def extract_time_range(self, unformatted_time_range):
if unformatted_time_range == 'TBA' or unformatted_time_range == '':
raise ParseJump(self.ingestor['course_code'] + ' time TBA')
search = re.match(r'(.*) \- (.*)', unformatted_time_range)
if search is None:
raise ParseJump('time not found on page')
def ampm(x):
return x.replace('a', 'am').replace('p', 'pm')
self.ingestor['time_start'] = ampm(search.group(1))
self.ingestor['time_end'] = ampm(search.group(2))
def extract_time_range(self, unformatted_time_range):
if unformatted_time_range == "TBA" or unformatted_time_range == "":
raise ParseJump(self.ingestor["course_code"] + " time TBA")
search = re.match(r"(.*) \- (.*)", unformatted_time_range)
if search is None:
raise ParseJump("time not found on page")
def ampm(x):
return x.replace("a", "am").replace("p", "pm")
self.ingestor["time_start"] = ampm(search.group(1))
self.ingestor["time_end"] = ampm(search.group(2))
def extract_days(self, unformatted_days):
if unformatted_days == 'TBA' or unformatted_days == '':
raise ParseJump(self.ingestor['course_code'] + ' days TBA')
self.ingestor['days'] = list(unformatted_days)
def parse_course(self, soup):
# remove cancelled classes
if soup.find('a', class_='cancelledStatus'):
raise ParseJump('cancelled course')
# Extract course code and term number to generate access to more info
details = soup.find('td', class_='classSection')['onclick']
# Extract course number and term code
search = re.search(
r"showClassDetailPanel.fire\({classNumber : '([0-9]*)', termCode : '([0-9]*)',",
details)
course_number = search.group(1)
soup = self.requester.get(Parser.URL + '/GetClassSectionDetail.action',
params={
'classNumber': course_number,
'termCode': search.group(2)
})
# Extract course name and abbreviation details
search = re.search(
r'(.*):.*\n(.*)',
soup.find(id='classSectionDetailDialog').find('h1').text)
abbr = search.group(1)
# Extract department code, catalog ID, and section number from abbr
title = re.match(r'(\S*)-(\S*)-(\S*)', abbr)
if not title:
raise ParseJump('no title in course')
self.ingestor['course_name'] = search.group(2)
self.ingestor['course_code'] = title.group(1) + '-' + title.group(2)
self.ingestor['section_code'] = '(' + title.group(3).strip() + ')'
# Deal with course details as subgroups seen on details page
detail_headers = soup.find_all('div', class_='detailHeader')
detail_panels = soup.find_all('div', class_='detailPanel')
if len(detail_headers) != len(detail_panels):
raise ParseError('there should be equal detail headers and panels')
for i in range(len(detail_headers)):
# Extract header name
header = detail_headers[i].text.strip()
# Choose parsing strategy dependent on header
if header == "Details" or header == "Availability":
self.parse_labeled_table(detail_panels[i])
elif header == "Description":
self.extract_description(detail_panels[i])
elif header == "Notes":
self.extract_notes(detail_panels[i])
elif header == "Meeting Times":
self.parse_meeting_times(detail_panels[i])
elif header == "Cross Listings":
pass
elif header == "Attributes":
self.parse_attributes(detail_panels[i])
elif header == "Ad Hoc Meeting Times":
pass
course = self.ingestor.ingest_course()
self.ingestor.ingest_section(course)
self.ingestor['meetings'] = []
return course_number
def extract_days(self, unformatted_days):
if unformatted_days == "TBA" or unformatted_days == "":
raise ParseJump(self.ingestor["course_code"] + " days TBA")
self.ingestor["days"] = list(unformatted_days)
def parse_course(self, soup):
# remove cancelled classes
if soup.find("a", class_="cancelledStatus"):
raise ParseJump("cancelled course")
# Extract course code and term number to generate access to more info
details = soup.find("td", class_="classSection")["onclick"]
# Extract course number and term code
search = re.search(
r"showClassDetailPanel.fire\({classNumber : '([0-9]*)', termCode : '([0-9]*)',",
details,
)
course_number = search.group(1)
soup = self.requester.get(
Parser.URL + "/GetClassSectionDetail.action",
params={
"classNumber": course_number,
"termCode": search.group(2)
},
)
# Extract course name and abbreviation details
search = re.search(
r"(.*):.*\n(.*)",
soup.find(id="classSectionDetailDialog").find("h1").text)
abbr = search.group(1)
# Extract department code, catalog ID, and section number from abbr
title = re.match(r"(\S*)-(\S*)-(\S*)", abbr)
if not title:
raise ParseJump("no title in course")
self.ingestor["course_name"] = search.group(2)
self.ingestor["course_code"] = title.group(1) + "-" + title.group(2)
self.ingestor["section_code"] = "(" + title.group(3).strip() + ")"
# Deal with course details as subgroups seen on details page
detail_headers = soup.find_all("div", class_="detailHeader")
detail_panels = soup.find_all("div", class_="detailPanel")
if len(detail_headers) != len(detail_panels):
raise ParseError("there should be equal detail headers and panels")
for i in range(len(detail_headers)):
# Extract header name
header = detail_headers[i].text.strip()
# Choose parsing strategy dependent on header
if header == "Details" or header == "Availability":
self.parse_labeled_table(detail_panels[i])
elif header == "Description":
self.extract_description(detail_panels[i])
elif header == "Notes":
self.extract_notes(detail_panels[i])
elif header == "Meeting Times":
self.parse_meeting_times(detail_panels[i])
elif header == "Cross Listings":
pass
elif header == "Attributes":
self.parse_attributes(detail_panels[i])
elif header == "Ad Hoc Meeting Times":
pass
course = self.ingestor.ingest_course()
self.ingestor.ingest_section(course)
self.ingestor["meetings"] = []
return course_number