pass test

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "python-jobspy"
-version = "1.1.72"
+version = "1.1.70"
 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"
@@ -19,7 +19,7 @@ pandas = "^2.1.0"
 NUMPY = "1.26.3"
 pydantic = "^2.3.0"
 tls-client = "^1.0.1"
-markdownify = "^0.13.1"
+markdownify = "^0.11.6"
 regex = "^2024.4.28"
 
 

src/jobspy/scrapers/indeed/__init__.py

@@ -69,8 +69,15 @@ class IndeedScraper(Scraper):
         page = 1
 
         cursor = None
+        offset_pages = math.ceil(self.scraper_input.offset / 100)
+        for _ in range(offset_pages):
+            logger.info(f"skipping search page: {page}")
+            __, cursor = self._scrape_page(cursor)
+            if not __:
+                logger.info(f"found no jobs on page: {page}")
+                break
 
-        while len(self.seen_urls) < scraper_input.results_wanted + scraper_input.offset:
+        while len(self.seen_urls) < scraper_input.results_wanted:
             logger.info(
                 f"search page: {page} / {math.ceil(scraper_input.results_wanted / 100)}"
             )
@@ -80,12 +87,7 @@ class IndeedScraper(Scraper):
                 break
             job_list += jobs
             page += 1
-        return JobResponse(
-            jobs=job_list[
-                scraper_input.offset : scraper_input.offset
-                + scraper_input.results_wanted
-            ]
-        )
+        return JobResponse(jobs=job_list[: scraper_input.results_wanted])
 
     def _scrape_page(self, cursor: str | None) -> Tuple[list[JobPost], str | None]:
         """