enh(li): job function (#160)

Correct initial page offset calculation
Separate page variable from request counter
Fix job offset starting value
Increment offset by number of jobs returned instead of expected value

README.md

@@ -13,9 +13,6 @@ work with us.*
 - Aggregates the job postings in a Pandas DataFrame
 - Proxies support
 
-[Video Guide for JobSpy](https://www.youtube.com/watch?v=RuP1HrAZnxs&pp=ygUgam9icyBzY3JhcGVyIGJvdCBsaW5rZWRpbiBpbmRlZWQ%3D) -
-Updated for release v1.1.3
-
 ![jobspy](https://github.com/cullenwatson/JobSpy/assets/78247585/ec7ef355-05f6-4fd3-8161-a817e31c5c57)
 
 ### Installation
@@ -41,12 +38,12 @@ jobs = scrape_jobs(
     country_indeed='USA',  # only needed for indeed / glassdoor
     
     # linkedin_fetch_description=True # get full description and direct job url for linkedin (slower)
-    # proxies=["Efb5EA8OIk0BQb:wifi;us;@proxy.soax.com:9000", "localhost"],
+    # proxies=["208.195.175.46:65095", "208.195.175.45:65095", "localhost"],
     
 )
 print(f"Found {len(jobs)} jobs")
 print(jobs.head())
-jobs.to_csv("jobs.csv", quoting=csv.QUOTE_NONNUMERIC, escapechar="\\", index=False) # to_xlsx
+jobs.to_csv("jobs.csv", quoting=csv.QUOTE_NONNUMERIC, escapechar="\\", index=False) # to_excel
 ```
 
 ### Output

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.54"
+version = "1.1.55"
 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

@@ -182,6 +182,7 @@ def scrape_jobs(
             "max_amount",
             "currency",
             "is_remote",
+            "job_function",
             "emails",
             "description",
             "company_url",

src/jobspy/jobs/__init__.py

@@ -254,6 +254,9 @@ class JobPost(BaseModel):
     logo_photo_url: str | None = None
     banner_photo_url: str | None = None
 
+    # linkedin only atm
+    job_function: str | None = None
+
 
 class JobResponse(BaseModel):
     jobs: list[JobPost] = []

src/jobspy/scrapers/linkedin/__init__.py

@@ -13,7 +13,6 @@ import regex as re
 from typing import Optional
 from datetime import datetime
 
-from threading import Lock
 from bs4.element import Tag
 from bs4 import BeautifulSoup
 from urllib.parse import urlparse, urlunparse, unquote
@@ -71,8 +70,8 @@ class LinkedInScraper(Scraper):
         self.scraper_input = scraper_input
         job_list: list[JobPost] = []
         seen_urls = set()
-        url_lock = Lock()
-        page = scraper_input.offset // 25 + 25 if scraper_input.offset else 0
+        page = scraper_input.offset // 10 * 10 if scraper_input.offset else 0
+        request_count = 0
         seconds_old = (
             scraper_input.hours_old * 3600 if scraper_input.hours_old else None
         )
@@ -80,7 +79,8 @@ class LinkedInScraper(Scraper):
             lambda: len(job_list) < scraper_input.results_wanted and page < 1000
         )
         while continue_search():
-            logger.info(f"LinkedIn search page: {page // 25 + 1}")
+            request_count += 1
+            logger.info(f"LinkedIn search page: {request_count}")
             params = {
                 "keywords": scraper_input.search_term,
                 "location": scraper_input.location,
@@ -92,7 +92,7 @@ class LinkedInScraper(Scraper):
                     else None
                 ),
                 "pageNum": 0,
-                "start": page + scraper_input.offset,
+                "start": page,
                 "f_AL": "true" if scraper_input.easy_apply else None,
                 "f_C": (
                     ",".join(map(str, scraper_input.linkedin_company_ids))
@@ -140,7 +140,6 @@ class LinkedInScraper(Scraper):
                     job_id = href.split("-")[-1]
                     job_url = f"{self.base_url}/jobs/view/{job_id}"
 
-                with url_lock:
                 if job_url in seen_urls:
                     continue
                 seen_urls.add(job_url)
@@ -156,7 +155,7 @@ class LinkedInScraper(Scraper):
 
             if continue_search():
                 time.sleep(random.uniform(self.delay, self.delay + self.band_delay))
-                page += self.jobs_per_page
+                page += len(job_list)
 
         job_list = job_list[: scraper_input.results_wanted]
         return JobResponse(jobs=job_list)
@@ -225,6 +224,7 @@ class LinkedInScraper(Scraper):
             job_url_direct=job_details.get("job_url_direct"),
             emails=extract_emails_from_text(job_details.get("description")),
             logo_photo_url=job_details.get("logo_photo_url"),
+            job_function=job_details.get("job_function"),
         )
 
     def _get_id(self, url: str):
@@ -248,7 +248,7 @@ class LinkedInScraper(Scraper):
             response.raise_for_status()
         except:
             return {}
-        if response.url == "https://www.linkedin.com/signup":
+        if "linkedin.com/signup" in response.url:
             return {}
 
         soup = BeautifulSoup(response.text, "html.parser")
@@ -267,6 +267,18 @@ class LinkedInScraper(Scraper):
             description = div_content.prettify(formatter="html")
             if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
                 description = markdown_converter(description)
+
+        h3_tag = soup.find(
+            "h3", text=lambda text: text and "Job function" in text.strip()
+        )
+
+        job_function = None
+        if h3_tag:
+            job_function_span = h3_tag.find_next(
+                "span", class_="description__job-criteria-text"
+            )
+            if job_function_span:
+                job_function = job_function_span.text.strip()
         return {
             "description": description,
             "job_type": self._parse_job_type(soup),
@@ -274,6 +286,7 @@ class LinkedInScraper(Scraper):
             "logo_photo_url": soup.find("img", {"class": "artdeco-entity-image"}).get(
                 "data-delayed-url"
             ),
+            "job_function": job_function,
         }
 
     def _get_location(self, metadata_card: Optional[Tag]) -> Location: