LinkedIn Scraper

.gitignore

@@ -0,0 +1,175 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+.gradio/

app.py

@@ -4,9 +4,9 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-
+from tools.linkedin import LinkedInProfileScraperTool
 from Gradio_UI import GradioUI
-
+import os 
 # Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
 def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
@@ -35,6 +35,7 @@ def get_current_time_in_timezone(timezone: str) -> str:
 
 
 final_answer = FinalAnswerTool()
+linkedin_scraper_tool = LinkedInProfileScraperTool()
 
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
@@ -44,6 +45,7 @@ max_tokens=2096,
 temperature=0.5,
 model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
 custom_role_conversions=None,
+token = os.getenv("HFTOKEN")
 )
 
 
@@ -55,9 +57,9 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[linkedin_scraper_tool, final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
-    verbosity_level=1,
+    verbosity_level=2,
     grammar=None,
     planning_interval=None,
     name=None,

tools/linkedin.py

@@ -0,0 +1,26 @@
+from smolagents.tools import Tool
+import requests
+import os 
+class LinkedInProfileScraperTool(Tool):
+    name = "linkedin_profile_scraper"
+    description = "Fetches the LinkedIn profile information for a given url."
+    inputs = {'profile_url': {'type': 'string', 'description': 'The LinkedIn URL to fetch information for.'}}
+    output_type = "object"
+
+    def forward(self, profile_url: str) -> dict:
+        url = "https://linkedin-data-api.p.rapidapi.com/get-profile-data-by-url"
+        querystring = {"url": profile_url}
+        headers = {
+            "x-rapidapi-key": os.getenv("rapidapi"),
+            "x-rapidapi-host": "linkedin-data-api.p.rapidapi.com"
+        }
+
+        try:
+            response = requests.get(url, headers=headers, params=querystring)
+            response.raise_for_status()  
+            profile_data = response.json()
+            keys_to_extract = ['firstName', 'lastName', 'summary', 'educations', 'position', 'skills', 'projects']
+            filtered_data = {key: profile_data[key] for key in keys_to_extract if key in profile_data}
+            return filtered_data 
+        except requests.exceptions.RequestException as e:
+            return f"An error occurred while fetching the LinkedIn profile: {str(e)}"

tools/visit_webpage.py

@@ -15,7 +15,7 @@ class VisitWebpageTool(Tool):
             import requests
             from markdownify import markdownify
             from requests.exceptions import RequestException
-
+            import re
             from smolagents.utils import truncate_content
         except ImportError as e:
             raise ImportError(