update for artifact with run ID

git commit -m "Added requirements.txt"
git push origin main

.github/workflows/job_scraper_dynamic.yml

@@ -0,0 +1,49 @@
+name: JobSpy Scraper Dynamic Workflow
+
+on:
+  workflow_dispatch:
+    inputs:
+      user_email:
+        description: 'Email of user'
+        required: true
+        default: 'Branden@autoemployme.onmicrosoft.com'
+
+permissions:
+  contents: read
+  id-token: write
+
+jobs:
+  scrape_jobs:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v3
+
+      - name: Set Up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install Dependencies
+        run: |
+          pip install --upgrade pip
+          pip install -r requirements.txt
+
+      - name: Sanitize Email + Create Run ID
+        id: vars
+        run: |
+          safe_email=$(echo "${{ github.event.inputs.user_email }}" | sed 's/@/_at_/g; s/\./_/g')
+          run_id=$(date +%s)
+          echo "safe_email=$safe_email" >> $GITHUB_OUTPUT
+          echo "run_id=$run_id" >> $GITHUB_OUTPUT
+
+      - name: Run Job Scraper
+        run: |
+          python job_scraper_dynamic.py "${{ github.event.inputs.user_email }}" "${{ steps.vars.outputs.run_id }}"
+
+      - name: Upload Output Artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: jobspy_output_${{ steps.vars.outputs.safe_email }}_${{ steps.vars.outputs.run_id }}
+          path: outputs/jobspy_output_${{ steps.vars.outputs.safe_email }}_${{ steps.vars.outputs.run_id }}.csv

.github/workflows/jobspy_scraper.yml

@@ -0,0 +1,48 @@
+name: JobSpy Scraper Workflow
+
+on:
+  workflow_dispatch:  # Allows manual trigger from GitHub or Power Automate
+  # Remove or comment out the schedule to prevent auto-runs
+  # schedule:
+  #   - cron: '0 */6 * * *'  # Runs every 6 hours (DISABLED)
+
+permissions:
+  actions: read
+  contents: read
+  id-token: write
+
+jobs:
+  scrape_jobs:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+
+      - name: Run JobSpy Scraper
+        run: python job_scraper_exact_match.py
+
+      - name: Debug - Check if jobspy_output.csv exists
+        run: |
+          if [ ! -f jobspy_output.csv ]; then
+            echo "❌ ERROR: jobspy_output.csv not found!"
+            exit 1
+          else
+            echo "✅ jobspy_output.csv found, proceeding to upload..."
+          fi
+
+      - name: Upload JobSpy Output as Artifact
+        uses: actions/upload-artifact@v4  # Explicitly using latest version
+        with:
+          name: jobspy-results
+          path: jobspy_output.csv

configs/config.json

@@ -0,0 +1,8 @@
+{
+    "search_terms": ["IT Support", "Help Desk"],
+    "results_wanted": 50,
+    "max_days_old": 7,
+    "target_state": "NY",
+    "user_email": "Branden@autoemployme.onmicrosoft.com"
+  }
+  

configs/config_Branden_at_autoemployme_onmicrosoft_com.json

@@ -0,0 +1,8 @@
+{
+    "search_terms": ["Testing", "Help Desk", "Support"],
+    "results_wanted": 50,
+    "max_days_old": 7,
+    "target_state": "NY",
+    "user_email": "Branden@autoemployme.onmicrosoft.com"
+  }
+  

job_scraper.py

@@ -0,0 +1,116 @@
+import csv
+import datetime
+from jobspy.google import Google
+from jobspy.linkedin import LinkedIn
+from jobspy.indeed import Indeed
+from jobspy.ziprecruiter import ZipRecruiter
+from jobspy.model import ScraperInput
+
+# Define job sources
+sources = {
+    "google": Google,
+    "linkedin": LinkedIn,
+    "indeed": Indeed,
+    "zip_recruiter": ZipRecruiter,
+}
+
+# Define search preferences
+search_terms = ["Automation Engineer", "CRM Manager", "Implementation Specialist"]
+results_wanted = 200  # Fetch more jobs
+max_days_old = 2  # Fetch jobs posted in last 48 hours
+target_state = "NY"  # Only keep jobs from New York
+
+
+def scrape_jobs(search_terms, results_wanted, max_days_old, target_state):
+    """Scrape jobs from multiple sources and filter by state."""
+    all_jobs = []
+    today = datetime.date.today()
+    print("\n🔎 DEBUG: Fetching jobs for search terms:", search_terms)
+
+    for search_term in search_terms:
+        for source_name, source_class in sources.items():
+            print(f"\n🚀 Scraping {search_term} from {source_name}...")
+
+            scraper = source_class()
+            search_criteria = ScraperInput(
+                site_type=[source_name],
+                search_term=search_term,
+                results_wanted=results_wanted,
+            )
+
+            job_response = scraper.scrape(search_criteria)
+
+            for job in job_response.jobs:
+                # Normalize location fields
+                location_city = job.location.city.strip() if job.location.city else "Unknown"
+                location_state = job.location.state.strip().upper() if job.location.state else "Unknown"
+                location_country = str(job.location.country) if job.location.country else "Unknown"
+
+                # Debug: Show all jobs being fetched
+                print(f"📍 Fetched Job: {job.title} - {location_city}, {location_state}, {location_country}")
+
+                # Ensure the job is recent
+                if job.date_posted and (today - job.date_posted).days <= max_days_old:
+                    if location_state == target_state or job.is_remote:
+                        print(f"✅ MATCH (In NY or Remote): {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
+
+                        all_jobs.append({
+                            "Job ID": job.id,
+                            "Job Title (Primary)": job.title,
+                            "Company Name": job.company_name if job.company_name else "Unknown",
+                            "Industry": job.company_industry if job.company_industry else "Not Provided",
+                            "Experience Level": job.job_level if job.job_level else "Not Provided",
+                            "Job Type": job.job_type[0].name if job.job_type else "Not Provided",
+                            "Is Remote": job.is_remote,
+                            "Currency": job.compensation.currency if job.compensation else "",
+                            "Salary Min": job.compensation.min_amount if job.compensation else "",
+                            "Salary Max": job.compensation.max_amount if job.compensation else "",
+                            "Date Posted": job.date_posted.strftime("%Y-%m-%d") if job.date_posted else "Not Provided",
+                            "Location City": location_city,
+                            "Location State": location_state,
+                            "Location Country": location_country,
+                            "Job URL": job.job_url,
+                            "Job Description": job.description[:500] if job.description else "No description available",
+                            "Job Source": source_name
+                        })
+                    else:
+                        print(f"❌ Ignored (Wrong State): {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
+                else:
+                    print(f"⏳ Ignored (Too Old): {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
+
+    print(f"\n✅ {len(all_jobs)} jobs retrieved in NY")
+    return all_jobs
+
+
+def save_jobs_to_csv(jobs, filename="jobspy_output.csv"):
+    """Save job data to a CSV file."""
+    if not jobs:
+        print("⚠️ No jobs found matching criteria.")
+        return
+
+    fieldnames = [
+        "Job ID", "Job Title (Primary)", "Company Name", "Industry",
+        "Experience Level", "Job Type", "Is Remote", "Currency",
+        "Salary Min", "Salary Max", "Date Posted", "Location City",
+        "Location State", "Location Country", "Job URL", "Job Description",
+        "Job Source"
+    ]
+
+    with open(filename, mode="w", newline="", encoding="utf-8") as file:
+        writer = csv.DictWriter(file, fieldnames=fieldnames)
+        writer.writeheader()
+        writer.writerows(jobs)
+
+    print(f"✅ Jobs saved to {filename} ({len(jobs)} entries)")
+
+
+# Run the scraper with multiple job searches
+job_data = scrape_jobs(
+    search_terms=search_terms,
+    results_wanted=results_wanted,
+    max_days_old=max_days_old,
+    target_state=target_state
+)
+
+# Save results to CSV
+save_jobs_to_csv(job_data)

job_scraper_dynamic.py

@@ -0,0 +1,94 @@
+import csv, datetime, os, sys, json
+from jobspy.google import Google
+from jobspy.linkedin import LinkedIn
+from jobspy.indeed import Indeed
+from jobspy.model import ScraperInput
+
+sources = {
+    "google": Google,
+    "linkedin": LinkedIn,
+    "indeed": Indeed,
+}
+
+def sanitize_email(email):
+    return email.replace("@", "_at_").replace(".", "_")
+
+def load_config(email):
+    safe_email = sanitize_email(email)
+    config_path = os.path.join("configs", f"config_{safe_email}.json")
+    if not os.path.exists(config_path):
+        raise FileNotFoundError(f"❌ Config for {email} not found at {config_path}")
+    with open(config_path, "r", encoding="utf-8") as f:
+        return json.load(f), safe_email
+
+def scrape_jobs(search_terms, results_wanted, max_days_old, target_state):
+    today = datetime.date.today()
+    all_jobs = []
+
+    for term in search_terms:
+        for source, Scraper in sources.items():
+            print(f"🔍 Scraping {term} from {source}")
+            scraper = Scraper()
+            try:
+                jobs = scraper.scrape(ScraperInput(
+                    site_type=[source],
+                    search_term=term,
+                    results_wanted=results_wanted
+                )).jobs
+            except Exception as e:
+                print(f"⚠️ {source} error: {e}")
+                continue
+
+            for job in jobs:
+                if job.date_posted and (today - job.date_posted).days <= max_days_old:
+                    if target_state == (job.location.state or "").upper() or job.is_remote:
+                        if any(term.lower() in job.title.lower() for term in search_terms):
+                            all_jobs.append({
+                                "Job ID": job.id,
+                                "Job Title (Primary)": job.title,
+                                "Company Name": job.company_name or "Unknown",
+                                "Industry": job.company_industry or "Not Provided",
+                                "Experience Level": job.job_level or "Not Provided",
+                                "Job Type": job.job_type[0].name if job.job_type else "Not Provided",
+                                "Is Remote": job.is_remote,
+                                "Currency": job.compensation.currency if job.compensation else "",
+                                "Salary Min": job.compensation.min_amount if job.compensation else "",
+                                "Salary Max": job.compensation.max_amount if job.compensation else "",
+                                "Date Posted": job.date_posted.strftime("%Y-%m-%d"),
+                                "Location City": job.location.city or "Unknown",
+                                "Location State": (job.location.state or "Unknown").upper(),
+                                "Location Country": job.location.country or "Unknown",
+                                "Job URL": job.job_url,
+                                "Job Description": job.description.replace(",", "") if job.description else "No description",
+                                "Job Source": source
+                            })
+    print(f"✅ Found {len(all_jobs)} jobs")
+    return all_jobs
+
+def save_to_csv(jobs, path):
+    os.makedirs(os.path.dirname(path), exist_ok=True)
+    fieldnames = [
+        "Job ID", "Job Title (Primary)", "Company Name", "Industry",
+        "Experience Level", "Job Type", "Is Remote", "Currency",
+        "Salary Min", "Salary Max", "Date Posted", "Location City",
+        "Location State", "Location Country", "Job URL", "Job Description", "Job Source"
+    ]
+    header = "|~|".join(fieldnames)
+    rows = [header] + ["|~|".join(str(job.get(col, "Not Provided")).replace(",", "").strip() for col in fieldnames) for job in jobs]
+    with open(path, "w", encoding="utf-8") as f:
+        f.write(",".join(rows))
+    print(f"💾 Saved output to: {path}")
+
+if __name__ == "__main__":
+    try:
+        if len(sys.argv) != 3:
+            raise ValueError("❌ Usage: python job_scraper_dynamic.py <user_email> <run_id>")
+
+        user_email, run_id = sys.argv[1], sys.argv[2]
+        config, safe_email = load_config(user_email)
+        jobs = scrape_jobs(config["search_terms"], config["results_wanted"], config["max_days_old"], config["target_state"])
+        save_to_csv(jobs, f"outputs/jobspy_output_{safe_email}_{run_id}.csv")
+
+    except Exception as e:
+        print(f"❌ Fatal error: {e}")
+        sys.exit(1)

job_scraper_exact_match.py

@@ -0,0 +1,146 @@
+import csv
+import datetime
+import os
+from jobspy.google import Google
+from jobspy.linkedin import LinkedIn
+from jobspy.indeed import Indeed
+from jobspy.model import ScraperInput
+
+# Define job sources
+sources = {
+    "google": Google,
+    "linkedin": LinkedIn,
+    "indeed": Indeed,
+}
+
+# Define search preferences
+search_terms = ["Automation Engineer", "CRM Manager", "Implementation Specialist", "CRM", "Project Manager", "POS", "Microsoft Power", "IT Support"]
+results_wanted = 100  # Fetch more jobs
+max_days_old = 2  # Fetch jobs posted in last 48 hours
+target_state = "NY"  # Only keep jobs from New York
+
+def scrape_jobs(search_terms, results_wanted, max_days_old, target_state):
+    """Scrape jobs from multiple sources and filter by state."""
+    all_jobs = []
+    today = datetime.date.today()
+    
+    print("\n🔎 DEBUG: Fetching jobs for search terms:", search_terms)
+
+    for search_term in search_terms:
+        for source_name, source_class in sources.items():
+            print(f"\n🚀 Scraping {search_term} from {source_name}...")
+
+            scraper = source_class()
+            search_criteria = ScraperInput(
+                site_type=[source_name],
+                search_term=search_term,
+                results_wanted=results_wanted,
+            )
+
+            job_response = scraper.scrape(search_criteria)
+
+            for job in job_response.jobs:
+                # Normalize location fields
+                location_city = job.location.city.strip() if job.location.city else "Unknown"
+                location_state = job.location.state.strip().upper() if job.location.state else "Unknown"
+                location_country = str(job.location.country) if job.location.country else "Unknown"
+
+                # Debug: Show all jobs being fetched
+                print(f"📍 Fetched Job: {job.title} - {location_city}, {location_state}, {location_country}")
+
+                # Exclude jobs that don’t explicitly match the search terms
+                if not any(term.lower() in job.title.lower() for term in search_terms):
+                    print(f"🚫 Excluding: {job.title} (Doesn't match {search_terms})")
+                    continue  # Skip this job
+
+                # Ensure the job is recent
+                if job.date_posted and (today - job.date_posted).days <= max_days_old:
+                    # Only accept jobs if they're in NY or Remote
+                    if location_state == target_state or job.is_remote:
+                        print(f"✅ MATCH: {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
+                        all_jobs.append({
+                            "Job ID": job.id,
+                            "Job Title (Primary)": job.title,
+                            "Company Name": job.company_name if job.company_name else "Unknown",
+                            "Industry": job.company_industry if job.company_industry else "Not Provided",
+                            "Experience Level": job.job_level if job.job_level else "Not Provided",
+                            "Job Type": job.job_type[0].name if job.job_type else "Not Provided",
+                            "Is Remote": job.is_remote,
+                            "Currency": job.compensation.currency if job.compensation else "",
+                            "Salary Min": job.compensation.min_amount if job.compensation else "",
+                            "Salary Max": job.compensation.max_amount if job.compensation else "",
+                            "Date Posted": job.date_posted.strftime("%Y-%m-%d") if job.date_posted else "Not Provided",
+                            "Location City": location_city,
+                            "Location State": location_state,
+                            "Location Country": location_country,
+                            "Job URL": job.job_url,
+                            "Job Description": job.description.replace(",", "") if job.description else "No description available",
+                            "Job Source": source_name
+                        })
+                    else:
+                        print(f"❌ Ignored (Wrong State): {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
+                else:
+                    print(f"⏳ Ignored (Too Old): {job.title} - {location_city}, {location_state} (Posted {job.date_posted})")
+
+    print(f"\n✅ {len(all_jobs)} jobs retrieved in NY")
+    return all_jobs
+
+
+def save_jobs_to_csv(jobs, filename="jobspy_output.csv"):
+    """Save job data to a CSV file with custom formatting:
+       - Fields within a record are separated by the custom delimiter |~|
+       - Records are separated by a comma
+       - All commas in field values are removed
+       - Blank fields are replaced with 'Not Provided'
+    """
+    if not jobs:
+        print("⚠️ No jobs found matching criteria.")
+        return
+
+    # Remove old CSV file before writing
+    if os.path.exists(filename):
+        os.remove(filename)
+
+    fieldnames = [
+        "Job ID", "Job Title (Primary)", "Company Name", "Industry",
+        "Experience Level", "Job Type", "Is Remote", "Currency",
+        "Salary Min", "Salary Max", "Date Posted", "Location City",
+        "Location State", "Location Country", "Job URL", "Job Description",
+        "Job Source"
+    ]
+
+    # Build header record using custom field delimiter
+    header_record = "|~|".join(fieldnames)
+    records = [header_record]
+
+    for job in jobs:
+        row = []
+        for field in fieldnames:
+            value = str(job.get(field, "")).strip()
+            if not value:
+                value = "Not Provided"
+            # Remove all commas from the value
+            value = value.replace(",", "")
+            row.append(value)
+        # Join fields with the custom delimiter
+        record = "|~|".join(row)
+        records.append(record)
+    
+    # Join records with a comma as the record separator
+    output = ",".join(records)
+    with open(filename, "w", encoding="utf-8") as file:
+        file.write(output)
+
+    print(f"✅ Jobs saved to {filename} ({len(jobs)} entries)")
+
+
+# Run the scraper with multiple job searches
+job_data = scrape_jobs(
+    search_terms=search_terms,
+    results_wanted=results_wanted,
+    max_days_old=max_days_old,
+    target_state=target_state
+)
+
+# Save results to CSV with custom formatting
+save_jobs_to_csv(job_data)

jobspy/indeed/__init__.py

@@ -205,6 +205,8 @@ class Indeed(Scraper):
         description = job["description"]["html"]
         if self.scraper_input.description_format == DescriptionFormat.MARKDOWN:
             description = markdown_converter(description)
+            description = description.replace(",", "")
+
 
         job_type = get_job_type(job["attributes"])
         timestamp_seconds = job["datePublished"] / 1000

jobspy/indeed/util.py

@@ -58,14 +58,11 @@ def is_job_remote(job: dict, description: str) -> bool:
         any(keyword in attr["label"].lower() for keyword in remote_keywords)
         for attr in job["attributes"]
     )
-    is_remote_in_description = any(
-        keyword in description.lower() for keyword in remote_keywords
-    )
     is_remote_in_location = any(
         keyword in job["location"]["formatted"]["long"].lower()
         for keyword in remote_keywords
     )
-    return is_remote_in_attributes or is_remote_in_description or is_remote_in_location
+    return is_remote_in_attributes or is_remote_in_location
 
 
 def get_compensation_interval(interval: str) -> CompensationInterval:

jobspy/linkedin/__init__.py

@@ -217,6 +217,8 @@ class LinkedIn(Scraper):
         job_details = {}
         if full_descr:
             job_details = self._get_job_details(job_id)
+            description = description.replace(",", "")
+
 
         return JobPost(
             id=f"li-{job_id}",

pyproject.toml

@@ -17,7 +17,7 @@ include = "jobspy"
 line-length = 88
 
 [tool.poetry.dependencies]
-python = "^3.10"
+python = "^3.10 || ^3.12"
 requests = "^2.31.0"
 beautifulsoup4 = "^4.12.2"
 pandas = "^2.1.0"

requirements.txt

@@ -0,0 +1,118 @@
+annotated-types==0.7.0
+anyio==4.6.2.post1
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==2.4.1
+async-lru==2.0.4
+attrs==24.2.0
+babel==2.16.0
+beautifulsoup4==4.12.3
+black==24.10.0
+bleach==6.1.0
+certifi==2024.8.30
+cffi==1.17.1
+cfgv==3.4.0
+charset-normalizer==3.4.0
+click==8.1.7
+comm==0.2.2
+debugpy==1.8.7
+decorator==5.1.1
+defusedxml==0.7.1
+distlib==0.3.9
+executing==2.1.0
+fastjsonschema==2.20.0
+filelock==3.16.1
+fqdn==1.5.1
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+identify==2.6.1
+idna==3.10
+ipykernel==6.29.5
+ipython==8.28.0
+ipywidgets==8.1.5
+isoduration==20.11.0
+jedi==0.19.1
+Jinja2==3.1.4
+json5==0.9.25
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter==1.1.1
+jupyter-console==6.6.3
+jupyter-events==0.10.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.14.2
+jupyter_server_terminals==0.5.3
+jupyterlab==4.2.5
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+markdownify==0.13.1
+MarkupSafe==3.0.2
+matplotlib-inline==0.1.7
+mistune==3.0.2
+mypy-extensions==1.0.0
+nbclient==0.10.0
+nbconvert==7.16.4
+nbformat==5.10.4
+nest-asyncio==1.6.0
+nodeenv==1.9.1
+notebook==7.2.2
+notebook_shim==0.2.4
+numpy==1.26.3
+overrides==7.7.0
+packaging==24.1
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+pathspec==0.12.1
+pexpect==4.9.0
+platformdirs==4.3.6
+pre_commit==4.0.1
+prometheus_client==0.21.0
+prompt_toolkit==3.0.48
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pycparser==2.22
+pydantic==2.9.2
+pydantic_core==2.23.4
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+-e git+https://github.com/fakebranden/JobSpy@60819a8fcabbd3eaba7741b673023612dc3d3692#egg=python_jobspy
+python-json-logger==2.0.7
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rpds-py==0.20.0
+Send2Trash==1.8.3
+setuptools==75.2.0
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.6
+stack-data==0.6.3
+terminado==0.18.1
+tinycss2==1.3.0
+tls-client==1.0.1
+tornado==6.4.1
+traitlets==5.14.3
+types-python-dateutil==2.9.0.20241003
+typing_extensions==4.12.2
+tzdata==2024.2
+uri-template==1.3.0
+urllib3==2.2.3
+virtualenv==20.27.0
+wcwidth==0.2.13
+webcolors==24.8.0
+webencodings==0.5.1
+websocket-client==1.8.0
+widgetsnbextension==4.0.13