Exams scraper

README.md

@@ -405,7 +405,8 @@ uoftscrapers.Exams
   "start_time": String,
   "end_time": String,
   "sections": [{
-    "section": String,
+    "lecture_code": String,
+    "exam_section": String,
     "location": String
   }]
 }

uoftscrapers/scrapers/exams/utm.py

@@ -45,12 +45,11 @@ def retrieve_exams(courses):
             soup = BeautifulSoup(html, 'html.parser')
 
             course_code = soup.find('div', class_='title').text.strip()
+            lecture_code = None
 
             # some course names include lecture code (see CHI200Y5Y)
             if ' ' in course_code:
                 course_code, lecture_code = course_code.split(' ')
-            else:
-                lecture_code = None
 
             data = [br.previous_sibling.string.strip()
                     for br in soup.find('div', class_='info').find_all('br')]
@@ -71,14 +70,14 @@ def retrieve_exams(courses):
                         for room in [x for x in data[3:] if 'Room:' in x]]
 
             # append lecture code to section range if it exists
-            if lecture_code:
-                sections[0]['section'] = '%s %s' % (lecture_code,
-                                                    sections[0]['section'])
+            for i in range(len(sections)):
+                sections[i]['lecture'] = lecture_code or ''
 
             doc = OrderedDict([
                 ('id', id_),
                 ('course_id', course_id),
                 ('course_code', course_code),
+                ('campus', 'UTM'),
                 ('period', period),
                 ('date', date),
                 ('start_time', start),
@@ -90,10 +89,11 @@ def retrieve_exams(courses):
                 exams[id_] = doc
 
             for section in sections:
-                exams[id_]['sections'].append({
-                    'section': section['section'].strip(),
-                    'locaton': section['room']
-                })
+                exams[id_]['sections'].append(OrderedDict([
+                    ('lecture_code', section['lecture']),
+                    ('exam_section', section['section']),
+                    ('location', section['room'])
+                ]))
         return exams
 
     @staticmethod

uoftscrapers/scrapers/exams/utsc.py

@@ -26,14 +26,13 @@ def scrape(location='.'):
             for tr in table.find_all('tr')[1:]:
                 data = [x.text.strip() for x in tr.find_all('td')]
 
-                course_code = data[0]
+                course_code, lecture_code = data[0], None
                 if ' ' in course_code:
                     course_code, lecture_code = course_code.split(' ')
-                else:
-                    lecture_code = None
 
                 date = data[1]
                 start, end = UTSCExams.parse_time(data[2], data[3], date)
+
                 location_ = data[4]
 
                 id_, course_id = UTSCExams.get_course_id(course_code, date)
@@ -47,6 +46,7 @@ def scrape(location='.'):
                     ('id', id_),
                     ('course_id', course_id),
                     ('course_code', course_code),
+                    ('campus', 'UTSC'),
                     ('period', period),
                     ('date', date),
                     ('start_time', start),
@@ -57,10 +57,11 @@ def scrape(location='.'):
                 if id_ not in exams:
                     exams[id_] = doc
 
-                exams[id_]['sections'].append({
-                    'section': lecture_code or '',
-                    'location': location_
-                })
+                exams[id_]['sections'].append(OrderedDict([
+                    ('lecture_code', lecture_code or ''),
+                    ('exam_section', ''),
+                    ('location', location_)
+                ]))
 
         for id_, doc in exams.items():
             Scraper.save_json(doc, location, id_)

uoftscrapers/scrapers/exams/utsg.py

@@ -50,14 +50,27 @@ def scrape(location='.', year=None):
                 if id_ is None:
                     continue
 
-                section, location_ = data[1], data[4]
+                section = data[1]
+
+                lecture_section = exam_section = None
+
+                if '  ' in section:
+                    lecture_section, exam_section = section.split('  ')
+                elif '-' in section:
+                    exam_section = section
+                else:
+                    lecture_section = section
+
+                location_ = data[4]
+
                 date_ = UTSGExams.parse_date(data[2], p[-2:]) or ''
                 start, end = UTSGExams.parse_time(data[3], date_) or (0, 0)
 
                 doc = OrderedDict([
                     ('id', id_),
                     ('course_id', course_id),
                     ('course_code', course_code),
+                    ('campus', 'UTSG'),
                     ('period', p.upper()),
                     ('date', date_),
                     ('start_time', start),
@@ -69,7 +82,8 @@ def scrape(location='.', year=None):
                     exams[id_] = doc
 
                 exams[id_]['sections'].append(OrderedDict([
-                    ('section', section),
+                    ('lecture_code', lecture_section or ''),
+                    ('exam_section', exam_section or ''),
                     ('location', location_)
                 ]))