docs: readme

* fix(ziprecruiter): pagination

* chore: version

README.md

@@ -70,6 +70,7 @@ Optional
 ├── full_description (bool): fetches full description for Indeed / LinkedIn (much slower)
 ├── 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 the job board site
+├── linkedin_company_ids (list[int): searches for linkedin jobs with specific company ids
 ├── country_indeed (enum): filters the country on Indeed (see below for correct spelling)
 ├── offset (num): starts the search from an offset (e.g. 25 will start the search from the 25th result)
 ```
@@ -80,6 +81,7 @@ Optional
 JobPost
 ├── title (str)
 ├── company (str)
+├── company_url (str)
 ├── job_url (str)
 ├── location (object)
 │   ├── country (str)
@@ -158,16 +160,11 @@ persist, [submit an issue](https://github.com/Bunsly/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. All of the job board sites are aggressive with blocking. We recommend:
 
-- Waiting a few seconds between requests.
+- Waiting some time between scrapes (site-dependent).
 - Trying a VPN or proxy to change your IP address.
 
 ---
 
-**Q: Experiencing a "Segmentation fault: 11" on macOS Catalina?**  
-**A:** This is due to `tls_client` dependency not supporting your architecture. Solutions and workarounds include:
-
-- Upgrade to a newer version of MacOS
-- Reach out to the maintainers of [tls_client](https://github.com/bogdanfinn/tls-client) for fixes
 
 
   

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.38"
+version = "1.1.42"
 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/__init__.py

@@ -1,7 +1,7 @@
 import pandas as pd
+from typing import Tuple
 import concurrent.futures
 from concurrent.futures import ThreadPoolExecutor
-from typing import Tuple, Optional
 
 from .jobs import JobType, Location
 from .scrapers.indeed import IndeedScraper
@@ -29,19 +29,20 @@ def _map_str_to_site(site_name: str) -> Site:
 
 
 def scrape_jobs(
-    site_name: str | list[str] | Site | list[Site],
-    search_term: str,
-    location: str = "",
-    distance: int = None,
+    site_name: str | list[str] | Site | list[Site] | None = None,
+    search_term: str | None = None,
+    location: str | None = None,
+    distance: int | None = None,
     is_remote: bool = False,
-    job_type: str = None,
-    easy_apply: bool = False,  # linkedin
+    job_type: str | None = None,
+    easy_apply: bool | None = None,
     results_wanted: int = 15,
     country_indeed: str = "usa",
     hyperlinks: bool = False,
-    proxy: Optional[str] = None,
-    full_description: Optional[bool] = False,
-    offset: Optional[int] = 0,
+    proxy: str | None = None,
+    full_description: bool | None = False,
+    linkedin_company_ids: list[int] | None = None,
+    offset: int | None = 0,
 ) -> pd.DataFrame:
     """
     Simultaneously scrapes job data from multiple job sites.
@@ -56,18 +57,23 @@ def scrape_jobs(
 
     job_type = get_enum_from_value(job_type) if job_type else None
 
-    if type(site_name) == str:
-        site_type = [_map_str_to_site(site_name)]
-    else:  #: if type(site_name) == list
-        site_type = [
-            _map_str_to_site(site) if type(site) == str else site_name
+    def get_site_type():
+        site_types = list(Site)
+        if isinstance(site_name, str):
+            site_types = [_map_str_to_site(site_name)]
+        elif isinstance(site_name, Site):
+            site_types = [site_name]
+        elif isinstance(site_name, list):
+            site_types = [
+                _map_str_to_site(site) if isinstance(site, str) else site
                 for site in site_name
             ]
+        return site_types
 
     country_enum = Country.from_string(country_indeed)
 
     scraper_input = ScraperInput(
-        site_type=site_type,
+        site_type=get_site_type(),
         country=country_enum,
         search_term=search_term,
         location=location,
@@ -77,6 +83,7 @@ def scrape_jobs(
         easy_apply=easy_apply,
         full_description=full_description,
         results_wanted=results_wanted,
+        linkedin_company_ids=linkedin_company_ids,
         offset=offset,
     )
 

src/jobspy/scrapers/__init__.py

@@ -1,5 +1,4 @@
 from ..jobs import Enum, BaseModel, JobType, JobResponse, Country
-from typing import List, Optional, Any
 
 
 class Site(Enum):
@@ -10,23 +9,24 @@ class Site(Enum):
 
 
 class ScraperInput(BaseModel):
-    site_type: List[Site]
-    search_term: str
+    site_type: list[Site]
+    search_term: str | None = None
 
-    location: str = None
-    country: Optional[Country] = Country.USA
-    distance: Optional[int] = None
+    location: str | None = None
+    country: Country | None = Country.USA
+    distance: int | None = None
     is_remote: bool = False
-    job_type: Optional[JobType] = None
-    easy_apply: bool = None  # linkedin
+    job_type: JobType | None = None
+    easy_apply: bool | None = None
     full_description: bool = False
     offset: int = 0
+    linkedin_company_ids: list[int] | None = None
 
     results_wanted: int = 15
 
 
 class Scraper:
-    def __init__(self, site: Site, proxy: Optional[List[str]] = None):
+    def __init__(self, site: Site, proxy: list[str] | None = None):
         self.site = site
         self.proxy = (lambda p: {"http": p, "https": p} if p else None)(proxy)
 

src/jobspy/scrapers/glassdoor/__init__.py

@@ -246,6 +246,8 @@ class GlassdoorScraper(Scraper):
             location_type = "CITY"
         elif location_type == "S":
             location_type = "STATE"
+        elif location_type == 'N':
+            location_type = "COUNTRY"
         return int(items[0]["locationId"]), location_type
 
     @staticmethod

src/jobspy/scrapers/indeed/__init__.py

@@ -154,8 +154,9 @@ class IndeedScraper(Scraper):
             )
             return job_post
 
+        workers = 10 if scraper_input.full_description else 10  # possibly lessen 10 when fetching desc based on feedback
         jobs = jobs["metaData"]["mosaicProviderJobCardsModel"]["results"]
-        with ThreadPoolExecutor(max_workers=1) as executor:
+        with ThreadPoolExecutor(max_workers=workers) as executor:
             job_results: list[Future] = [
                 executor.submit(process_job, job) for job in jobs
             ]
@@ -206,7 +207,7 @@ class IndeedScraper(Scraper):
         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"
+        formatted_url = f"{self.url}/m/viewjob?jk={jk_value}&spa=1"
         session = create_session(self.proxy)
 
         try:
@@ -223,10 +224,18 @@ class IndeedScraper(Scraper):
             return None
 
         try:
-            data = json.loads(response.text)
-            job_description = data["body"]["jobInfoWrapperModel"]["jobInfoModel"][
-                "sanitizedJobDescription"
-            ]
+            soup = BeautifulSoup(response.text, 'html.parser')
+            script_tags = soup.find_all('script')
+
+            job_description = ''
+            for tag in script_tags:
+                if 'window._initialData' in tag.text:
+                    json_str = tag.text
+                    json_str = json_str.split('window._initialData=')[1]
+                    json_str = json_str.rsplit(';', 1)[0]
+                    data = json.loads(json_str)
+                    job_description = data["jobInfoWrapperModel"]["jobInfoModel"]["sanitizedJobDescription"]
+                    break
         except (KeyError, TypeError, IndexError):
             return None
 
@@ -339,7 +348,7 @@ class IndeedScraper(Scraper):
     def add_params(scraper_input: ScraperInput, page: int) -> dict[str, str | Any]:
         params = {
             "q": scraper_input.search_term,
-            "l": scraper_input.location,
+            "l": scraper_input.location if scraper_input.location else scraper_input.country.value[0].split(',')[-1],
             "filter": 0,
             "start": scraper_input.offset + page * 10,
             "sort": "date"

src/jobspy/scrapers/linkedin/__init__.py

@@ -70,7 +70,9 @@ class LinkedInScraper(Scraper):
 
             return mapping.get(job_type_enum, "")
 
-        while len(job_list) < scraper_input.results_wanted and page < 1000:
+        continue_search = lambda: len(job_list) < scraper_input.results_wanted and page < 1000
+
+        while continue_search():
             session = create_session(is_tls=False, has_retry=True, delay=5)
             params = {
                 "keywords": scraper_input.search_term,
@@ -83,6 +85,7 @@ class LinkedInScraper(Scraper):
                 "pageNum": 0,
                 "start": page + scraper_input.offset,
                 "f_AL": "true" if scraper_input.easy_apply else None,
+                "f_C": ','.join(map(str, scraper_input.linkedin_company_ids)) if scraper_input.linkedin_company_ids else None
             }
 
             params = {k: v for k, v in params.items() if v is not None}
@@ -130,8 +133,9 @@ class LinkedInScraper(Scraper):
                 except Exception as e:
                     raise LinkedInException("Exception occurred while processing jobs")
 
-            page += 25
+            if continue_search():
                 time.sleep(random.uniform(LinkedInScraper.DELAY, LinkedInScraper.DELAY + 2))
+                page += 25
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -6,8 +6,7 @@ This module contains routines to scrape ZipRecruiter.
 """
 import math
 import time
-import re
-from datetime import datetime, date
+from datetime import datetime, timezone
 from typing import Optional, Tuple, Any
 
 from bs4 import BeautifulSoup
@@ -32,6 +31,7 @@ class ZipRecruiterScraper(Scraper):
 
         self.jobs_per_page = 20
         self.seen_urls = set()
+        self.delay = 5
 
     def find_jobs_in_page(
         self, scraper_input: ScraperInput, continue_token: str | None = None
@@ -44,12 +44,12 @@ class ZipRecruiterScraper(Scraper):
         """
         params = self.add_params(scraper_input)
         if continue_token:
-            params["continue"] = continue_token
+            params["continue_from"] = continue_token
         try:
             response = self.session.get(
                 f"https://api.ziprecruiter.com/jobs-app/jobs",
                 headers=self.headers(),
-                params=self.add_params(scraper_input),
+                params=params
             )
             if response.status_code != 200:
                 raise ZipRecruiterException(
@@ -60,7 +60,6 @@ class ZipRecruiterScraper(Scraper):
                 raise ZipRecruiterException("bad proxy")
             raise ZipRecruiterException(str(e))
 
-        time.sleep(5)
         response_data = response.json()
         jobs_list = response_data.get("jobs", [])
         next_continue_token = response_data.get("continue", None)
@@ -68,7 +67,7 @@ class ZipRecruiterScraper(Scraper):
         with ThreadPoolExecutor(max_workers=self.jobs_per_page) as executor:
             job_results = [executor.submit(self.process_job, job) for job in jobs_list]
 
-        job_list = [result.result() for result in job_results if result.result()]
+        job_list = list(filter(None, (result.result() for result in job_results)))
         return job_list, next_continue_token
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
@@ -86,6 +85,9 @@ class ZipRecruiterScraper(Scraper):
             if len(job_list) >= scraper_input.results_wanted:
                 break
 
+            if page > 1:
+                time.sleep(self.delay)
+
             jobs_on_page, continue_token = self.find_jobs_in_page(
                 scraper_input, continue_token
             )
@@ -95,22 +97,21 @@ class ZipRecruiterScraper(Scraper):
             if not continue_token:
                 break
 
-        if len(job_list) > scraper_input.results_wanted:
-            job_list = job_list[: scraper_input.results_wanted]
+        return JobResponse(jobs=job_list[: scraper_input.results_wanted])
 
-        return JobResponse(jobs=job_list)
-
-    @staticmethod
-    def process_job(job: dict) -> JobPost:
+    def process_job(self, job: dict) -> JobPost | None:
         """Processes an individual job dict from the response"""
         title = job.get("name")
-        job_url = job.get("job_url")
+        job_url = f"https://www.ziprecruiter.com/jobs//j?lvk={job['listing_key']}"
+        if job_url in self.seen_urls:
+            return
+        self.seen_urls.add(job_url)
 
         job_description_html = job.get("job_description", "").strip()
         description_soup = BeautifulSoup(job_description_html, "html.parser")
         description = modify_and_get_description(description_soup)
 
-        company = job["hiring_company"].get("name") if "hiring_company" in job else None
+        company = job.get("hiring_company", {}).get("name")
         country_value = "usa" if job.get("job_country") == "US" else "canada"
         country_enum = Country.from_string(country_value)
 
@@ -120,17 +121,7 @@ class ZipRecruiterScraper(Scraper):
         job_type = ZipRecruiterScraper.get_job_type_enum(
             job.get("employment_type", "").replace("_", "").lower()
         )
-
-        save_job_url = job.get("SaveJobURL", "")
-        posted_time_match = re.search(
-            r"posted_time=(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z)", save_job_url
-        )
-        if posted_time_match:
-            date_time_str = posted_time_match.group(1)
-            date_posted_obj = datetime.strptime(date_time_str, "%Y-%m-%dT%H:%M:%SZ")
-            date_posted = date_posted_obj.date()
-        else:
-            date_posted = date.today()
+        date_posted = datetime.fromisoformat(job['posted_time'].rstrip("Z")).date()
 
         return JobPost(
             title=title,
@@ -173,7 +164,6 @@ class ZipRecruiterScraper(Scraper):
         params = {
             "search": scraper_input.search_term,
             "location": scraper_input.location,
-            "form": "jobs-landing",
         }
         job_type_value = None
         if scraper_input.job_type:
@@ -197,6 +187,8 @@ class ZipRecruiterScraper(Scraper):
         if scraper_input.distance:
             params["radius"] = scraper_input.distance
 
+        params = {k: v for k, v in params.items() if v is not None}
+
         return params
 
     @staticmethod