Initial commit

Author: vpascal

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

.gitignore

@@ -0,0 +1,125 @@
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# 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/

README.md

@@ -0,0 +1,2 @@
+# DARS
+ 

extract.py

@@ -0,0 +1,72 @@
+import tabula
+import pandas as pd
+import re
+import subprocess
+import os
+
+def extract(file):
+    df = tabula.read_pdf(file, pages="1,2", area=(9.405,41.085,600.435,770.715),nospreadsheet = True,guess=False, pandas_options={'header': None})
+    pid = df.iloc[3,0]
+    name = df.iloc[4,0].replace(" ","").replace(".","").lower().title()
+    
+    pid = re.findall(r'\d+',pid)[0]
+    pid ="P{}".format(pid)
+
+    # this extracts hours attempted and gpa
+    vals = df.iloc[:,0]
+    vals = vals[vals.str.contains('TRANSCRIPT|T RANSCRIPT',na=False)].to_string()
+    vals = vals.split('|')
+
+    earned = float(vals[2])
+    gpa = "Fail" if float(vals[3])<3 else u'\u2714'
+
+    df = df.iloc[:,0]
+    df = df[df.str.contains('Fa\d+\s+|Sp\d+\s+|Su\d+\s+',na=False)]
+
+    # this extracts lines that begin with fall, spring or summer untill it gets to the |
+    df1 = df[df.str.contains('^Fa\d+\s+|^Sp\d+\s+|^Su\d+\s+',na=False)]
+    df1 = df1.iloc[:, ].str.extract('([^\|]+)')
+
+    # this extracts lines where course information is in the middle of the line
+
+    df2 = df[df.str.contains('^[^Fa\d+\s+]|^[^Sp\d+\s+]|^[^Su\d+\s+]',na=False)]
+    df2 = df.iloc[:, ].str.extract('(Fa\d+\s+\w*(.*)|Sp\d+\s+\w*(.*)|Su\d+\s+\w*(.*))')
+    df2 = df2.iloc[:,0:1]
+
+    total = pd.concat([df1,df2],ignore_index=True)
+    total.rename(columns={ total.columns[0]: "course" }, inplace = True)
+    total = total.drop_duplicates()
+    total['course'] =total['course'].str.split('|').str[0]
+    total['course'] =total['course'].str.lstrip()
+
+    total['term'] = total['course'].str[0:4]
+    total['class'] = total['course'].str[4:13]
+    total['course'] = total['course'].str[13:]
+    total['hours'] = total['course'].str.extract("(\d*\.?\d+)", expand=True)
+    total['course'] = total['course'].str.replace(r"(\d*\.?)","", regex=True)
+    total['course'] = total['course'].str.lstrip()
+    total['grade'] = total['course'].str[0:2]
+    total['acad_year'] = '20'+total['term'].str[2:]
+    total.drop(columns=['course'], inplace=True)
+    total.drop_duplicates(inplace=True)
+    total.sort_values(by=['acad_year','term'], inplace=True)
+  
+    fn = "Fail" if total.grade.str.contains('FN',regex=True).any() else u'\u2714'
+    pr = 'Fail' if total.grade.str.contains('PR', regex=True).any() else u'\u2714'
+    wp = "Fail" if total.grade.str.contains('WP', regex=True).any() else u'\u2714'
+    ip = "Fail" if total.grade.str.contains('IP', regex=True).any() else u'\u2714'
+    lower_C = "Fail" if total.grade.str.contains( 'C\-|^D$|^F$', regex=True).any() else u'\u2714'
+    
+    file = os.path.basename(file)
+
+    temp = [name, file, gpa, pr, fn,wp,ip,lower_C]
+    return(temp)
+    #return(total)
+# pdf launcher
+def launcher(file):
+    command = "C:\Program Files (x86)\Adobe\Acrobat Reader DC\Reader\AcroRd32.exe"
+    return subprocess.Popen([command, file], stdout=subprocess.PIPE)
+
+if __name__ == "__main__":
+    extract()
+    launcher()