Update app.py

app.py

@@ -9,7 +9,9 @@ Features
 2. Score résumé vs. job description
 3. AI Section Co-Pilot (rewrite, quantify, bulletize…)
 4. Cover-letter generator
-5. Job-description via LinkedIn API (OAuth client_credentials) + fallback scraping
+5. Fetch any job description by URL:
+   • LinkedIn via OAuth2 Jobs API
+   • All other sites via HTML scraping
 6. Multilingual export via Deep-Translator (DeepL backend)
 """
 
@@ -26,6 +28,7 @@ from docx import Document
 from reportlab.lib.pagesizes import LETTER
 from reportlab.pdfgen import canvas
 from deep_translator import DeeplTranslator
+from urllib.parse import urlparse
 
 # ──────────────────────────────────────────────────────────────────────────────
 # Load Secrets & Configure Clients
@@ -56,7 +59,6 @@ def get_linkedin_token():
     data = _token_cache.get("data", {})
     if data and data.get("expires_at", 0) > time.time():
         return data["access_token"]
-
     resp = requests.post(
         "https://www.linkedin.com/oauth/v2/accessToken",
         data={
@@ -66,54 +68,72 @@ def get_linkedin_token():
         },
         timeout=10
     )
-    if resp.status_code != 200:
-        # raise or let caller fallback
-        resp.raise_for_status()
-
+    resp.raise_for_status()
     payload = resp.json()
     payload["expires_at"] = time.time() + payload.get("expires_in", 0) - 60
     _token_cache["data"] = payload
     return payload["access_token"]
 
-def fetch_job_via_api(url: str) -> str:
-    # Extract numeric job ID
-    m = re.search(r"(?:jobs/view/|currentJobId=)(\d+)", url)
-    if not m:
-        return "[Error] Unable to parse job ID from URL."
-    job_id = m.group(1)
-
-    # Try LinkedIn Jobs API
+# ──────────────────────────────────────────────────────────────────────────────
+# Job-Description Fetcher (LinkedIn API or Generic Scraping)
+# ──────────────────────────────────────────────────────────────────────────────
+def fetch_job_description(url: str) -> str:
+    domain = urlparse(url).netloc.lower()
+    # 1) If it's LinkedIn, try the Jobs API first
+    if "linkedin.com" in domain:
+        m = re.search(r"(?:jobs/view/|currentJobId=)(\d+)", url)
+        if m:
+            job_id = m.group(1)
+            try:
+                token = get_linkedin_token()
+                api_url = (
+                    f"https://api.linkedin.com/v2/jobPosts/{job_id}"
+                    "?projection=(description)"
+                )
+                r = requests.get(
+                    api_url,
+                    headers={"Authorization": f"Bearer {token}"},
+                    timeout=10
+                )
+                r.raise_for_status()
+                return r.json().get("description", "")
+            except Exception:
+                # fall through to generic scraping
+                pass
+
+    # 2) Generic scraping for any other site (or LinkedIn fallback)
     try:
-        token = get_linkedin_token()
-        api_url = f"https://api.linkedin.com/v2/jobPosts/{job_id}?projection=(description)"
-        r = requests.get(api_url,
-                         headers={"Authorization": f"Bearer {token}"},
-                         timeout=10)
-        r.raise_for_status()
-        return r.json().get("description", "")
-    except Exception:
-        # Fallback to scraping
-        try:
-            page = requests.get(url, headers={"User-Agent":"Mozilla/5.0"}, timeout=10)
-            soup = BeautifulSoup(page.text, "html.parser")
-            for sel in [
-                "div.jobsearch-jobDescriptionText",
-                "section.description",
-                "div.jobs-description__content"
-            ]:
-                block = soup.select_one(sel)
-                if block:
-                    return block.get_text(" ", strip=True)
-            return "[Error] No description found via scraping."
-        except Exception as e:
-            return f"[Scrape Error] {e}"
+        page = requests.get(url, headers={"User-Agent":"Mozilla/5.0"}, timeout=10)
+        soup = BeautifulSoup(page.text, "html.parser")
+
+        # Common job-description selectors across platforms
+        selectors = [
+            "div.jobsearch-jobDescriptionText",      # Indeed
+            "section.description",                   # generic
+            "div.jobs-description__content",         # LinkedIn client-side
+            "div#job-details",                       # Greenhouse
+            "article.jobPosting",                    # Workday / custom
+            "div.jd-container",                      # many ATS
+        ]
+        for sel in selectors:
+            block = soup.select_one(sel)
+            if block and block.get_text(strip=True):
+                return block.get_text(" ", strip=True)
+
+        # Fallback: return full page text (truncated)
+        text = soup.get_text(" ", strip=True)
+        return text[:5000] + ("…" if len(text) > 5000 else "")
+    except Exception as e:
+        return f"[Error fetching job description] {e}"
 
 # ──────────────────────────────────────────────────────────────────────────────
-# AI & File Utilities
+# AI & File Utilities (unchanged)
 # ──────────────────────────────────────────────────────────────────────────────
 def ask_gemini(prompt: str, temp: float = 0.6) -> str:
     try:
-        return GEMINI.generate_content(prompt, generation_config={"temperature": temp}).text.strip()
+        return GEMINI.generate_content(
+            prompt, generation_config={"temperature": temp}
+        ).text.strip()
     except Exception as e:
         return f"[Gemini Error] {e}"
 
@@ -140,7 +160,7 @@ def save_pdf(text: str) -> str:
     return f.name
 
 # ──────────────────────────────────────────────────────────────────────────────
-# Core Logic
+# Core AI Logic & UI Setup (unchanged)
 # ──────────────────────────────────────────────────────────────────────────────
 LANGS = {
     "EN": "English", "DE": "German",  "FR": "French",   "ES": "Spanish",
@@ -181,10 +201,10 @@ def score_resume(resume_md, jd):
 Evaluate this résumé against the job description. Return compact Markdown:
 
 ### Match Score
-<0-100>
+<0–100>
 
 ### Suggestions
-- ...
+- …
 """
     return ask_gemini(prompt, temp=0.4)
 
@@ -214,34 +234,33 @@ Job Description:
     return translate_text(letter, lang)
 
 # ──────────────────────────────────────────────────────────────────────────────
-# Gradio App
+# Gradio App Definition
 # ──────────────────────────────────────────────────────────────────────────────
 with gr.Blocks(title="AI Resume Studio") as demo:
-    gr.Markdown("## 🧠 AI Resume Studio (Gemini × DeepL × LinkedIn)")
+    gr.Markdown("## 🧠 AI Resume Studio (Gemini × DeepL + Universal Job Fetcher)")
 
     # Tab 1: Generate Résumé
     with gr.Tab("📄 Generate Résumé"):
-        with gr.Row():
-            name_in, email_in, phone_in = (
-                gr.Textbox(label="Name"),
-                gr.Textbox(label="Email"),
-                gr.Textbox(label="Phone"),
-            )
+        name_in, email_in, phone_in = (
+            gr.Textbox(label="Name"),
+            gr.Textbox(label="Email"),
+            gr.Textbox(label="Phone")
+        )
         sum_in    = gr.Textbox(label="Professional Summary")
         exp_in    = gr.Textbox(label="Experience")
         edu_in    = gr.Textbox(label="Education")
         skills_in = gr.Textbox(label="Skills")
         lang_in   = gr.Dropdown(list(LANGS.keys()), value="EN", label="Language")
 
-        out_md   = gr.Markdown(label="Résume (Markdown)")
-        out_docx = gr.File(label="⬇ Download .docx")
-        out_pdf  = gr.File(label="⬇ Download .pdf")
+        md_out   = gr.Markdown(label="Résumé (Markdown)")
+        docx_out = gr.File(label="⬇ Download .docx")
+        pdf_out  = gr.File(label="⬇ Download .pdf")
         btn_gen  = gr.Button("Generate")
 
         btn_gen.click(
             generate_and_export,
             inputs=[name_in, email_in, phone_in, sum_in, exp_in, edu_in, skills_in, lang_in],
-            outputs=[out_md, out_docx, out_pdf],
+            outputs=[md_out, docx_out, pdf_out],
         )
 
     # Tab 2: Score Résumé
@@ -255,10 +274,9 @@ with gr.Blocks(title="AI Resume Studio") as demo:
     # Tab 3: AI Section Co-Pilot
     with gr.Tab("✏️ AI Section Co-Pilot"):
         sec_in   = gr.Textbox(label="Section Text", lines=6)
-        act_in   = gr.Radio(
-            ["Rewrite", "Make More Concise", "Quantify Achievements", "Convert to Bullet Points"],
-            label="Action"
-        )
+        act_in   = gr.Radio([
+            "Rewrite", "Make More Concise", "Quantify Achievements", "Convert to Bullet Points"
+        ], label="Action")
         lang_sec = gr.Dropdown(list(LANGS.keys()), value="EN", label="Language")
         sec_out  = gr.Textbox(label="AI Output", lines=6)
         btn_sec  = gr.Button("Apply")
@@ -267,18 +285,20 @@ with gr.Blocks(title="AI Resume Studio") as demo:
     # Tab 4: Cover-Letter Generator
     with gr.Tab("📧 Cover-Letter Generator"):
         cv_res   = gr.Textbox(label="Résumé (Markdown)", lines=12)
-        cv_jd    = gr.Textbox(label="Job Description", lines=8)
-        cv_tone  = gr.Radio(["Professional", "Friendly", "Enthusiastic"], label="Tone")
+        cv_jd    = gr.Textbox(label="Job Description",   lines=8)
+        cv_tone  = gr.Radio(["Professional","Friendly","Enthusiastic"], label="Tone")
         cv_lang  = gr.Dropdown(list(LANGS.keys()), value="EN", label="Language")
         cv_out   = gr.Markdown(label="Cover Letter")
         btn_cv   = gr.Button("Generate")
-        btn_cv.click(generate_cover_letter, inputs=[cv_res, cv_jd, cv_tone, cv_lang], outputs=cv_out)
+        btn_cv.click(generate_cover_letter,
+                     inputs=[cv_res, cv_jd, cv_tone, cv_lang],
+                     outputs=cv_out)
 
-    # Tab 5: LinkedIn Job Fetcher
-    with gr.Tab("🌐 Fetch Job via LinkedIn API"):
-        url_in    = gr.Textbox(label="LinkedIn Job URL")
+    # Tab 5: Universal Job Description Fetcher
+    with gr.Tab("🌐 Fetch Job Description"):
+        url_in    = gr.Textbox(label="Job URL")
         jd_out    = gr.Textbox(label="Job Description", lines=12)
-        btn_fetch = gr.Button("Fetch from LinkedIn")
-        btn_fetch.click(fetch_job_via_api, inputs=[url_in], outputs=[jd_out])
+        btn_fetch = gr.Button("Fetch Description")
+        btn_fetch.click(fetch_job_description, inputs=[url_in], outputs=[jd_out])
 
 demo.launch(share=False)