linkfetch 0.1.3__tar.gz → 1.0.0__tar.gz

{linkfetch-0.1.3 → linkfetch-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: linkfetch
-Version: 0.1.3
+Version: 1.0.0
 Summary: Capture your own LinkedIn profile on your own computer and turn it into structured profile files
 Project-URL: Homepage, https://github.com/Prosperis/linkfetch
 Project-URL: Issues, https://github.com/Prosperis/linkfetch/issues
@@ -8,7 +8,7 @@ Author: Prosperis
 License-Expression: MIT
 License-File: LICENSE
 Keywords: cv,export,linkedin,playwright,profile,resume
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: End Users/Desktop
 Classifier: Operating System :: OS Independent

{linkfetch-0.1.3 → linkfetch-1.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "linkfetch"
-version = "0.1.3"
+version = "1.0.0"
 description = "Capture your own LinkedIn profile on your own computer and turn it into structured profile files"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -9,7 +9,7 @@ license-files = ["LICENSE"]
 authors = [{ name = "Prosperis" }]
 keywords = ["linkedin", "profile", "resume", "cv", "export", "playwright"]
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Intended Audience :: End Users/Desktop",
     "Operating System :: OS Independent",

{linkfetch-0.1.3 → linkfetch-1.0.0}/src/linkfetch/cli.py

@@ -52,6 +52,20 @@ def _playwright_installed() -> bool:
     return importlib.util.find_spec("playwright") is not None
 
 
+def _browser_downloaded() -> bool:
+    """True if the Chromium build this Playwright version drives is on disk.
+
+    Starts Playwright's driver only to ask for the path; no browser opens.
+    """
+    try:
+        from playwright.sync_api import sync_playwright
+
+        with sync_playwright() as p:
+            return Path(p.chromium.executable_path).is_file()
+    except Exception:
+        return False
+
+
 def _section_arg(sections: list[str] | None) -> list[Section]:
     try:
         return resolve(sections)
@@ -76,6 +90,10 @@ def doctor() -> None:
 
     if _playwright_installed():
         console.print("[green]✓[/] Playwright is installed")
+        if _browser_downloaded():
+            console.print("[green]✓[/] The browser is downloaded")
+        else:
+            console.print("[yellow]![/] The browser is not downloaded yet — run `linkfetch install-browser`")
     else:
         console.print(
             "[yellow]![/] Playwright not installed — capture/login unavailable.\n"

{linkfetch-0.1.3 → linkfetch-1.0.0}/src/linkfetch/emit.py

@@ -24,7 +24,30 @@ def _to_plain(models: list[BaseModel] | BaseModel) -> object:
     """
     if isinstance(models, BaseModel):
         return _prune(models.model_dump())
-    return [_prune(m.model_dump()) for m in models]
+    return _unique([_prune(m.model_dump()) for m in models])
+
+
+def _unique(items: list[dict]) -> list[dict]:
+    """Drop exact duplicates and keep ``id`` values unique.
+
+    LinkedIn can render the same entry twice (a lazy-loaded list re-rendering,
+    or an entry genuinely listed twice); an identical copy adds nothing. Two
+    *different* entries that slug to the same ``id`` both stay, the later one
+    suffixed ``-2``, ``-3`` … so ids remain unique within a file.
+    """
+    out: list[dict] = []
+    seen_ids: dict[str, int] = {}
+    for item in items:
+        if item in out:
+            continue
+        base = item.get("id")
+        if isinstance(base, str):
+            count = seen_ids.get(base, 0) + 1
+            seen_ids[base] = count
+            if count > 1:
+                item = {**item, "id": f"{base}-{count}"}
+        out.append(item)
+    return out
 
 
 def _prune(value: object) -> object:

{linkfetch-0.1.3 → linkfetch-1.0.0}/src/linkfetch/parse/common.py

@@ -44,6 +44,9 @@ _CHROME = (
     "select language", "profile language", "accessibility", "talent solutions",
     "community guidelines", "marketing solutions", "privacy & terms",
     "ad choices", "sales solutions", "small business", "safety center",
+    # In-section notices, e.g. "Projects from connected apps sync
+    # automatically and can't be edited on LinkedIn."
+    "sync automatically", "be edited on linkedin",
 )
 
 # Section-title fragments that appear as the first child block of the content

linkfetch-1.0.0/tests/test_regressions.py

@@ -0,0 +1,34 @@
+"""Bugs found in a real capture, kept fixed."""
+
+from linkfetch.emit import _to_plain
+from linkfetch.models import Course
+from linkfetch.parse import projects
+
+
+def _page(*entries: str) -> str:
+    return (
+        "<html><body><main><section aria-label='Primary content'>"
+        "<div><p>Projects</p></div><div>" + "".join(entries) + "</div>"
+        "</section></main></body></html>"
+    )
+
+
+def test_linkedin_notice_is_not_a_project():
+    html = _page(
+        "<div><p>Projects from connected apps sync automatically and can’t be edited on LinkedIn.</p>"
+        "<span>Learn more</span></div>",
+        "<div><p>Example Viewer</p><p>Nov 2025 – Present</p></div>",
+        "<div><p>Example CLI</p><p>Jan 2024 – Mar 2024</p></div>",
+    )
+    assert [p.name for p in projects.parse(html)] == ["Example Viewer", "Example CLI"]
+
+
+def test_identical_entries_are_written_once_and_ids_stay_unique():
+    data = _to_plain([
+        Course(id="stats-math-32", name="Probability and Statistics", number="MATH 32"),
+        Course(id="stats-math-32", name="Probability and Statistics", number="MATH 32"),
+        Course(id="intro", name="Intro", associated_with="School A"),
+        Course(id="intro", name="Intro", associated_with="School B"),
+    ])
+    assert [c["id"] for c in data] == ["stats-math-32", "intro", "intro-2"]
+    assert data[2]["associated_with"] == "School B"

{linkfetch-0.1.3 → linkfetch-1.0.0}/uv.lock

@@ -138,7 +138,7 @@ wheels = [
 
 [[package]]
 name = "linkfetch"
-version = "0.1.3"
+version = "1.0.0"
 source = { editable = "." }
 dependencies = [
     { name = "lxml" },