Merge pull request #2 from simo97/scrapper

[UPDATE] Finish to add scraping engine and some scraping logic

Author: Sanix-Darker

.gitignore

@@ -0,0 +1,194 @@
+
+# Created by https://www.gitignore.io/api/sonar,flask,python,sonarqube
+# Edit at https://www.gitignore.io/?templates=sonar,flask,python,sonarqube
+
+### Flask ###
+instance/*
+!instance/.gitignore
+.webassets-cache
+
+### Flask.Python Stack ###
+# 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
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# 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/
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+
+# C extensions
+
+# Distribution / packaging
+
+# 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.
+
+# Installer logs
+
+# Unit test / coverage reports
+
+# Translations
+
+# Django stuff:
+
+# Flask stuff:
+
+# Scrapy stuff:
+
+# Sphinx documentation
+
+# PyBuilder
+
+# Jupyter Notebook
+
+# IPython
+
+# pyenv
+
+# celery beat schedule file
+
+# SageMath parsed files
+
+# Environments
+
+# Spyder project settings
+
+# Rope project settings
+
+# mkdocs documentation
+
+# mypy
+
+# Pyre type checker
+
+### Python Patch ###
+.venv/
+
+### Sonar ###
+#Sonar generated dir
+/.sonar/
+
+### SonarQube ###
+# SonarQube ignore files.
+#
+# https://docs.sonarqube.org/display/SCAN/Analyzing+with+SonarQube+Scanner
+# Sonar Scanner working directories
+.sonar/
+.scannerwork/
+
+# http://www.sonarlint.org/commandline/
+# SonarLint working directories, configuration files (including credentials)
+.sonarlint/
+
+# End of https://www.gitignore.io/api/sonar,flask,python,sonarqube

README.md

@@ -44,7 +44,7 @@ PyToMe have a list of website where it wil fetch data(jobs/projects) and will no
 [Sanix-darker](https://github.com/sanix-darker)
 
 ## Contributors
-[Adonis Simo](https://github.com/simo97)
+[Adonis Simo (root)](https://github.com/simo97)
 
 ## Organization
 [Python Cameroon](https://github.com/python-cameroun)

node_modules/mime/.npmignore api/__init__.pynode_modules/mime/.npmignore renamed to api/__init__.py

@@ -0,0 +1,18 @@
+"""
+An example on how to use this code.
+
+** How it work **
+1 - import available scrapers
+2 - import Scraping engine
+3 - import default callback method, json_callback_writer() 
+4 - create an instance of the scraping engine with the 2 default available scraper
+5 - run it by calling it run() method and pass to it the utils's method which will be use as callback
+
+normally you will have a scrapper.json file in the current folder with result of scraping
+"""
+from scraper.scraper import GitHubJobScrapper, PythonJobScrapper
+from scraper.engine import ScraperEngine
+from scraper.utils import json_callback_writer
+
+app = ScraperEngine([GitHubJobScrapper(), PythonJobScrapper()])
+app.run(json_callback_writer)

api/example.py

@@ -0,0 +1,24 @@
+from scraper.mixins import PyToMeBaseScrapperMixin
+
+
+class ScraperEngine:
+
+    _data = []
+    _scrapers = []
+    """
+    Plugin system to load and unload scrapers
+    """
+    def __init__(self, plugins: list=list(), *args, **kwargs):
+        self._data = []
+        self._scrapers = []
+        for scraper in plugins:
+            if isinstance(scraper, PyToMeBaseScrapperMixin): #  only consider class based on PyToMeBaseScrapperMixin
+                self._scrapers.append(scraper)
+
+    def run(self, cb):
+        scrapers = self._scrapers
+        scrp_data = []
+        for scraper in scrapers:
+            scrp_data += scraper.launch() #  run and add result to the same var here
+        self._data = scrp_data
+        cb(self._data) #  the callback here

api/requirements.txt

@@ -0,0 +1,18 @@
+"""
+An example on how to use this code.
+
+** How it work **
+1 - import available scrapers
+2 - import Scraping engine
+3 - import default callback method, json_callback_writer() 
+4 - create an instance of the scraping engine with the 2 default available scraper
+5 - run it by calling it run() method and pass to it the utils's method which will be use as callback
+
+normally you will have a scrapper.json file in the current folder with result of scraping
+"""
+from scraper.scraper import GitHubJobScrapper, PythonJobScrapper
+from scraper.engine import ScraperEngine
+from scraper.utils import json_callback_writer
+
+app = ScraperEngine([GitHubJobScrapper(), PythonJobScrapper()])
+app.run(json_callback_writer)

node_modules/union/test/fixtures/index.js api/scraper/__init__.pynode_modules/union/test/fixtures/index.js renamed to api/scraper/__init__.py

@@ -0,0 +1,79 @@
+"""
+The base mixin used to implement the different scraper
+
+TODO : Write a complete and working doc
+TODO : Write tests
+TODO : Let the code follow PEP 8 Coding style
+"""
+
+import requests
+import shortuuid as shuuid
+from bs4 import BeautifulSoup
+import time
+
+NO_DESCRIPTION = 'No description provided by the site'
+
+
+class PyToMeBaseScrapperMixin:
+    """
+    default url : https://pythonjobs.github.io/
+    """
+
+    base_url = ''
+    job_block = []
+    job_data_set = []
+
+    def __init__(self, base_url, *args, **kwargs):
+        if base_url == None:
+            self.base_url = 'https://pythonjobs.github.io/' 
+        else:
+            self.base_url = base_url
+        self.job_block = []
+
+    def get_datablocks(self,page_content):
+        """
+        Retrive all the block from the targeted page which represents job info,
+        result should be on the form of 
+        [
+            'html content here',
+            'html content here',
+            ......
+        ] # to be parsed one by one with get_block_content() 
+        """
+        raise NotImplementedError('This method has not being implemented, the current class should be use only by inheritance')
+
+    def get_block_content(self):
+        """
+        Retrive the content of one block of data, data should be shaped as follow
+        {
+            'job_title':'',
+            'job_description:'',
+            'job_date':'',
+            'job_location':'',
+            'job_details_link':'',
+            'job_compagny':'',
+            'job_site':'', # where the job has been scrapped
+            'job_hash':'' # built by using shortuuuid() lib by combining job_title+job_compagny+job_date str
+        }
+        """
+        raise NotImplementedError('This method has not being implemented, the current class should be use only by inheritance')
+    
+    def _log_result(self):
+        #print(self.job_block)
+        pass
+
+    def launch(self):
+        self.__init__()
+
+        if self.job_block == []:
+            page_response = requests.get(self.base_url)
+            page_content = BeautifulSoup(page_response.content, 'html.parser')
+            self.get_datablocks(page_content)
+        self.get_block_content()
+        return self.get_job_dataset()
+
+    def get_job_dataset(self):
+        """
+        Just return the current dataset of job fetched or not yet fetched
+        """
+        return self.job_data_set