Merge pull request #39 from bunsenmurder/dev

Version 2.0: Major functionality updates and bug fixes

.gitignore

@@ -49,6 +49,7 @@ nosetests.xml
 coverage.xml
 *.cover
 .hypothesis/
+.pytest_cache/
 
 # Translations
 *.mo
@@ -57,6 +58,8 @@ coverage.xml
 # Django stuff:
 *.log
 local_settings.py
+db.sqlite3
+db.sqlite3-journal
 
 # Flask stuff:
 instance/
@@ -103,8 +106,72 @@ ENV/
 
 # mypy
 .mypy_cache/
+.dmypy.json
+dmypy.json
 
 # PyCharm
 .idea/workspace.xml
 .idea/usage.statistics.xml
 .idea/tasks.xml
+.idea/inspectionProfiles
+
+# Pyre type checker
+.pyre/
+
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+# Backups Files
+*~
+*.bak
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+# Mac General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Mac Thumbnails
+._*
+
+# Mac Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent

.travis.yml

@@ -1,7 +1,8 @@
 language: python
 python:
-  - '3.6'
+  - '3.6.9'
 install:
   - 'pip install pipenv'
   - 'pipenv sync'
+  - 'python -m nltk.downloader stopwords'
 script: 'python -m jobfunnel -s demo/settings.yaml -o demo/'

Pipfile

@@ -7,6 +7,7 @@ verify_ssl = true
 
 [packages]
 jobfunnel = {editable = true,path = "."}
+nltk = "*"
 
 [requires]
 python_version = "3.6"

demo/settings.yaml

@@ -5,29 +5,48 @@
 output_path: './'
 
 # Providers from which to search (case insensitive)
-# use indeed only for speed
 providers:
   - 'Indeed'
   - 'Monster'
-  - 'GlassDoor' # This takes ~10x longer to run than the other providers
+  - 'GlassDoor' # This used to take ~10x longer to run than the other providers
+
 
 # Filters.
 search_terms:
   region:
     province: 'ON'
     city:     'waterloo'
     domain:   'ca'
-    radius:   25
+    radius:   10
 
-# this search is focused on programming
   keywords:
     - 'Python'
+    - 'Java'
 
-# exclude these from the search
 black_list:
   - 'Infox Consulting'
   - 'Terminal'
 
 # Logging level options are: critical, error, warning, info, debug, notset
-# show me only errors
 log_level: 'info'
+
+# Saves duplicates removed by tfidf filter to duplicate_list.csv
+save_duplicates: False
+
+# Turn on or off delaying
+set_delay: True 
+
+# Delaying algorithm configuration
+delay_config:
+    # Functions used for delaying algorithm, options are: constant, linear, sigmoid
+    function: 'linear'
+    # Maximum delay/upper bound for converging random delay
+    delay: 30
+    # Minimum delay/lower bound for random delay  
+    min_delay: 15 
+    # Random delay
+    random: True 
+    # Converging random delay, only used if 'random' is set to True
+    converge: True 
+
+

jobfunnel/__init__.py

@@ -1 +1 @@
-__version__ = '1.1.4'
+__version__ = '2.0.0'

jobfunnel/__main__.py

@@ -12,6 +12,7 @@
 
 providers = {'indeed': Indeed, 'monster': Monster, 'glassdoor': GlassDoor}
 
+
 def main():
     """Main function.
 
@@ -47,7 +48,9 @@ def main():
     jp.update_masterlist()
 
     # done!
-    jp.logger.info("done. see un-archived jobs in " + config['master_list_path'])
+    jp.logger.info(
+        "done. see un-archived jobs in " + config['master_list_path'])
+
 
 if __name__ == '__main__':
     main()