Structured Extraction of Resume Details

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

app.py

@@ -0,0 +1,113 @@
+import os
+import io
+import base64
+import json
+import re
+from dotenv import load_dotenv
+import streamlit as st
+import fitz  # PyMuPDF
+import google.generativeai as genai
+from PIL import Image
+
+# Load environment variables
+load_dotenv()
+
+# Configure Google API Key
+api_key = os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=api_key)
+
+def get_gemini_response(pdf_content, prompt):
+    model = genai.GenerativeModel('gemini-1.5-pro')
+    response = model.generate_content([pdf_content[0], prompt])
+    return response.text
+
+def input_pdf_setup(uploaded_file):
+    if uploaded_file is not None:
+        try:
+            pdf_document = fitz.open(stream=uploaded_file.read(), filetype="pdf")
+            first_page = pdf_document.load_page(0)
+            pix = first_page.get_pixmap()
+
+            img_byte_arr = io.BytesIO()
+            img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+            img.save(img_byte_arr, format='JPEG')
+            img_byte_arr = img_byte_arr.getvalue()
+
+            pdf_parts = [
+                {
+                    "mime_type": "image/jpeg",
+                    "data": base64.b64encode(img_byte_arr).decode()
+                }
+            ]
+            return pdf_parts
+        except Exception as e:
+            st.error(f"Error processing PDF: {e}")
+            return None
+    else:
+        raise FileNotFoundError("No file uploaded")
+
+def clean_and_format_json(response_text):
+    # Extract JSON content
+    json_match = re.search(r'```json\s*(.*?)\s*```', response_text, re.DOTALL)
+    if json_match:
+        json_str = json_match.group(1)
+        # Remove any trailing commas before closing brackets or braces
+        json_str = re.sub(r',\s*([}\]])', r'\1', json_str)
+        return json_str
+    return None
+
+# Streamlit App
+st.set_page_config(page_title="ATS Resume Expert")
+st.header("ATS Resume Parser")
+
+uploaded_file = st.file_uploader("Upload your resume (PDF)...", type=["pdf"])
+
+if uploaded_file is not None:
+    st.write("PDF Uploaded Successfully")
+
+submit = st.button("Parse Resume to JSON")
+
+if submit:
+    if uploaded_file is not None:
+        pdf_content = input_pdf_setup(uploaded_file)
+        if pdf_content:
+            input_prompt = """
+            Parse the content of the resume and convert it into a JSON format. The JSON should include the following fields:
+
+            - Name
+            - Contact Information (phone number, email, address)
+            - Summary/Objective
+            - Skills
+            - Experience (company, position, start date, end date, responsibilities)
+            - Education (institution, degree, start date, end date)
+            - Certifications
+            - Projects (name, description, technologies used)
+            - Languages
+            - Hobbies/Interests
+
+            Provide the output in valid JSON format, enclosed in triple backticks with 'json' specified, like this:
+            ```json
+            {
+                "key": "value"
+            }
+            ```
+            Ensure all JSON is properly formatted and there's no additional text outside the JSON.
+            """
+            response_text = get_gemini_response(pdf_content, input_prompt)
+            
+            # Clean and format the response
+            cleaned_json_str = clean_and_format_json(response_text)
+            
+            if cleaned_json_str:
+                try:
+                    response_json = json.loads(cleaned_json_str)
+                    st.subheader("Parsed Resume in JSON")
+                    st.json(response_json)
+                except json.JSONDecodeError as e:
+                    st.error(f"Error parsing JSON. Please try again.")
+            else:
+                st.error("Unable to extract JSON from the response. Please try again.")
+        else:
+            st.write("Please upload a valid resume")
+    else:
+        st.write("Please upload the resume")

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+python-dotenv
+pdf2image
+Pillow
+google.generativeai
+fitz
+frontend
+PyMuPDF