Job type

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.43"
+version = "1.1.44"
 description = "Job scraper for LinkedIn, Indeed, Glassdoor & ZipRecruiter"
 authors = ["Zachary Hampton <[email protected]>", "Cullen Watson <[email protected]>"]
 homepage = "https://github.com/Bunsly/JobSpy"

src/jobspy/__init__.py

@@ -192,4 +192,4 @@ def worker(site):
     else:
         jobs_formatted_df = pd.DataFrame()
 
-    return jobs_formatted_df.sort_values(by='date_posted', ascending=False)
+    return jobs_formatted_df.sort_values(by=['site', 'date_posted'], ascending=[True, False])

src/jobspy/scrapers/indeed/__init__.py

@@ -11,7 +11,6 @@
 from typing import Any
 from datetime import datetime
 
-import urllib.parse
 from bs4 import BeautifulSoup
 from bs4.element import Tag
 from concurrent.futures import ThreadPoolExecutor, Future
@@ -22,7 +21,7 @@
     extract_emails_from_text,
     create_session,
     get_enum_from_job_type,
-    modify_and_get_description
+    logger
 )
 from ...jobs import (
     JobPost,
@@ -50,13 +49,14 @@ def __init__(self, proxy: str | None = None):
 
     def scrape_page(
         self, scraper_input: ScraperInput, page: int
-    ) -> tuple[list[JobPost], int]:
+    ) -> list[JobPost]:
         """
         Scrapes a page of Indeed for jobs with scraper_input criteria
         :param scraper_input:
         :param page:
         :return: jobs found on page, total number of jobs found for search
         """
+        job_list = []
         self.country = scraper_input.country
         domain = self.country.indeed_domain_value
         self.url = f"https://{domain}.indeed.com"
@@ -76,14 +76,14 @@ def scrape_page(
                 )
         except Exception as e:
             if "Proxy responded with" in str(e):
-                raise IndeedException("bad proxy")
-            raise IndeedException(str(e))
+                logger.error(f'Indeed: Bad proxy')
+            else:
+                logger.error(f'Indeed: {str(e)}')
+            return job_list
 
         soup = BeautifulSoup(response.content, "html.parser")
-        job_list = []
-        total_num_jobs = IndeedScraper.total_jobs(soup)
         if "did not match any jobs" in response.text:
-            return job_list, total_num_jobs
+            return job_list
 
         jobs = IndeedScraper.parse_jobs(
             soup
@@ -145,15 +145,15 @@ def process_job(job: dict, job_detailed: dict) -> JobPost | None:
 
         job_list = [result.result() for result in job_results if result.result()]
 
-        return job_list, total_num_jobs
+        return job_list
 
     def scrape(self, scraper_input: ScraperInput) -> JobResponse:
         """
         Scrapes Indeed for jobs with scraper_input criteria
         :param scraper_input:
         :return: job_response
         """
-        job_list, total_results = self.scrape_page(scraper_input, 0)
+        job_list = self.scrape_page(scraper_input, 0)
         pages_processed = 1
 
         while len(self.seen_urls) < scraper_input.results_wanted:
@@ -167,7 +167,7 @@ def scrape(self, scraper_input: ScraperInput) -> JobResponse:
                 ]
 
                 for future in futures:
-                    jobs, _ = future.result()
+                    jobs = future.result()
                     if jobs:
                         job_list += jobs
                         new_jobs = True
@@ -182,55 +182,7 @@ def scrape(self, scraper_input: ScraperInput) -> JobResponse:
         if len(self.seen_urls) > scraper_input.results_wanted:
             job_list = job_list[:scraper_input.results_wanted]
 
-        job_response = JobResponse(
-            jobs=job_list,
-            total_results=total_results,
-        )
-        return job_response
-
-    def get_description(self, job_page_url: str) -> str | None:
-        """
-        Retrieves job description by going to the job page url
-        :param job_page_url:
-        :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}/m/viewjob?jk={jk_value}&spa=1"
-        session = create_session(self.proxy)
-
-        try:
-            response = session.get(
-                formatted_url,
-                headers=self.get_headers(),
-                allow_redirects=True,
-                timeout_seconds=5,
-            )
-        except Exception as e:
-            return None
-
-        if response.status_code not in range(200, 400):
-            return None
-
-        try:
-            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
-
-        soup = BeautifulSoup(job_description, "html.parser")
-        return modify_and_get_description(soup)
+        return JobResponse(jobs=job_list)
 
     @staticmethod
     def get_job_type(job: dict) -> list[JobType] | None:
@@ -330,24 +282,6 @@ def find_mosaic_script() -> Tag | None:
                 "Could not find any results for the search"
             )
 
-    @staticmethod
-    def total_jobs(soup: BeautifulSoup) -> int:
-        """
-        Parses the total jobs for that search from soup object
-        :param soup:
-        :return: total_num_jobs
-        """
-        script = soup.find("script", string=lambda t: t and "window._initialData" in t)
-
-        pattern = re.compile(r"window._initialData\s*=\s*({.*})\s*;", re.DOTALL)
-        match = pattern.search(script.string)
-        total_num_jobs = 0
-        if match:
-            json_str = match.group(1)
-            data = json.loads(json_str)
-            total_num_jobs = int(data["searchTitleBarModel"]["totalNumResults"])
-        return total_num_jobs
-
     @staticmethod
     def get_headers():
         return {
@@ -380,7 +314,7 @@ def add_params(scraper_input: ScraperInput, page: int) -> dict[str, str | Any]:
         if scraper_input.is_remote:
             sc_values.append("attr(DSQF7)")
         if scraper_input.job_type:
-            sc_values.append("jt({})".format(scraper_input.job_type.value))
+            sc_values.append("jt({})".format(scraper_input.job_type.value[0]))
 
         if sc_values:
             params["sc"] = "0kf:" + "".join(sc_values) + ";"
@@ -406,7 +340,7 @@ def is_job_remote(job: dict, job_detailed: dict, description: str) -> bool:
             taxonomy["label"] == "remote" and len(taxonomy["attributes"]) > 0
             for taxonomy in job.get("taxonomyAttributes", [])
         )
-        return is_remote_in_attributes or is_remote_in_description or is_remote_in_location
+        return is_remote_in_attributes or is_remote_in_description or is_remote_in_location or is_remote_in_taxonomy
 
     def get_job_details(self, job_keys: list[str]) -> dict:
         """

src/jobspy/scrapers/linkedin/__init__.py

@@ -31,8 +31,7 @@
     count_urgent_words,
     extract_emails_from_text,
     get_enum_from_job_type,
-    currency_parser,
-    modify_and_get_description
+    currency_parser
 )
 
 
@@ -236,10 +235,15 @@ def get_job_description(
         div_content = soup.find(
             "div", class_=lambda x: x and "show-more-less-html__markup" in x
         )
-
         description = None
-        if div_content:
-            description = modify_and_get_description(div_content)
+        if div_content is not None:
+            def remove_attributes(tag):
+                for attr in list(tag.attrs):
+                    del tag[attr]
+                return tag
+
+            div_content = remove_attributes(div_content)
+            description = div_content.prettify(formatter="html")
 
         def get_job_type(
             soup_job_type: BeautifulSoup,

src/jobspy/scrapers/utils.py

@@ -1,4 +1,5 @@
 import re
+import logging
 import numpy as np
 
 import tls_client
@@ -7,14 +8,14 @@
 
 from ..jobs import JobType
 
-
-def modify_and_get_description(soup):
-    for li in soup.find_all('li'):
-        li.string = "- " + li.get_text()
-
-    description = soup.get_text(separator='\n').strip()
-    description = re.sub(r'\n+', '\n', description)
-    return description
+logger = logging.getLogger("JobSpy")
+if not logger.handlers:
+    logger.setLevel(logging.ERROR)
+    console_handler = logging.StreamHandler()
+    console_handler.setLevel(logging.ERROR)
+    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+    console_handler.setFormatter(formatter)
+    logger.addHandler(console_handler)
 
 
 def count_urgent_words(description: str) -> int:
@@ -79,6 +80,7 @@ def get_enum_from_job_type(job_type_str: str) -> JobType | None:
             res = job_type
     return res
 
+
 def currency_parser(cur_str):
     # Remove any non-numerical characters
     # except for ',' '.' or '-' (e.g. EUR)
@@ -94,3 +96,5 @@ def currency_parser(cur_str):
         num = float(cur_str)
 
     return np.round(num, 2)
+
+

src/jobspy/scrapers/ziprecruiter/__init__.py

@@ -9,13 +9,12 @@
 from datetime import datetime, timezone
 from typing import Optional, Tuple, Any
 
-from bs4 import BeautifulSoup
 from concurrent.futures import ThreadPoolExecutor
 
 from .. import Scraper, ScraperInput, Site
 from ..exceptions import ZipRecruiterException
 from ...jobs import JobPost, Compensation, Location, JobResponse, JobType, Country
-from ..utils import count_urgent_words, extract_emails_from_text, create_session, modify_and_get_description
+from ..utils import count_urgent_words, extract_emails_from_text, create_session
 
 
 class ZipRecruiterScraper(Scraper):
@@ -107,9 +106,7 @@ def process_job(self, job: dict) -> JobPost | None:
             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)
+        description = job.get("job_description", "").strip()
 
         company = job.get("hiring_company", {}).get("name")
         country_value = "usa" if job.get("job_country") == "US" else "canada"
@@ -168,25 +165,16 @@ def add_params(scraper_input) -> dict[str, str | Any]:
         if scraper_input.hours_old:
             fromage = max(scraper_input.hours_old // 24, 1) if scraper_input.hours_old else None
             params['days'] = fromage
-        job_type_value = None
+        job_type_map = {
+            JobType.FULL_TIME: 'full_time',
+            JobType.PART_TIME: 'part_time'
+        }
         if scraper_input.job_type:
-            if scraper_input.job_type.value == "fulltime":
-                job_type_value = "full_time"
-            elif scraper_input.job_type.value == "parttime":
-                job_type_value = "part_time"
-            else:
-                job_type_value = scraper_input.job_type.value
+            params['employment_type'] = job_type_map[scraper_input.job_type] if scraper_input.job_type in job_type_map else scraper_input.job_type.value[0]
         if scraper_input.easy_apply:
             params['zipapply'] = 1
-
-        if job_type_value:
-            params[
-                "refine_by_employment"
-            ] = f"employment_type:employment_type:{job_type_value}"
-
         if scraper_input.is_remote:
-            params["refine_by_location_type"] = "only_remote"
-
+            params["remote"] = 1
         if scraper_input.distance:
             params["radius"] = scraper_input.distance