Add 6 new dental job site adapters

- ihs: Indian Health Service Dentistry (table, keyword filter)
- gilariver: Gila River Health Care via Infor CloudSuite (Angular, click pagination)
- nativehealth: NATIVE HEALTH via SmartRecruiters (AJAX Show More, keyword filter)
- srpmic: Salt River Pima-Maricopa via GovernmentJobs company page (URL keyword search)
- bfrench: Consulting BFrench via JazzHR (simple table, keyword filter)
- govtjobs: GovernmentJobs.com main search (URL keyword search, URL pagination)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

gimme_job/adapters/bfrench.py

@@ -0,0 +1,58 @@
+"""Consulting BFrench Jobs adapter — JazzHR single-page table, keyword filter."""
+from __future__ import annotations
+
+from loguru import logger
+
+from gimme_job.adapters.base import ManifestDrivenAdapter
+from gimme_job.adapters.registry import register
+from gimme_job.models.dto import JobPostingCandidate, RawJobCard
+
+_KEYWORDS = ["orthodontist", "orthodontic", "dentist"]
+
+
+@register("bfrench")
+class BFrenchAdapter(ManifestDrivenAdapter):
+
+    def collect_cards(self, page, manifest) -> list[RawJobCard]:
+        """Extract all job rows from the table and filter by keywords."""
+        raw_data = page.evaluate("""() => {
+            const links = document.querySelectorAll('a[href*="/apply/jobs/details/"]');
+            return Array.from(links).map(a => {
+                const row = a.closest('tr');
+                const cells = row ? Array.from(row.querySelectorAll('td')) : [];
+                return {
+                    title: a.innerText.trim(),
+                    url: a.href,
+                    location: cells[1]?.innerText?.trim() || null
+                };
+            }).filter(j => j.title);
+        }""")
+
+        cards = []
+        for item in raw_data:
+            if not self._matches_keywords(item["title"]):
+                continue
+            cards.append(RawJobCard(
+                title=item["title"],
+                company="Consulting BFrench",
+                location=item["location"],
+                url=item["url"],
+            ))
+
+        logger.info(
+            f"[bfrench] Keyword filter: {len(cards)}/{len(raw_data)} cards matched"
+        )
+        return cards
+
+    def paginate(self, page, page_index: int, config) -> bool:
+        return False
+
+    def normalize(self, raw: RawJobCard) -> JobPostingCandidate:
+        return super().normalize(raw)
+
+    @staticmethod
+    def _matches_keywords(title: str | None) -> bool:
+        if not title:
+            return False
+        title_lower = title.lower()
+        return any(kw in title_lower for kw in _KEYWORDS)

gimme_job/adapters/gilariver.py

@@ -0,0 +1,104 @@
+"""Gila River Health Care adapter — Infor CloudSuite, keyword search + click pagination."""
+from __future__ import annotations
+
+from loguru import logger
+
+from gimme_job.adapters.base import ManifestDrivenAdapter
+from gimme_job.adapters.registry import register
+from gimme_job.models.dto import JobPostingCandidate, RawJobCard
+
+_SEARCH_KEYWORD = "dent"  # broad match: captures Dentist, Dental, etc.
+_KEYWORDS = ["orthodontist", "orthodontic", "dentist"]
+
+
+@register("gilariver")
+class GilaRiverAdapter(ManifestDrivenAdapter):
+
+    def apply_search(self, page, query) -> None:
+        """Type keyword into search form and submit; wait for filtered results."""
+        try:
+            page.wait_for_selector(
+                ".JobPostingSearchRel_col_KeywordSearch",
+                timeout=15000,
+                state="visible",
+            )
+            kw_input = page.query_selector(".JobPostingSearchRel_col_KeywordSearch")
+            if not kw_input:
+                logger.warning("[gilariver] Keyword input not found")
+                return
+
+            kw_input.click(click_count=3)
+            kw_input.type(_SEARCH_KEYWORD, delay=50)
+            kw_input.press("Enter")
+            page.wait_for_load_state("networkidle", timeout=15000)
+            logger.info(f"[gilariver] Searched for '{_SEARCH_KEYWORD}'")
+        except Exception as e:
+            logger.warning(f"[gilariver] apply_search failed: {e}")
+
+    def collect_cards(self, page, manifest) -> list[RawJobCard]:
+        """Extract cards via JS and filter by keywords in-memory."""
+        raw_data = page.evaluate("""() => {
+            const cards = document.querySelectorAll('.lm-card-content');
+            return Array.from(cards).map(card => {
+                const titleA = card.querySelector('span.lm-card-field.text-strong a');
+                const subtitle = card.querySelector(
+                    'span.lm-card-field:not(.text-strong):not(.text-emphasis)'
+                );
+                const posted = card.querySelector('span.lm-card-field.text-emphasis');
+                return {
+                    title: (titleA?.textContent || '').trim(),
+                    url: titleA?.href || '',
+                    subtitle: (subtitle?.textContent || '').trim(),
+                    posted: (posted?.textContent || '').trim()
+                };
+            }).filter(r => r.title);
+        }""")
+
+        cards = []
+        for item in raw_data:
+            title = item["title"]
+            if not self._matches_keywords(title):
+                continue
+
+            # Subtitle: "Location | Category | Status - Employment Type"
+            parts = [p.strip() for p in item["subtitle"].split("|")]
+            location = parts[0] if parts else None
+
+            cards.append(RawJobCard(
+                title=title,
+                company="Gila River Health Care",
+                location=location or None,
+                posted_text=item["posted"] or None,
+                url=item["url"] or None,
+            ))
+
+        logger.info(
+            f"[gilariver] Keyword filter: {len(cards)}/{len(raw_data)} cards matched"
+        )
+        return cards
+
+    def paginate(self, page, page_index: int, config) -> bool:
+        """Click Next Page button; return False when disabled or missing."""
+        try:
+            buttons = page.query_selector_all("button")
+            next_btn = next(
+                (b for b in buttons if b.inner_text().strip() == "Next Page"), None
+            )
+            if not next_btn or not next_btn.is_enabled():
+                return False
+            next_btn.click()
+            page.wait_for_load_state("networkidle", timeout=15000)
+            return True
+        except Exception as e:
+            logger.debug(f"[gilariver] paginate failed: {e}")
+            return False
+
+    def normalize(self, raw: RawJobCard) -> JobPostingCandidate:
+        return super().normalize(raw)
+
+    @staticmethod
+    def _matches_keywords(title: str | None) -> bool:
+        if not title:
+            return False
+        title_lower = title.lower()
+        return any(kw in title_lower for kw in _KEYWORDS)

gimme_job/adapters/govtjobs.py

@@ -0,0 +1,85 @@
+"""GovernmentJobs.com main search adapter — URL keyword search, URL-based pagination."""
+from __future__ import annotations
+
+import re
+
+from loguru import logger
+
+from gimme_job.adapters.base import ManifestDrivenAdapter
+from gimme_job.adapters.registry import register
+from gimme_job.models.dto import JobPostingCandidate, RawJobCard
+
+
+@register("govtjobs")
+class GovtJobsAdapter(ManifestDrivenAdapter):
+
+    def collect_cards(self, page, manifest) -> list[RawJobCard]:
+        """Extract job cards from the search results page."""
+        raw_data = page.evaluate("""() => {
+            const cards = document.querySelectorAll('h3 a[href*="/jobs/"]');
+            return Array.from(cards).map(a => {
+                const cardDiv = a.closest('h3')?.parentElement;
+                const generics = cardDiv
+                    ? Array.from(cardDiv.children).filter(el => el.tagName !== 'H3')
+                    : [];
+                return {
+                    title: a.innerText.trim(),
+                    url: a.href,
+                    company: generics[0]?.innerText?.trim() || null,
+                    location: generics[1]?.innerText?.trim() || null,
+                    salary: generics[2]?.innerText?.trim() || null
+                };
+            }).filter(j => j.title && j.url.includes('/jobs/'));
+        }""")
+
+        cards = []
+        for item in raw_data:
+            cards.append(RawJobCard(
+                title=item["title"],
+                company=item["company"],
+                location=item["location"],
+                salary_text=item["salary"],
+                url=item["url"],
+            ))
+
+        logger.info(f"[govtjobs] Extracted {len(cards)} cards")
+        return cards
+
+    def paginate(self, page, page_index: int, config) -> bool:
+        """Navigate to next page using URL ?page=N parameter."""
+        has_next = page.evaluate("""() => {
+            const links = Array.from(document.querySelectorAll('a'));
+            const next = links.find(a =>
+                a.textContent.trim() === 'Next' ||
+                (a.getAttribute('aria-label') || '').toLowerCase().includes('next page')
+            );
+            return !!(next && !next.hasAttribute('disabled') &&
+                      next.getAttribute('aria-disabled') !== 'true');
+        }""")
+
+        if not has_next:
+            return False
+
+        next_page_num = page_index + 2  # page_index 0 → go to page 2
+        current_url = page.url
+
+        if re.search(r'[?&]page=\d+', current_url):
+            next_url = re.sub(r'(page=)\d+', f'page={next_page_num}', current_url)
+        elif '?' in current_url:
+            next_url = current_url + f'&page={next_page_num}'
+        else:
+            next_url = current_url + f'?page={next_page_num}'
+
+        logger.debug(f"[govtjobs] Navigating to page {next_page_num}: {next_url}")
+        page.goto(next_url, timeout=30000)
+        try:
+            page.wait_for_selector(
+                "h3 a[href*='/jobs/']", timeout=15000, state="attached"
+            )
+        except Exception:
+            logger.debug("[govtjobs] No jobs found on next page — stopping")
+            return False
+        return True
+
+    def normalize(self, raw: RawJobCard) -> JobPostingCandidate:
+        return super().normalize(raw)

gimme_job/adapters/ihs.py

@@ -0,0 +1,79 @@
+"""Indian Health Service Dentistry adapter — single-page table, keyword post-filter."""
+from __future__ import annotations
+
+import re
+
+from loguru import logger
+
+from gimme_job.adapters.base import ManifestDrivenAdapter
+from gimme_job.adapters.registry import register
+from gimme_job.models.dto import JobPostingCandidate, RawJobCard
+
+_BASE_URL = "https://www.ihs.gov"
+_KEYWORDS = ["orthodontist", "orthodontic", "dentist"]
+
+
+@register("ihs")
+class IHSAdapter(ManifestDrivenAdapter):
+
+    def collect_cards(self, page, manifest):
+        """Extract all rows via JS, combine city+state into location, filter by keywords."""
+        try:
+            page.wait_for_selector("table.cf_grid tbody tr", timeout=15000, state="attached")
+        except Exception:
+            logger.debug("[ihs] Table wait timed out")
+
+        raw_data = page.evaluate("""() => {
+            const rows = document.querySelectorAll('table.cf_grid tbody tr');
+            return Array.from(rows).map(row => {
+                const titleEl = row.querySelector('td:nth-child(2) a');
+                const city = (row.querySelector('td:nth-child(3)')?.textContent || '').trim();
+                const state = (row.querySelector('td:nth-child(4)')?.textContent || '').trim();
+                return {
+                    title: (titleEl?.textContent || '').trim(),
+                    url: titleEl?.getAttribute('href') || '',
+                    city: city,
+                    state: state
+                };
+            }).filter(r => r.title);
+        }""")
+
+        cards = []
+        for item in raw_data:
+            title = item["title"]
+            if not self._matches_keywords(title):
+                continue
+
+            # Strip HPSA score prefix: "(N-HPSA Score) CityName" → "CityName"
+            city = re.sub(r"^\([^)]+\)\s*", "", item["city"])
+            location = f"{city}, {item['state']}".strip(", ")
+
+            url = item["url"]
+            if url.startswith("/"):
+                url = _BASE_URL + url
+
+            cards.append(RawJobCard(
+                title=title,
+                company="Indian Health Service",
+                location=location or None,
+                url=url or None,
+            ))
+
+        logger.info(
+            f"[ihs] Keyword filter: {len(cards)}/{len(raw_data)} cards matched"
+        )
+        return cards
+
+    def paginate(self, page, page_index: int, config) -> bool:
+        """Single page — no pagination."""
+        return False
+
+    def normalize(self, raw: RawJobCard) -> JobPostingCandidate:
+        return super().normalize(raw)
+
+    @staticmethod
+    def _matches_keywords(title: str | None) -> bool:
+        if not title:
+            return False
+        title_lower = title.lower()
+        return any(kw in title_lower for kw in _KEYWORDS)

gimme_job/adapters/nativehealth.py

@@ -0,0 +1,94 @@
+"""NATIVE HEALTH adapter — SmartRecruiters career page, Show More AJAX, keyword filter."""
+from __future__ import annotations
+
+from loguru import logger
+
+from gimme_job.adapters.base import ManifestDrivenAdapter
+from gimme_job.adapters.registry import register
+from gimme_job.models.dto import JobPostingCandidate, RawJobCard
+
+_MAX_SHOW_MORE = 10  # max "Show more jobs" clicks to prevent infinite loops
+_KEYWORDS = ["orthodontist", "orthodontic", "dentist"]
+
+
+@register("nativehealth")
+class NativeHealthAdapter(ManifestDrivenAdapter):
+
+    def collect_cards(self, page, manifest) -> list[RawJobCard]:
+        """Click all 'Show more jobs' links, then extract and keyword-filter all jobs."""
+        try:
+            page.wait_for_selector(
+                "a[href*='smartrecruiters.com/NATIVEHEALTH/']",
+                timeout=15000,
+                state="attached",
+            )
+        except Exception:
+            logger.debug("[nativehealth] Initial jobs wait timed out")
+
+        # Click "Show more jobs" links until none remain (AJAX loads more into same page)
+        for i in range(_MAX_SHOW_MORE):
+            show_more = page.query_selector("a:text('Show more jobs')")
+            if not show_more:
+                break
+
+            prev_count = len(
+                page.query_selector_all("a[href*='smartrecruiters.com/NATIVEHEALTH/']")
+            )
+            show_more.click()
+
+            try:
+                page.wait_for_function(
+                    f"document.querySelectorAll(\"a[href*='smartrecruiters.com/NATIVEHEALTH/']\").length > {prev_count}",
+                    timeout=10000,
+                )
+                logger.debug(f"[nativehealth] Show more {i + 1}: loaded more jobs")
+            except Exception:
+                logger.debug(f"[nativehealth] Show more {i + 1}: no new jobs appeared")
+                break
+
+        # Extract all jobs via JS, getting location from h3 heading of each group
+        raw_data = page.evaluate("""() => {
+            const links = document.querySelectorAll("a[href*='smartrecruiters.com/NATIVEHEALTH/']");
+            return Array.from(links).map(a => {
+                // Walk up: a → li → ul (job list) → location group div → h3
+                const locationDiv = a.closest('li')?.parentElement?.parentElement;
+                const location = locationDiv?.querySelector('h3')?.textContent?.trim() || null;
+                return {
+                    title: (a.querySelector('h4')?.textContent || '').trim(),
+                    employment: (a.querySelector('p')?.textContent || '').trim(),
+                    url: a.href,
+                    location
+                };
+            }).filter(j => j.title);
+        }""")
+
+        cards = []
+        for item in raw_data:
+            if not self._matches_keywords(item["title"]):
+                continue
+            cards.append(RawJobCard(
+                title=item["title"],
+                company="NATIVE HEALTH",
+                location=item["location"] or None,
+                employment_type=item["employment"] or None,
+                url=item["url"] or None,
+            ))
+
+        logger.info(
+            f"[nativehealth] Keyword filter: {len(cards)}/{len(raw_data)} cards matched"
+        )
+        return cards
+
+    def paginate(self, page, page_index: int, config) -> bool:
+        """Single page after Show More clicks — no further pagination."""
+        return False
+
+    def normalize(self, raw: RawJobCard) -> JobPostingCandidate:
+        return super().normalize(raw)
+
+    @staticmethod
+    def _matches_keywords(title: str | None) -> bool:
+        if not title:
+            return False
+        title_lower = title.lower()
+        return any(kw in title_lower for kw in _KEYWORDS)

gimme_job/adapters/srpmic.py

@@ -0,0 +1,93 @@
+"""SRPMIC (Salt River Pima-Maricopa Indian Community) adapter — GovernmentJobs.com."""
+from __future__ import annotations
+
+import re
+
+from loguru import logger
+
+from gimme_job.adapters.base import ManifestDrivenAdapter
+from gimme_job.adapters.registry import register
+from gimme_job.models.dto import JobPostingCandidate, RawJobCard
+
+
+@register("srpmic")
+class SRPMICAdapter(ManifestDrivenAdapter):
+
+    def collect_cards(self, page, manifest) -> list[RawJobCard]:
+        """Extract job cards via JS from the current results page."""
+        raw_data = page.evaluate("""() => {
+            const links = document.querySelectorAll('a[href*="/careers/srpmic/jobs/"]');
+            return Array.from(links).map(a => {
+                const li = a.closest('li');
+                // Details list is the first <ul> directly inside the job card <li>
+                const detailsUl = li?.querySelector(':scope > ul');
+                const details = detailsUl
+                    ? Array.from(detailsUl.querySelectorAll('li')).map(l => l.innerText.trim())
+                    : [];
+                // Posted date is in a direct child element starting with "Posted"
+                const postedText = Array.from(li?.children || [])
+                    .map(c => c.innerText?.trim())
+                    .find(t => t && t.startsWith('Posted')) || null;
+                return {
+                    title: a.innerText.trim(),
+                    url: a.href,
+                    location: details[0] || null,
+                    salary: details[1] || null,
+                    posted: postedText
+                };
+            }).filter(j => j.title && j.url.includes('/careers/srpmic/jobs/'));
+        }""")
+
+        cards = []
+        for item in raw_data:
+            cards.append(RawJobCard(
+                title=item["title"],
+                company="Salt River Pima-Maricopa Indian Community",
+                location=item["location"],
+                salary_text=item["salary"],
+                posted_text=item["posted"],
+                url=item["url"],
+            ))
+
+        logger.info(f"[srpmic] Extracted {len(cards)} cards")
+        return cards
+
+    def paginate(self, page, page_index: int, config) -> bool:
+        """Navigate to next page using URL ?page=N parameter."""
+        # Check if Next link is present and enabled
+        has_next = page.evaluate("""() => {
+            const links = Array.from(document.querySelectorAll('a'));
+            const next = links.find(a =>
+                a.textContent.trim() === 'Next' ||
+                (a.getAttribute('aria-label') || '').toLowerCase().includes('next page')
+            );
+            return !!(next && !next.hasAttribute('disabled') &&
+                      next.getAttribute('aria-disabled') !== 'true');
+        }""")
+
+        if not has_next:
+            return False
+
+        next_page_num = page_index + 2  # page_index 0 → go to page 2
+        current_url = page.url
+
+        if re.search(r'[?&]page=\d+', current_url):
+            next_url = re.sub(r'(page=)\d+', f'page={next_page_num}', current_url)
+        elif '?' in current_url:
+            next_url = current_url + f'&page={next_page_num}'
+        else:
+            next_url = current_url + f'?page={next_page_num}'
+
+        logger.debug(f"[srpmic] Navigating to page {next_page_num}: {next_url}")
+        page.goto(next_url, timeout=30000)
+        try:
+            page.wait_for_selector(
+                "a[href*='/careers/srpmic/jobs/']", timeout=15000, state="attached"
+            )
+        except Exception:
+            logger.debug("[srpmic] No jobs found on next page — stopping")
+            return False
+        return True
+
+    def normalize(self, raw: RawJobCard) -> JobPostingCandidate:
+        return super().normalize(raw)

sites/bfrench.yaml

@@ -0,0 +1,46 @@
+site_id: bfrench
+enabled: true
+repair_needed: false
+
+identity:
+  label: Consulting BFrench Jobs
+  category: employer
+  base_url: https://consultbfrench.applytojob.com
+  start_url_template: "https://consultbfrench.applytojob.com/apply/jobs/"
+
+browser:
+  profile_mode: persistent_chrome_profile
+  profile_name: JobAgent
+  headed_on_learn: true
+  headless_on_run: true
+
+search:
+  keyword_mode: none
+  location_mode: none
+  sort_mode: none
+  date_mode: none
+  result_list_wait_selector: "a[href*='/apply/jobs/details/']"
+
+pagination:
+  mode: none
+  max_pages: 1
+
+extract:
+  container_selectors:
+    - "a[href*='/apply/jobs/details/']"
+  fields:
+    title:
+      text: []
+
+post_filters:
+  include_posted_text: []
+
+healthcheck:
+  min_items_expected: 0
+  required_fields:
+    - title
+  fail_if_zero_when_known_active: false
+
+learn:
+  last_learned_at: null
+  source_url: null

sites/gilariver.yaml

@@ -0,0 +1,47 @@
+site_id: gilariver
+enabled: true
+repair_needed: false
+
+identity:
+  label: Gila River Health Care
+  category: employer
+  base_url: https://css-vlublqzyke7bgjm6-prd.inforcloudsuite.com
+  start_url_template: "https://css-vlublqzyke7bgjm6-prd.inforcloudsuite.com/hcm/Jobs/form/JobBoard%281,EXTERNAL%29.JobSearchCompositeForm?csk.JobBoard=EXTERNAL&csk.HROrganization=1&csk.IsoLocale=en_US&menu=JobsNavigationMenu.NewJobSearch"
+
+browser:
+  profile_mode: persistent_chrome_profile
+  profile_name: JobAgent
+  headed_on_learn: true
+  headless_on_run: true
+
+search:
+  keyword_mode: none
+  location_mode: none
+  sort_mode: none
+  date_mode: none
+  result_list_wait_selector: ".lm-card-content"
+
+pagination:
+  mode: none
+  max_pages: 5
+
+extract:
+  container_selectors:
+    - ".lm-card-content"
+  fields:
+    title:
+      text:
+        - "span.lm-card-field.text-strong a"
+
+post_filters:
+  include_posted_text: []
+
+healthcheck:
+  min_items_expected: 0
+  required_fields:
+    - title
+  fail_if_zero_when_known_active: false
+
+learn:
+  last_learned_at: null
+  source_url: null

sites/govtjobs.yaml

@@ -0,0 +1,50 @@
+site_id: govtjobs
+enabled: true
+repair_needed: false
+
+identity:
+  label: GovernmentJobs.com
+  category: government
+  base_url: https://www.governmentjobs.com
+  start_url_template: "https://www.governmentjobs.com/jobs?keyword={keywords_urlencoded}"
+
+browser:
+  profile_mode: persistent_chrome_profile
+  profile_name: JobAgent
+  headed_on_learn: true
+  headless_on_run: true
+
+search:
+  keyword_mode: url_param
+  location_mode: none
+  sort_mode: none
+  date_mode: none
+  result_list_wait_selector: "h3 a[href*='/jobs/']"
+
+search_override:
+  keywords:
+    - orthodontist
+
+pagination:
+  mode: none
+  max_pages: 5
+
+extract:
+  container_selectors:
+    - "h3 a[href*='/jobs/']"
+  fields:
+    title:
+      text: []
+
+post_filters:
+  include_posted_text: []
+
+healthcheck:
+  min_items_expected: 0
+  required_fields:
+    - title
+  fail_if_zero_when_known_active: false
+
+learn:
+  last_learned_at: null
+  source_url: null

sites/ihs.yaml

@@ -0,0 +1,51 @@
+site_id: ihs
+enabled: true
+repair_needed: false
+
+identity:
+  label: Indian Health Service Dentistry
+  category: government
+  base_url: https://www.ihs.gov
+  start_url_template: "https://www.ihs.gov/dentistry/otheropportunities/"
+
+browser:
+  profile_mode: persistent_chrome_profile
+  profile_name: JobAgent
+  headed_on_learn: true
+  headless_on_run: true
+
+search:
+  keyword_mode: none
+  location_mode: none
+  sort_mode: none
+  date_mode: none
+  result_list_wait_selector: "table.cf_grid tbody tr"
+
+pagination:
+  mode: none
+  max_pages: 1
+
+extract:
+  container_selectors:
+    - "table.cf_grid tbody tr"
+  fields:
+    title:
+      text:
+        - "td:nth-child(2) a"
+    url:
+      attr:
+        selector: "td:nth-child(2) a"
+        name: href
+
+post_filters:
+  include_posted_text: []
+
+healthcheck:
+  min_items_expected: 0
+  required_fields:
+    - title
+  fail_if_zero_when_known_active: false
+
+learn:
+  last_learned_at: null
+  source_url: null

sites/nativehealth.yaml

@@ -0,0 +1,47 @@
+site_id: nativehealth
+enabled: true
+repair_needed: false
+
+identity:
+  label: NATIVE HEALTH
+  category: employer
+  base_url: https://careers.smartrecruiters.com
+  start_url_template: "https://careers.smartrecruiters.com/NATIVEHEALTH"
+
+browser:
+  profile_mode: persistent_chrome_profile
+  profile_name: JobAgent
+  headed_on_learn: true
+  headless_on_run: true
+
+search:
+  keyword_mode: none
+  location_mode: none
+  sort_mode: none
+  date_mode: none
+  result_list_wait_selector: "a[href*='smartrecruiters.com/NATIVEHEALTH/']"
+
+pagination:
+  mode: none
+  max_pages: 1
+
+extract:
+  container_selectors:
+    - "a[href*='smartrecruiters.com/NATIVEHEALTH/']"
+  fields:
+    title:
+      text:
+        - "h4"
+
+post_filters:
+  include_posted_text: []
+
+healthcheck:
+  min_items_expected: 0
+  required_fields:
+    - title
+  fail_if_zero_when_known_active: false
+
+learn:
+  last_learned_at: null
+  source_url: null

sites/srpmic.yaml

@@ -0,0 +1,51 @@
+site_id: srpmic
+enabled: true
+repair_needed: false
+
+identity:
+  label: SRPMIC Employment Opportunities
+  category: government
+  base_url: https://www.governmentjobs.com
+  start_url_template: "https://www.governmentjobs.com/careers/srpmic?keywords={keywords_urlencoded}"
+
+browser:
+  profile_mode: persistent_chrome_profile
+  profile_name: JobAgent
+  headed_on_learn: true
+  headless_on_run: true
+
+search:
+  keyword_mode: url_param
+  location_mode: none
+  sort_mode: none
+  date_mode: none
+  result_list_wait_selector: "a[href*='/careers/srpmic/jobs/']"
+
+search_override:
+  keywords:
+    - dentist
+
+pagination:
+  mode: none
+  max_pages: 5
+
+extract:
+  container_selectors:
+    - "a[href*='/careers/srpmic/jobs/']"
+  fields:
+    title:
+      text:
+        - "h4"
+
+post_filters:
+  include_posted_text: []
+
+healthcheck:
+  min_items_expected: 0
+  required_fields:
+    - title
+  fail_if_zero_when_known_active: false
+
+learn:
+  last_learned_at: null
+  source_url: null