Commit d09a0594 authored by Landon DeCoito's avatar Landon DeCoito

made parscript a BIT nicer and revamped the cleanup() function

parent 7241df82
#print "and we begin"
# print "and we begin"
# third party imports
from bs4 import BeautifulSoup
from datetime import date, time
import requests
def cleanup(str): #this function cleans up some of the useless html leftovers to characters we can actually use
str = str.replace("&", "&")
str = str.replace(" ", " ")
str = str.replace("–", "-")
str = str.replace("&lt;", "<")
str = str.replace("&gt;", ">")
str = str.replace("<br/>", "\n")
str = str.replace("Publish event on the Calendar?: TRUE \n" , "")
str = str.replace("Performing any medical procedures?: FALSE \n" , "")
str = str.replace("Parking Needed?: FALSE \n" , "")
str = str[0:len(str) - 1]
str = str.replace("&rsquo;", "'")
# this function cleans up some of the useless html leftovers to characters we can actually use
def cleanup(dirtystring):
replacements = [
("&amp;", "&"),
("&nbsp;", " "),
("&ndash;", "-"),
("&lt;", "<"),
("&gt;", ">"),
("<br/>", "\n"),
("Publish event on the Calendar?: TRUE \n", ""),
("Performing any medical procedures?: FALSE \n", ""),
("Parking Needed?: FALSE \n", ""),
("\n\n\n", "\n"),
("\n\n", "\n"),
("&rsquo;", "'")
]
for replacement in replacements:
dirtystring.replace(replacement[0], replacement[1])
dirtystring = dirtystring[0:len(dirtystring) - 1]
return str
class eventException: #this class is just an exception for our use
def __init__(self,message):
class eventException: # this class is just an exception for our use
def __init__(self, message):
self.__message = message
#self.__exceptionlist = []
def __str__(self):
return self.__message
#convertTime accepts strings in the form of ""
def convertTime(stri): #this function is used for splicing the event times.
if (stri[-2:] == "pm" or stri[-2:] == "PM"): #checks to see if the time presented is pm
if not ((stri[0] == "1") and (stri[1] == "2")): #if the time is pm, then the 12:00 hour is noon and shouldn't get 12 added to it
try: #this try block works with the exception handler to add 12 to any pm times
# convertTime accepts strings in the form of ""
def convertTime(stri): # this function is used for splicing the event times.
if (stri[-2:] == "pm" or stri[-2:] == "PM"): # checks to see if the time presented is pm
if not ((stri[0] == "1") and (stri[1] == "2")): # if the time is pm, then the 12:00 hour is noon and shouldn't get 12 added to it
try: # this try block works with the exception handler to add 12 to any pm times
stri = stri.replace(stri[0:2], str(int(stri[0:2]) + 12), 1)
#print "I did the first one " + stri
# print "I did the first one " + stri
except:
stri = stri.replace(stri[0], str(int(stri[0]) + 12), 1)
#print "I did the NOT first one " + stri
if ":" in stri: #this if/else reliably converts the time to minutes. accepts either "hour:minute" or simply "hour"
# print "I did the NOT first one " + stri
if ":" in stri: # this if/else reliably converts the time to minutes. accepts either "hour:minute" or simply "hour"
try:
return ((int(stri[0:2])) * 60) + int(stri[3:5])
except:
......@@ -46,7 +57,7 @@ def convertTime(stri): #this function is used for splicing the event times.
return (int(stri[0:2])) * 60
except:
return (int(stri[0])) * 60
elif (stri[-2:] == "am" or stri[-2:] == "AM"): #checks if the time presented is am, and executes identical code from the pm block, just without adding 12
elif (stri[-2:] == "am" or stri[-2:] == "AM"): # checks if the time presented is am, and executes identical code from the pm block, just without adding 12
if ":" in stri:
try:
return (int(stri[0:2]) * 60) + int(stri[3:5])
......@@ -68,117 +79,115 @@ def load_data():
"""
dictlist = []
DaysOfWeek = {
"Sunday" : 0,
"Monday" : 1,
"Tuesday" : 2,
"Wednesday" : 3,
"Thursday" : 4,
"Friday" : 5,
"Saturday" : 6,
"Sunday": 0,
"Monday": 1,
"Tuesday": 2,
"Wednesday": 3,
"Thursday": 4,
"Friday": 5,
"Saturday": 6,
}
notProvide = "Not Provided"
counter = 0
soup = BeautifulSoup(cleanup(requests.get("http://25livepub.collegenet.com/calendars/events_all.xml").text), "lxml") #creates soup of the xml
#creates a list of all the entry tags from the xml
soup = BeautifulSoup(cleanup(requests.get("http://25livepub.collegenet.com/calendars/events_all.xml").text), "lxml")
# creates a list of all the entry tags from the xml
entries = soup.findAll('entry')
#indexs an entry in the list of entries
# indexs an entry in the list of entries
for entry in entries:
error = []
#pulls up an entries in the list of entries, finds the title tag and .text deletes all xml tags and returns just the text as a string
# pulls up an entries in the list of entries, finds the title tag and .text deletes all xml tags and returns just the text as a string
entry_title = entry.title.text
entry_content = entry.content.text
uniqueid = entry.id.text
#makes it easy to find as things may be unevenly spaced
entry_content = entry_content.replace("\n\n\n" , "\n")
entry_content = entry_content.replace("\n\n" , "\n")
#check clearcontent function
entry_content = cleanup(entry_content) #we might just get rid of this one
# makes it easy to find as things may be unevenly spaced
entry_content = entry_content.replace("\n\n\n", "\n")
entry_content = entry_content.replace("\n\n", "\n")
# check clearcontent function
entry_content = cleanup(entry_content) # we might just get rid of this one
#each piece of content may is seperated by a newline, entry_detailes creates a list
# each piece of content may is seperated by a newline, entry_detailes creates a list
entry_detailes = entry_content.split("\n")
# in entry detailes list normally the conditions go as follow
# [0] is the location
# [1] is the date
# [2] is the description
# either conditions follows
# [0] is date
# [0] is location
# [1] is date
# [0] is date
# [1] is description
#in entry detailes list normally the conditions go as follow
#[0] is the location
#[1] is the date
#[2] is the description
#either conditions follows
#[0] is date
#[0] is location
#[1] is date
#[0] is date
#[1] is description
#sometimes the location or description is not given; however, the location always goes before date and
#the description always follows the date. The date is always present. See examples above
#(A) if the location is not given then the date must be index [0]
#(B) if the length of the list = 1 and date is index [0] --> location not given & description is not given
#(C) if the length of the list = 2 and date is index [0] --> location not given but description is given at [1]
#(D) if the location is given then the date must be index [1]
#(E) if the length of the list = 2 and date is index [1] --> location is given at [0] but description is not given
#(F) if the length of the list = 3 and date is index [1] --> location is given at [0] and description is given at [2]
#the two if statements finds the date string. The date string always starts with
#Monday Tuesday Wednesday Thursday Friday Saturday Sunday or Ongoing and the date
#is always on either [0] or [1]
#see (A) above
# sometimes the location or description is not given; however, the location always goes before date and
# the description always follows the date. The date is always present. See examples above
# (A) if the location is not given then the date must be index [0]
# (B) if the length of the list = 1 and date is index [0] --> location not given & description is not given
# (C) if the length of the list = 2 and date is index [0] --> location not given but description is given at [1]
# (D) if the location is given then the date must be index [1]
# (E) if the length of the list = 2 and date is index [1] --> location is given at [0] but description is not given
# (F) if the length of the list = 3 and date is index [1] --> location is given at [0] and description is given at [2]
# the two if statements finds the date string. The date string always starts with
# Monday Tuesday Wednesday Thursday Friday Saturday Sunday or Ongoing and the date
# is always on either [0] or [1]
# see (A) above
try:
if entry_detailes[0].split(",")[0] in DaysOfWeek:
#See (B)
# See (B)
if len(entry_detailes) == 1:
location = notProvide
date = entry_detailes[0]
description = notProvide
#see (C)
# see (C)
elif len(entry_detailes) == 2:
location = notProvide
date = entry_detailes[0]
description = entry_detailes[1]
#This extra case was made because one entry had the description split into two by a
#newline so it registered as two descriptions making the length = 3
elif len(entry_detailes) == 3:
# This extra case was made because one entry had the description split into two by a
# newline so it registered as two descriptions making the length = 3
elif len(entry_detailes) == 3:
location = notProvide
date = entry_detailes[0]
description = entry_detailes[1] + " " + entry_detailes[2]
#this will print if the code has failed to account for something in detailes, but it works as of December 26th 2017
# this will print if the code has failed to account for something in detailes, but it works as of December 26th 2017
else:
raise eventException("failed to account for detail in entry_detailes when date element is index 0 on entry_detailes list")
#see (D) above
# see (D) above
elif entry_detailes[1].split(",")[0] in DaysOfWeek:
#See (E)
# See (E)
if len(entry_detailes) == 2:
location = entry_detailes[0]
date = entry_detailes[1]
description = notProvide
#See (F)
# See (F)
elif len(entry_detailes) == 3:
location = entry_detailes[0]
date = entry_detailes[1]
description = entry_detailes[2]
#This extra case was made because one entry had the description split into two by a
#newline so it registered as two descriptions making the length = 3
# This extra case was made because one entry had the description split into two by a
# newline so it registered as two descriptions making the length = 3
elif len(entry_detailes) == 4:
location = entry_detailes[0]
date = entry_detailes[1]
description = entry_detailes[2] + " " + entry_detailes[3]
#this will print if the code has failed to account for something in detailes
# this will print if the code has failed to account for something in detailes
else:
raise eventException("failed to account for detail in entry_detailes when date element is index 1 on entry_detailes list")
#this will print if the above if statements failed to find the date block
# this will print if the above if statements failed to find the date block
else:
raise eventException("failed to find and account for date element in entry_detailes list")
except eventException as e:
......@@ -227,7 +236,7 @@ def load_data():
timestop = convertTime(time[1])
except ValueError:
raise eventException(str(time))
if timestop == None:
if timestop is None:
raise eventException(str(time))
if not (time[0][-2:] == "am") and not (time[0][-2:] == "pm"):
if (time[1][-2:] == "am"):
......@@ -239,8 +248,6 @@ def load_data():
except Exception:
error.append("Error with time reformatting")
'''print "-----------------------------------------------------------------------------"
print location
print day
......@@ -252,10 +259,11 @@ def load_data():
print description
print "----------------------------------------------------------------------------"
'''
if (error == []):
dictlist.append({"id":uniqueid, "title":entry_title, "dayofweek":day, "dayofmonth":monthday, "month":month, "year":year, "timestart":timestart, "timestop":timestop, "location":location, "description":description})
dictlist.append({"id": uniqueid, "title": entry_title, "dayofweek": day, "dayofmonth": monthday, "month": month, "year": year, "timestart": timestart, "timestop": timestop, "location": location, "description": description})
else:
dictlist.append({"id":uniqueid, "error":error})
dictlist.append({"id": uniqueid, "error": error})
return dictlist
# everything in the house is fuzzy, stupid dogs were acting like pollinators, if that's how you even spell it
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment