feat: professionalize platform release 0.3.13

apps/sources/adapters/generic_html.py

@@ -9,13 +9,15 @@ from .base import ExtractedJob, ExtractionResult, FieldEvidence
 
 LABEL_PATTERNS = {
     "location": re.compile(r"^(locatie|location|lieu|plaats|standplaats)\s*:?$", re.I),
+    "date_posted": re.compile(r"^(publicatiedatum|geplaatst|date posted|published)\s*:?$", re.I),
+    "employment_type": re.compile(r"^(dienstverband|contract|employment type)\s*:?$", re.I),
     "employer": re.compile(r"^(werkgever|employer|company|organisatie|société)\s*:?$", re.I),
 }
 
 
 class GenericHtmlAdapter:
     parser_key = "generic-html"
-    parser_version = "1.0.0"
+    parser_version = "1.1.0"
 
     @staticmethod
     def _meta(soup: BeautifulSoup, *names: str) -> str:
@@ -59,6 +61,8 @@ class GenericHtmlAdapter:
             soup, LABEL_PATTERNS["employer"]
         )
         location = self._label_value(soup, LABEL_PATTERNS["location"])
+        date_posted = self._label_value(soup, LABEL_PATTERNS["date_posted"])
+        employment_type = self._label_value(soup, LABEL_PATTERNS["employment_type"])
         main = soup.find("main") or soup.find("article") or soup.body
         description_html = str(main) if main else ""
         description_text = (
@@ -74,6 +78,12 @@ class GenericHtmlAdapter:
             FieldEvidence("location_text", "html-label", 0.62, location[:240]),
             FieldEvidence("description", "html-main", 0.70, description_text[:300]),
         ]
+        if date_posted:
+            evidence.append(FieldEvidence("date_posted", "html-label", 0.62, date_posted[:40]))
+        if employment_type:
+            evidence.append(
+                FieldEvidence("employment_types", "html-label", 0.62, employment_type[:120])
+            )
         job = ExtractedJob(
             url=job_url,
             title=title,
@@ -81,6 +91,8 @@ class GenericHtmlAdapter:
             location_text=location,
             description_html=description_html,
             description_text=description_text,
+            date_posted=date_posted,
+            employment_types=[employment_type] if employment_type else [],
             raw={"generic_html": True},
             evidence=evidence,
         )