sanity checking and updating to parse argos (cvc report) dump

pipelines.py

@@ -1953,12 +1953,12 @@ def scrape_for_db():
 def argos_data():
     global dean,gp
     
-    f2 = codecs.open('cache/enrollment_sp23.csv','w','utf-8')
+    f2 = codecs.open('cache/enrollment_argos_fa23.csv','w','utf-8')
     writer = csv.writer(f2)
     headers = 'gp dean dept num code crn name act site'.split(' ')
     writer.writerow(headers)
     
-    f = codecs.open('cache/sched_draft_sp23.csv','r','utf-8')
+    f = codecs.open('cache/sched_draft_fa23.csv','r','utf-8')
     reader = csv.reader(f, delimiter=',')
     headers = next(reader)
     for r in reader:
@@ -1979,6 +1979,87 @@ def argos_data():
         print(site)
         writer.writerow([my_gp,my_dean,dept,num,code,crn,name,act,site])
 
+def days_times(s):
+    parts = re.search(r'^([MTWThRF]+)\s?(.*?)$',s)
+    if parts:
+        day = parts.group(1)
+        time = parts.group(2)
+        parts2 = re.search(r'^(.*)\s?-\s?(.*)$',time)
+        if parts2:
+            time_start = parts2.group(1).strip()
+            time_end = parts2.group(2).strip()
+            return day, time_start, time_end
+        return day, time, ''
+    return '','',''
+
+def remove_year(s):
+    s = re.sub(r'\-', '/', s)
+    if len(s)>5: return s[5:]
+    return s
+
+def argos_data_from_cvc():
+    global dean,gp
+    short_sem = 'su23'
+    
+    f3 = codecs.open('cache/%s_sched.json' % short_sem, 'w', 'utf-8')
+    all_courses = []
+    
+    f = codecs.open('cache/sched_draft_%s.csv' % short_sem, 'r','utf-8')
+    reader = csv.reader(f, delimiter=',')
+    headers = next(reader)
+    for r in reader:
+        d = dict(list(zip(headers,r)))
+        #print(d)
+        parts = re.search(r'^([A-Z]+)(\d+[A-Z]*)$', d['Course_Code'])
+        if parts:
+            dept = parts.group(1)
+            num = parts.group(2)
+        my_dean = dean[dept]
+        my_gp = gp[dept]
+        code = dept + " " + num
+        crn = d['CRN']
+        cred = d['Units_Credit_hours']
+        days, time_start, time_end = days_times(d['Meeting_Days_and_Times'])
+        times = ""
+        if time_start: times = time_start + "-" + time_end
+        date = remove_year(d['Start_Date']) + "-" + remove_year(d['End_Date'])
+        start = remove_year(d['Start_Date'])
+        end = remove_year(d['End_Date'])
+        ztc = d['ZTC']
+        name = d['Course_Name']
+        cap = d['Class_Capacity']
+        rem = d['Available_Seats']
+        act = int(cap) - int(rem)
+        teacher = d['Instructor_First_Name'] + " " + d['Instructor_Last_Name']
+        delivery = d['Delivery']
+        if delivery == "Online":
+            if days:
+                site = "Online"
+                type = "online live"
+                loc = "Online Live"
+            else:
+                site = "Online"
+                type = "online"
+                loc = "ONLINE"
+        elif delivery == "Hybrid":
+            site = d['Campus_College']
+            type = "hybrid"
+            loc = d['Meeting_Locations']
+        else:
+            site = d['Campus_College']
+            type = "in-person"
+            loc = d['Meeting_Locations']
+        this_course = { "crn": crn, "dept": dept, "num": num, "code": code, "name": name, "teacher": teacher, "type": type, "loc": loc, \
+                       "cap": cap.strip(), "act": act, "site": site, "date": date, "cred": cred.strip(), "ztc": ztc, "days": days, "time": times, \
+                        "start": start, "end": end, "time_start": time_start, "time_end": time_end, "dean": my_dean, "gp": my_gp}
+        all_courses.append(this_course)
+        print(site)
+        #writer.writerow([my_gp,my_dean,dept,num,code,crn,name,act,site])
+    print(all_courses)
+    #print(json.dumps(all_courses))
+    f3.write( json.dumps(all_courses,indent=2) )
+    f3.close()
+    expanded = list_latestarts(short_sem)
 
 
 
@@ -2101,7 +2182,7 @@ if __name__ == "__main__":
                 8: ['Scrape schedule from ssb', scrape_schedule_multi ], 
                 9: ['Test ssb calls with python', scrape_schedule_py ], 
                 10: ['schedule to db', scrape_for_db ], 
-                11: ['clean argos draft schedule file', argos_data],
+                11: ['clean argos draft schedule file', argos_data_from_cvc],
                 12: ['make expanded schedule json files of old semesters', expand_old_semesters ],
                 13: ['Parse deanza schedule', dza_sched ],
               }