             location_type = job["header"].get("locationType", "")
-            is_remote = False
+            age_in_days = job["header"].get("ageInDays")
-            location = None
+            is_remote, location = False, None
+            date_posted = (datetime.now() - timedelta(days=age_in_days)).date() if age_in_days else None
 
             if location_type == "S":
                 is_remote = True
@@ -99,10 +92,11 @@ class GlassdoorScraper(Scraper):
             job = JobPost(
                 title=title,
                 company_name=company_name,
+                date_posted=date_posted,
                 job_url=job_url,
                 location=location,
                 compensation=compensation,
-                is_remote=is_remote,
+                is_remote=is_remote
             )
             jobs.append(job)
 
@@ -161,15 +155,8 @@ class GlassdoorScraper(Scraper):
         interval = None
         if pay_period == "ANNUAL":
             interval = CompensationInterval.YEARLY
-        elif pay_period == "MONTHLY":
+        elif pay_period:
-            interval = CompensationInterval.MONTHLY
+            interval = CompensationInterval.get_interval(pay_period)
-        elif pay_period == "WEEKLY":
-            interval = CompensationInterval.WEEKLY
-        elif pay_period == "DAILY":
-            interval = CompensationInterval.DAILY
-        elif pay_period == "HOURLY":
-            interval = CompensationInterval.HOURLY
-
         min_amount = int(adjusted_pay.get("p10") // 1)
         max_amount = int(adjusted_pay.get("p90") // 1)
 
@@ -180,17 +167,11 @@ class GlassdoorScraper(Scraper):
             currency=currency,
         )
 
-    def get_job_type_enum(self, job_type_str: str) -> list[JobType] | None:
-        for job_type in JobType:
-            if job_type_str in job_type.value:
-                return [job_type]
-        return None
-
     def get_location(self, location: str, is_remote: bool) -> (int, str):
         if not location or is_remote:
             return "11047", "STATE"  # remote options
         url = f"{self.url}/findPopularLocationAjax.htm?maxLocationsToReturn=10&term={location}"
-        session = create_session(self.proxy)
+        session = create_session(self.proxy, has_retry=True)
         response = session.get(url)
         if response.status_code != 200:
             raise GlassdoorException(
@@ -213,7 +194,7 @@ class GlassdoorScraper(Scraper):
         location_type: str,
         page_num: int,
         cursor: str | None = None,
-    ) -> dict[str, str | Any]:
+    ) -> str:
         payload = {
             "operationName": "JobSearchResultsQuery",
             "variables": {
@@ -243,10 +224,17 @@ class GlassdoorScraper(Scraper):
             payload["variables"]["filterParams"].append(
                 {"filterKey": "jobType", "values": filter_value}
             )
-
         return json.dumps([payload])
 
-    def parse_location(self, location_name: str) -> Location:
+    @staticmethod
+    def get_job_type_enum(job_type_str: str) -> list[JobType] | None:
+        for job_type in JobType:
+            if job_type_str in job_type.value:
+                return [job_type]
+        return None
+
+    @staticmethod
+    def parse_location(location_name: str) -> Location:
         if not location_name or location_name == "Remote":
             return None
         city, _, state = location_name.partition(", ")

src/jobspy/scrapers/indeed/__init__.py

@@ -64,6 +64,7 @@ class IndeedScraper(Scraper):
             "l": scraper_input.location,
             "filter": 0,
             "start": scraper_input.offset + page * 10,
+            "sort": "date"
         }
         if scraper_input.distance:
             params["radius"] = scraper_input.distance
@@ -150,6 +151,7 @@ class IndeedScraper(Scraper):
                 title=job["normTitle"],
                 description=description,
                 company_name=job["company"],
+                company_url=self.url + job["companyOverviewLink"] if "companyOverviewLink" in job else None,
                 location=Location(
                     city=job.get("jobLocationCity"),
                     state=job.get("jobLocationState"),
@@ -235,24 +237,9 @@ class IndeedScraper(Scraper):
         if response.status_code not in range(200, 400):
             return None
 
-        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"][
+            data = json.loads(response.text)
+            job_description = data["body"]["jobInfoWrapperModel"]["jobInfoModel"][
                 "sanitizedJobDescription"
             ]
         except (KeyError, TypeError, IndexError):
@@ -320,7 +307,7 @@ class IndeedScraper(Scraper):
                 raise IndeedException("Could not find mosaic provider job cards data")
         else:
             raise IndeedException(
-                "Could not find a script tag containing mosaic provider data"
+                "Could not find any results for the search"
             )
 
     @staticmethod

src/jobspy/scrapers/linkedin/__init__.py

@@ -4,6 +4,7 @@ jobspy.scrapers.linkedin
 
 This module contains routines to scrape LinkedIn.
 """
+import random
 from typing import Optional
 from datetime import datetime
 
@@ -16,14 +17,14 @@ from threading import Lock
 from urllib.parse import urlparse, urlunparse
 
 from .. import Scraper, ScraperInput, Site
-from ..utils import count_urgent_words, extract_emails_from_text, get_enum_from_job_type, currency_parser
 from ..exceptions import LinkedInException
+from ..utils import create_session
 from ...jobs import JobPost, Location, JobResponse, JobType, Country, Compensation
+from ..utils import count_urgent_words, extract_emails_from_text, get_enum_from_job_type, currency_parser
 
 
 class LinkedInScraper(Scraper):
-    MAX_RETRIES = 3
+    DELAY = 3
-    DELAY = 10
 
     def __init__(self, proxy: Optional[str] = None):
         """
@@ -57,6 +58,7 @@ class LinkedInScraper(Scraper):
             return mapping.get(job_type_enum, "")
 
         while len(job_list) < scraper_input.results_wanted and page < 1000:
+            session = create_session(is_tls=False, has_retry=True, delay=5)
             params = {
                 "keywords": scraper_input.search_term,
                 "location": scraper_input.location,
@@ -71,40 +73,23 @@ class LinkedInScraper(Scraper):
             }
 
             params = {k: v for k, v in params.items() if v is not None}
-            retries = 0
-            while retries < self.MAX_RETRIES:
             try:
-                    response = requests.get(
+                response = session.get(
                     f"{self.url}/jobs-guest/jobs/api/seeMoreJobPostings/search?",
                     params=params,
                     allow_redirects=True,
                     proxies=self.proxy,
+                    headers=self.headers(),
                     timeout=10,
                 )
                 response.raise_for_status()
 
-                    break
             except requests.HTTPError as e:
-                    if hasattr(e, "response") and e.response is not None:
+                raise LinkedInException(f"bad response status code: {e.response.status_code}")
-                        if e.response.status_code in (429, 502):
-                            time.sleep(self.DELAY)
-                            retries += 1
-                            continue
-                        else:
-                            raise LinkedInException(
-                                f"bad response status code: {e.response.status_code}"
-                            )
-                    else:
-                        raise
             except ProxyError as e:
                 raise LinkedInException("bad proxy")
             except Exception as e:
                 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"
-                )
 
             soup = BeautifulSoup(response.text, "html.parser")
 
@@ -130,6 +115,7 @@ class LinkedInScraper(Scraper):
                     raise LinkedInException("Exception occurred while processing jobs")
 
             page += 25
+            time.sleep(random.uniform(LinkedInScraper.DELAY, LinkedInScraper.DELAY + 2))
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
@@ -181,22 +167,22 @@ class LinkedInScraper(Scraper):
         benefits_tag = job_card.find("span", class_="result-benefits__text")
         benefits = " ".join(benefits_tag.get_text().split()) if benefits_tag else None
 
-        description, job_type = self.get_job_description(job_url)
+        # removed to speed up scraping
-        # description, job_type = None, []
+        # description, job_type = self.get_job_description(job_url)
 
         return JobPost(
             title=title,
-            description=description,
             company_name=company,
             company_url=company_url,
             location=location,
             date_posted=date_posted,
             job_url=job_url,
-            job_type=job_type,
             compensation=compensation,
             benefits=benefits,
-            emails=extract_emails_from_text(description) if description else None,
+            # job_type=job_type,
-            num_urgent_words=count_urgent_words(description) if description else None,
+            # description=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(
@@ -208,12 +194,10 @@ class LinkedInScraper(Scraper):
         :return: description or None
         """
         try:
-            response = requests.get(job_page_url, timeout=5, proxies=self.proxy)
+            session = create_session(is_tls=False, has_retry=True)
+            response = session.get(job_page_url, timeout=5, proxies=self.proxy)
             response.raise_for_status()
         except requests.HTTPError as e:
-            if hasattr(e, "response") and e.response is not None:
-                if e.response.status_code in (429, 502):
-                    time.sleep(self.DELAY)
             return None, None
         except Exception as e:
             return None, None
@@ -278,5 +262,30 @@ class LinkedInScraper(Scraper):
                     state=state,
                     country=Country.from_string(self.country),
                 )
+            elif len(parts) == 3:
+                city, state, country = parts
+                location = Location(
+                    city=city,
+                    state=state,
+                    country=Country.from_string(country),
+                )
 
         return location
+
+    @staticmethod
+    def headers() -> dict:
+        return {
+            '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',
+            'sec-ch-ua': '"Not_A Brand";v="8", "Chromium";v="120", "Google Chrome";v="120"',
+            # 'sec-ch-ua-mobile': '?0',
+            # 'sec-ch-ua-platform': '"macOS"',
+            # 'sec-fetch-dest': 'document',
+            # 'sec-fetch-mode': 'navigate',
+            # 'sec-fetch-site': 'none',
+            # '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/120.0.0.0 Safari/537.36'
+        }

src/jobspy/scrapers/utils.py

@@ -1,8 +1,10 @@
 import re
 import numpy as np
 
-import requests
 import tls_client
+import requests
+from requests.adapters import HTTPAdapter, Retry
+
 from ..jobs import JobType
 
 
@@ -27,11 +29,11 @@ def extract_emails_from_text(text: str) -> list[str] | None:
     return email_regex.findall(text)
 
 
-def create_session(proxy: dict | None = None, is_tls: bool = True):
+def create_session(proxy: dict | None = None, is_tls: bool = True, has_retry: bool = False, delay: int = 1) -> requests.Session:
     """
-    Creates a tls client session
+    Creates a requests session with optional tls, proxy, and retry settings.
 
-    :return: A session object with or without proxies.
+    :return: A session object
     """
     if is_tls:
         session = tls_client.Session(
@@ -39,17 +41,21 @@ def create_session(proxy: dict | None = None, is_tls: bool = True):
             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),
-        #     }
     else:
         session = requests.Session()
         session.allow_redirects = True
         if proxy:
             session.proxies.update(proxy)
+        if has_retry:
+            retries = Retry(total=3,
+                            connect=3,
+                            status=3,
+                            status_forcelist=[500, 502, 503, 504, 429],
+                            backoff_factor=delay)
+            adapter = HTTPAdapter(max_retries=retries)
+
+            session.mount('http://', adapter)
+            session.mount('https://', adapter)
 
     return session
 

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -44,12 +44,12 @@ class ZipRecruiterScraper(Scraper):
         if continue_token:
             params["continue"] = continue_token
         try:
-            session = create_session(self.proxy, is_tls=False)
+            session = create_session(self.proxy, is_tls=True)
             response = session.get(
                 f"https://api.ziprecruiter.com/jobs-app/jobs",
                 headers=self.headers(),
                 params=self.add_params(scraper_input),
-                timeout=10,
+                timeout_seconds=10,
             )
             if response.status_code != 200:
                 raise ZipRecruiterException(
@@ -195,17 +195,12 @@ class ZipRecruiterScraper(Scraper):
     @staticmethod
     def headers() -> dict:
         """
-        Returns headers needed for requests
+        Returns headers needed for ZipRecruiter API requests
         :return: dict - Dictionary containing headers
         """
         return {
-            "Host": "api.ziprecruiter.com",
+            'Host': 'api.ziprecruiter.com',
-            "Cookie": "ziprecruiter_browser=018188e0-045b-4ad7-aa50-627a6c3d43aa; ziprecruiter_session=5259b2219bf95b6d2299a1417424bc2edc9f4b38; SplitSV=2016-10-19%3AU2FsdGVkX19f9%2Bx70knxc%2FeR3xXR8lWoTcYfq5QjmLU%3D%0A; __cf_bm=qXim3DtLPbOL83GIp.ddQEOFVFTc1OBGPckiHYxcz3o-1698521532-0-AfUOCkgCZyVbiW1ziUwyefCfzNrJJTTKPYnif1FZGQkT60dMowmSU/Y/lP+WiygkFPW/KbYJmyc+MQSkkad5YygYaARflaRj51abnD+SyF9V; zglobalid=68d49bd5-0326-428e-aba8-8a04b64bc67c.af2d99ff7c03.653d61bb; ziprecruiter_browser=018188e0-045b-4ad7-aa50-627a6c3d43aa; ziprecruiter_session=5259b2219bf95b6d2299a1417424bc2edc9f4b38",
+            'accept': '*/*',
-            "accept": "*/*",
+            'authorization': 'Basic YTBlZjMyZDYtN2I0Yy00MWVkLWEyODMtYTI1NDAzMzI0YTcyOg==',
-            "x-zr-zva-override": "100000000;vid:ZT1huzm_EQlDTVEc",
+            'Cookie': '__cf_bm=DZ7eJOw6lka.Bwy5jLeDqWanaZ8BJlVAwaXrmcbYnxM-1701505132-0-AfGaVIfTA2kJlmleK14o722vbVwpZ+4UxFznsWv+guvzXSpD9KVEy/+pNzvEZUx88yaEShJwGt3/EVjhHirX/ASustKxg47V/aXRd2XIO2QN; zglobalid=61f94830-1990-4130-b222-d9d0e09c7825.57da9ea9581c.656ae86b; ziprecruiter_browser=018188e0-045b-4ad7-aa50-627a6c3d43aa; ziprecruiter_session=5259b2219bf95b6d2299a1417424bc2edc9f4b38; zva=100000000%3Bvid%3AZWroa0x_F1KEeGeU'
-            "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",
         }