def term(page):
data = {}
# Store all tables with "datadisplaytable" class
tables = iter(__parse(page).findall(".//table[@class='datadisplaytable']"))
# Loop through every two tables as one (head and body)
for head, body in zip(tables, tables):
# Split table caption into three parts ["title", "key", "section"]
title, course_key, section = head.find("caption").text.split(" - ")
# Remove spaces from course key
course_key = course_key.replace(" ", "")
# Store all table head cells and body rows into arrays
cells, rows = head.findall(".//td"), body.findall("tr")
# Combine all course data
course_data = dict(
{
"title": title,
"section": section,
"crn": int(cells[1].text),
"ch": int(cells[5].text.strip()[0])
# Get & add lecture/lab details
},
**__get_data(rows, title))
# If course key is new to term
if data.get(course_key) is None:
# Store the course with that key
data[course_key] = course_data
# If the course already exists
else: # Store it as a lab of the previous course
data[course_key]["lab"] = course_data
return data
def course(page):
# Store main table's caption and body
caption, body = __parse(page).find(
".//table[@class='datadisplaytable']").findall("tr")
# Split caption to get course's title, crn, key and section
title, crn, course_key, section = caption.text_content().strip().split(
" - ")
# Return course data dictionary
return { # In {course key: course data} format
course_key.replace(" ", ""):
dict(
{
"title":
title,
"section":
section,
"crn":
int(crn),
# Credits hours value isn't structured, so search among the strings to find it
"ch":
int(
body.xpath("td/text()[contains(., 'Credits')]")[0].strip()
[0])
# Get & add lecture/lab details
},
**__get_data(body.findall(".//tr"), title))
}
def registered_terms(page):
return {
# Return a dictionary that contains {term code: term name} pairs
__get_term_code(term_name.text): term_name.text
# Loop through tags which contain term name
for term_name in __parse(page).findall(
".//span[@class='fieldOrangetextbold']")
}
def all_terms(response):
# Initialize terms dictionary
terms = {}
# Loop through terms in academic calendar
for term in __parse(response).findall(".//div[@class='pageTurn']/div/div"):
# Split(" ") term & store it's season and year
season, _, year = term.find("label").text.split()
# Add term to terms dictionary as a {term name: term code} pair
terms[season + " " +
year.replace("/", "-")] = year[:4] + seasons_codes[season]
return terms
def student_details(page):
# Extract tables from page and store needed cells
cells = __parse(page).findall(".//table[@class='datadisplaytable']/tr/td")
# Return student's registration term, collage and major
return {
"term":
__get_term_code(cells[2].text),
"college":
cells[4].text,
"major":
f"{cells[3].text} in {cells[5].text}".replace("Undergraduate in ", "")
}
def holds(page):
data = []
# Loop through holds table's rows which contain data
for hold in __parse(page).findall(
".//table[@class='datadisplaytable']/tr")[1:]:
# Store hold's row cells
cells = hold.findall("td")
# Add holds type, reason, start & end dates
data.append({
"type": cells[0].text,
"start": cells[1].text,
"end": cells[2].text,
"reason": cells[4].text
})
return data
def final_exams(page):
data = []
# Loop through finals table's rows which contain data
for final in __parse(page).findall(
".//table[@class='datadisplaytable'][2]/tr")[1:]:
# Store final's row cells
cells = final.findall("td")
# If final's date is announced (not all asterisk)
if cells and any(letter != "*" for letter in cells[2].text):
# Add final course key, title, date, start & end time and location
data.append({
"course": cells[0].text,
"date": cells[2].text,
"start": cells[3].text,
"end": cells[4].text,
"location": __extract_location(cells[5].text.split())
})
return data
def term_events(response, term_code):
# Initialize events and store year
year, events = term_code[:4], []
# Define a function to clean cell from whitespaces
clean = lambda cell: re.sub(" +", " ", cell.strip())
# Format term name in "Fall Semester 2017/2017" format from term code
term_name = f"{seasons_codes[term_code[4:]]} {year}/{int(year) + 1}"
# Loop through available terms calendars
for term in __parse(response).findall(".//div[@class='pageTurn']/div/div"):
# If calendar's label matches requested term name
if term.find("label").text == term_name:
# Loop through it's events (table rows)
for event in term.findall(".//tbody/tr")[2:]:
# Store event row's cells
cells = event.findall("td")
# Add event's date and text to events array
events.append({
"date":
clean(re.sub("(Till|-|–)", " - ",
cells[1].text_content())).split(',')[0],
"text":
clean(cells[3].text_content())
})
return events