Merge pull request #7 from martinm76/sortedevents

Implemented sorting of events before writing to file. Ignore TRANSP: …

README.md

@@ -1,4 +1,4 @@
-# ical2csv
+# ical2csv w/sorted events by start date
 
 ![alt text](images/ics.png) → ![alt text](images/python.png) → ![alt text](images/csv.png) 
 
@@ -14,11 +14,33 @@ Download the `ical2csv.py` file.
     * **Installation**: `pip install icalendar`
 * ***Python* 3**
 
-## Usage
+***Note:*** pip may be called pip3 on some systems with both python2 and python3 as options.
+
+## Usage of ical2csv
 
 Call the script and pass in the location of the ics file.
 
-Ex: `python ical2csv event.ics`
+Ex: `python ical2csv.py event.ics`
+
+# ical2txt w/sorted events by start date
+
+Like ical2csv.py, it parses an ics file and writes the output to a text-file. This is more of an agenda style.
+
+## Installation of ical2txt
+Download the script or clone the project and get it from there.
+
+### Dependencies for ical2txt
+* ***setuptools*** (just in case : pip3 install setuptools)
+* ***BeautifulSoup4*** (pip3 install beautifulsoup4)
+* ***icalendar*** (pip3 install icalendar)
+	*  [**Homepage**](http://icalendar.readthedocs.org/)
+	*  [**Code**](http://github.com/collective/icalendar)
+
+## Usage of ical2txt
+
+Call the script and pass in the location of the ics file.
+
+Ex: `python ical2txt.py event.ics` / `python3 ical2txt.py event.ics`
 
 ## Contributing
 
@@ -30,10 +52,16 @@ Ex: `python ical2csv event.ics`
 
 ## Credits
 
-Lead Developer - [Erik Cox](https://github.com/erikcox/)
+Lead Developer - ical2csv - [Erik Cox](https://github.com/erikcox/)
+
+Developer - ical2txt - [Martin Møller](https://github.com/martinm76)
 
 Python 3 compatibility and improvements - [bozoslivehere](https://github.com/bozoslivehere/)
 
+Logic and adjustments to sort events chronologically (Google Calendar doesn't do this in its export) - [Martin Møller](https://github.com/martinm76)
+
+Removal of HTML code from events (currently only ical2txt) - [Martin Møller](https://github.com/martinm76)
+
 ## License
 
 The MIT License (MIT)

ical2csv.py

@@ -1,3 +1,5 @@
+#!/usr/bin/python3
+
 import sys
 import os.path
 from icalendar import Calendar
@@ -33,6 +35,7 @@ def open_cal():
 
             for component in gcal.walk():
                 event = CalendarEvent("event")
+                if component.get('TRANSP') == 'TRANSPARENT': continue #skip event that have not been accepted
                 if component.get('SUMMARY') == None: continue #skip blank items
                 event.summary = component.get('SUMMARY')
                 event.uid = component.get('UID')
@@ -64,8 +67,8 @@ def csv_write(icsfile):
         with open(csvfile, 'w') as myfile:
             wr = csv.writer(myfile, quoting=csv.QUOTE_ALL)
             wr.writerow(headers)
-            for event in events:
+            for event in sortedevents:
-                values = (event.summary.encode('utf-8'), event.uid, event.description.encode('utf-8'), event.location, event.start, event.end, event.url)
+                values = (event.summary.encode('utf8').decode(), event.uid, event.description.encode('uft8').decode(), event.location, event.start, event.end, event.url)
                 wr.writerow(values)
             print("Wrote to ", csvfile, "\n")
     except IOError:
@@ -84,5 +87,6 @@ def debug_event(class_name):
     print(class_name.url, "\n")
 
 open_cal()
+sortedevents=sorted(events, key=lambda obj: obj.start) # Needed to sort events. They are not fully chronological in a Google Calendard export ...
 csv_write(filename)
 #debug_event(event)

ical2txt.py

@@ -0,0 +1,157 @@
+#!/usr/bin/python3
+
+import sys
+import os.path
+from icalendar import Calendar
+import csv
+from bs4 import BeautifulSoup
+import warnings
+from dateutil.parser import parse
+
+warnings.filterwarnings("ignore", category=UserWarning, module='bs4') # We don't want warnings about URL's. We just what the URL printed, if there.
+
+filename = sys.argv[1]
+# TODO: use regex to get file extension (chars after last period), in case it's not exactly 3 chars.
+file_extension = str(sys.argv[1])[-3:]
+headers = ('Summary', 'UID', 'Description', 'Location', 'Start Time', 'End Time', 'URL')
+
+class CalendarEvent:
+    """Calendar event class"""
+    summary = ''
+    uid = ''
+    description = ''
+    location = ''
+    start = ''
+    end = ''
+    url = ''
+
+    def __init__(self, name):
+        self.name = name
+
+events = []
+
+def removehtml(html):
+    # Almost word for word copy from here: https://stackoverflow.com/questions/328356/extracting-text-from-html-file-using-python
+
+    soup = BeautifulSoup(html, features="html.parser")
+    # kill all script and style elements
+    for script in soup(["script", "style"]):
+        script.extract() # remove it
+
+    text = soup.get_text() # Get plain text
+
+    # break into lines and remove leading and trailing space on each
+    lines = (line.strip() for line in text.splitlines())
+    # break multi-headlines into a line each
+    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+    # drop blank lines
+    text = '\n'.join(chunk for chunk in chunks if chunk)
+
+    return text
+
+
+def open_cal():
+    if os.path.isfile(filename):
+        if file_extension == 'ics':
+            print("Extracting events from file:", filename, "\n")
+            f = open(sys.argv[1], 'rb')
+            gcal = Calendar.from_ical(f.read())
+
+            for component in gcal.walk():
+                event = CalendarEvent("event")
+                if component.get('TRANSP') == 'TRANSPARENT': continue #skip event that have not been accepted
+                if component.get('SUMMARY') == None: continue #skip blank items
+                event.summary = component.get('SUMMARY')
+                event.uid = component.get('UID')
+                if component.get('DESCRIPTION') == None: continue #skip blank items
+                event.description = component.get('DESCRIPTION')
+                event.location = component.get('LOCATION')
+                if hasattr(component.get('dtstart'), 'dt'):
+                    event.start = component.get('dtstart').dt
+                if hasattr(component.get('dtend'), 'dt'):
+                    event.end = component.get('dtend').dt
+
+
+                event.url = component.get('URL')
+                events.append(event)
+            f.close()
+        else:
+            print("You entered ", filename, ". ")
+            print(file_extension.upper(), " is not a valid file format. Looking for an ICS file.")
+            exit(0)
+    else:
+        print("I can't find the file ", filename, ".")
+        print("Please enter an ics file located in the same folder as this script.")
+        exit(0)
+
+
+def txt_write(icsfile):
+    txtfile = icsfile[:-3] + "txt"
+    prevdate=""
+    spent=0
+    evcount=0
+    evskip=0
+    istart=0
+    istop=4102441200.0 # The year 2100. Hopefully this will not be in use by then ...
+    if sys.argv[2] != '':
+        istart=parse(sys.argv[2]).timestamp()
+    if sys.argv[3] != '':
+        istop=parse(sys.argv[3]).timestamp()
+    print("Processing events :", end=" ")
+    try:
+        with open(txtfile, 'w') as myfile:
+            for event in sortedevents:
+
+                if prevdate != event.start.strftime("%Y-%m-%d") and spent > 0: # Make a header for each day
+                    if prevdate != '': # If you don't want a summary of the time spent added, comment this section. 
+                        th=divmod(spent, 3600)[0]
+                        tm=divmod(spent, 3600)[1]/60
+                        myfile.write("\nTime Total: " + '{:02.0f}'.format(th) + ":" + '{:02.0f}'.format(tm) + "\n")
+                        spent=0
+                if event.start.timestamp() > istart and event.start.timestamp() < istop:
+                    if prevdate != event.start.strftime("%Y-%m-%d"): # Make a header for each day
+                        prevdate = event.start.strftime("%Y-%m-%d")
+                        myfile.write("\nWorklog, " + prevdate + "\n===================\n")
+
+                    duration = event.end - event.start
+                    ds = duration.total_seconds()
+                    spent += ds
+                    hours = divmod(ds, 3600)[0]
+                    minutes = divmod(ds,3600)[1]/60
+                    description=removehtml(event.description.encode('utf-8').decode())
+                    values = event.start.strftime("%H:%M:%S") + " - " + event.end.strftime("%H:%M:%S") + " (" + '{:02.0f}'.format(hours) + ":" + '{:02.0f}'.format(minutes) + ") " + event.summary.encode('utf-8').decode()
+                    if event.location != '': values = values + " [" + event.location + "]" # Only include location if there is one
+
+                    # Remove Google Meet and Skype Meeting part of description
+                    trimmed=description.split('-::~')[0].split('......')[0]
+                    #print("DescLen: " + str(len(description)) + " TrimmedLen: " + str(len(trimmed)) + " : " + trimmed) # For debugging
+                    description=trimmed
+                    if description != '':
+                        values = values + "\n" + description + "\n"
+                    myfile.write(values+"\n")
+                    print("", end=".")
+                    evcount+=1
+                else:
+                    print("", end="S")
+                    evskip+=1
+
+            print("\n\nWrote " + str(evcount) + " events to ", txtfile, " and skipped ", str(evskip), " events\n")
+    except IOError:
+        print("Could not open file!")
+        exit(0)
+
+
+def debug_event(class_name):
+    print("Contents of ", class_name.name, ":")
+    print(class_name.summary)
+    print(class_name.uid)
+    print(class_name.description)
+    print(class_name.location)
+    print(class_name.start)
+    print(class_name.end)
+    print(class_name.url, "\n")
+
+open_cal()
+sortedevents=sorted(events, key=lambda obj: obj.start)
+txt_write(filename)
+#debug_event(event)