def test5():
courses = []
coursera_root_page_filepath = ls.get_default_coursera_stocked_root_webpage_osfilepath()
html_text = open(coursera_root_page_filepath).read()
root = etree.HTML(html_text)
elements = root.findall(".//div[@class]")
for element in elements:
classname = element.get('class')
if classname == 'coursera-course-listing-main':
course_obj = process_element(element)
if course_obj != None:
courses.append(course_obj)
#sys.exit(0)
grabber = CourseraRootCourseGrabber()
grabber.restart_items_by_reading_htmlwebroot_source()
for course_id in grabber.unique_course_id_dict.keys():
msg = '%s seq = %s' %(course_id, grabber.unique_course_id_dict[course_id].course_n_seq)
logging.info(msg)
logging.info('**********************************')
for i, course_obj in enumerate(courses):
if course_obj.course_id in grabber.unique_course_id_dict.keys():
course_there = grabber.unique_course_id_dict[course_obj.course_id]
course_obj.course_n_seq = course_there.course_n_seq
msg = '****EQUAL **** %s :: seq = %s' %(course_obj.course_id, course_there.course_n_seq)
logging.info(msg)
print i, course_obj.course_id
logging.info(course_obj.course_id)
print 'title', course_obj.title
print 'nseq', course_obj.course_n_seq
def test5():
courses = []
coursera_root_page_filepath = ls.get_default_coursera_stocked_root_webpage_osfilepath()
html_text = open(coursera_root_page_filepath).read()
root = etree.HTML(html_text)
elements = root.findall(".//div[@class]")
for element in elements:
classname = element.get('class')
if classname == 'coursera-course-listing-main':
course_obj = process_element(element)
if course_obj != None:
courses.append(course_obj)
sys.exit(0)
for i, course_obj in enumerate(courses):
print i, course_obj.course_id
print course_obj.title
