cleaned up getconnectedscript and made error handling even better!

mason-today/getconnectedscript.py

-import requests
-from bs4 import BeautifulSoup
+# app imports
 from parscript import cleanup, convertTime
+
+# third party imports
 import feedparser
+from bs4 import BeautifulSoup
+import requests
+
+# DEV REMINDER: CHANGE THE LINES IN INTIALISATION ERROR MESSAGE (LINE 138)
 
-# TODO: ADD "getconnected" ATTRIBUTE TO LOAD_DATA DICTLIST
 
 def splitAndConvertTime(strin):
     strin = strin.replace(" ", "")
     strin = strin.split("-")
-    returnlist = ["",""]
+    returnlist = ["", ""]
     returnlist[1] = convertTime(strin[1])
-    if not (strin[0][-2:] == "am" or strin[0][-2:] == "AM") and not (strin[0][-2:] == "pm" or strin[0][-2:] == "PM"):
+    if not (strin[0][-2:] == "am" or strin[0][-2:] == "AM") \
+            and not (strin[0][-2:] == "pm" or strin[0][-2:] == "PM"):
         if (strin[1][-2:] == "am"):
             returnlist[0] = convertTime(strin[0] + "am")
         else:
@@ -19,23 +24,30 @@ def splitAndConvertTime(strin):
         returnlist[0] = convertTime(strin[0])
     return returnlist
 
+
 def load_getconn_data():
-    feedtext = requests.get("https://getconnected.gmu.edu/events/events.rss").text
+    feedtext = requests.get(
+            "https://getconnected.gmu.edu/events/events.rss").text
     feedtext = cleanup(feedtext)
 
     # this calls the RSS feed parser from !feedparser
     feed = feedparser.parse(feedtext)
 
     dictlist = []
+    error = []
 
     for entry in feed.entries:
+        # this collects the attributes which are always there
+        # also creates the Soup and sets up for the rest of the parsing
+        try:
             uniqueid = entry.id[-7:]
             # print uniqueid
 
             title = entry.title
             # print title
 
-        sumdetsoup = BeautifulSoup(entry.summary_detail["value"].encode("utf-8"), "html.parser")
+            sumdetsoup = BeautifulSoup(entry.summary_detail["value"]
+                                       .encode("utf-8"), "html.parser")
 
             location = [sumdetsoup.div.span.text]
             # print location
@@ -43,32 +55,51 @@ def load_getconn_data():
             description = sumdetsoup.find_all("div")[1].text
             # print description
 
-        
             datetime = sumdetsoup.b.text
             # print datetime
+        except Exception as e:
+            error.append(str(e))
 
         # this handles events which start and end on the same day
-        if (datetime.count("(") == 1):
+        # if we've found an error, there's not point in continuing
+        if (datetime.count("(") == 1) and (error == []):
+            # parses out date info
+            try:
                 datesplit = datetime.split(", ")
                 weekday = datesplit[0]
                 temp = datesplit[1].split(" ")
                 monthday = temp[1]
                 month = temp[0]
                 year = datesplit[2][:5]
+            except Exception as e:
+                error.append(str(e))
 
             # uses helper function to get the start and end time
+            try:
                 parsedtimelist = splitAndConvertTime(datesplit[2][6:-1])
                 timestart = parsedtimelist[0]
                 timestop = parsedtimelist[1]
-
-            dictlist.append({"id":uniqueid, "title":title, "dayofweek":weekday, "dayofmonth":monthday, "month":month, 
-                            "year":year, "timestart":timestart, "timestop":timestop, "location":location, "description":description})
-        
-        # this handles events which start on one day and end on another
+            except Exception as e:
+                error.append(str(e))
+
+            # appends the dictlist if no errors were found
+            if error == []:
+                dictlist.append({
+                                "multiday": False, "id": uniqueid,
+                                "title": title, "dayofweek": weekday,
+                                "dayofmonth": monthday, "month": month,
+                                "year": year, "timestart": timestart,
+                                "timestop": timestop, "location": location,
+                                "description": description
+                                })
             else:
-            datesplit = datetime.split(" - ")
-
+                dictlist.append({"id": uniqueid, "error": str(e),
+                                 "errorlocation": ""})
+        # this handles events which start on one day and end on another
+        elif error == []:
             # getting the information for the start day/time
+            try:
+                datesplit = datetime.split(" - ")
                 tempsplits = datesplit[0].split(", ")
                 weekday = tempsplits[0]
                 month = tempsplits[1].split(" ")[0]
@@ -76,8 +107,11 @@ def load_getconn_data():
                 year = tempsplits[2].split(" ")[0]
                 timestart = datesplit[0].split("(")[1][:-1]
                 timestart = convertTime(timestart)
+            except Exception as e:
+                error.append(str(e))
 
             # getting the information for the end day/time
+            try:
                 tempsplits = datesplit[1].split(", ")
                 endweekday = tempsplits[0]
                 endmonth = tempsplits[1].split(" ")[0]
@@ -85,15 +119,30 @@ def load_getconn_data():
                 endyear = tempsplits[2].split(" ")[0]
                 timestop = datesplit[1].split("(")[1][:-1]
                 timestop = convertTime(timestop)
+            except Exception as e:
+                error.append(str(e))
+
+            # append the dictlist if no errors were found
+            if error == []:
+                dictlist.append({
+                                "multiday": True, "id": uniqueid,
+                                "title": title, "dayofweek": weekday,
+                                "dayofmonth": monthday, "month": month,
+                                "year": year, "timestart": timestart,
+                                "timestop": timestop, "location": location,
+                                "description": description,
+                                "enddayofweek": endweekday,
+                                "enddayofmonth": endmonthday,
+                                "endmonth": endmonth, "endyear": endyear
+                                })
+            else:
+                dictlist.append({"id": uniqueid, "error": str(e)})
+        else:
+            dictlist.append("error": "issue in initialization of event.\
+                            check lines 40-56 in getconnectedscript.py")
 
-            dictlist.append({"id":uniqueid, "title":title, "dayofweek":weekday, "dayofmonth":monthday, "month":month, 
-                            "year":year, "timestart":timestart, "timestop":timestop, "location":location, "description":description,
-                            "enddayofweek":endweekday, "enddayofmonth":endmonthday, "endmonth":endmonth, "endyear":endyear})
     return dictlist
 
-# dictlist.append({"id":uniqueid, "title":entry_title, "dayofweek":weekday, "dayofmonth":monthday, "month":month, "year":year, "timestart":timestart, "timestop":timestop, "location":location, "description":description})
-# This was intended to figure out what objects are in each entry and what appears only sometimes
-# The results are:
 # Every event has:
 # -------summary
 # -------published_parsed