def library_login(s, libCardNum, libCardPin, orgDomain, LDEBUG=False):
global DEBUG
DEBUG = LDEBUG
libraryLoginURL = "https://www.lynda.com/portal/sip"
payload = {
"org": orgDomain
}
r = s.get(libraryLoginURL, params=payload)
# log(str(r))
# log(r.text)
# log("lib login url: " + r.url)
form = pd(r.text, "form")[1]
seasurf_sec_token = pd(form, "input", attrs={"name": "seasurf"}, ret="value")[0].encode("utf-8")
payload = {
"libraryCardNumber": libCardNum,
"libraryCardPin": libCardPin,
"libraryCardPasswordVerify": "",
"org": orgDomain,
"seasurf": seasurf_sec_token
}
# from pprint import pformat
# log(pformat(payload))
r2 = s.post(libraryLoginURL + '?org=' + orgDomain, data=payload)
# log("lib login post url: " + r2.url)
if r2.url != 'http://www.lynda.com/member' and r2.url != 'https://www.lynda.com/member' and r2.url != 'https://www.lynda.com/':
return False
else:
name = getName(r2.text)
return name
def get_category_letter_software(s, search_letter):
r = s.get("http://www.lynda.com/subject/all")
letters_html = pd(r.text, "div", attrs={"class": "letter"})
softwares = []
for letter in letters_html:
letter_name = pd(letter, "h3")[0]
if letter_name == search_letter:
softwares_html = pd(letter,
"div",
attrs={"class": "software-name"})
for software_html in softwares_html:
software_name = pd(software_html, "a")[0]
link = pd(software_html, "a", ret="href")[0]
if link[0] == "/":
link = "http://www.lynda.com" + link
num_courses, software_name = software_name.split(
"<span>")[1].split("</span>")
softwares.append({
"name": software_name + " " + num_courses,
"link": link
})
break
return softwares
def library_login(s, libCardNum, libCardPin, orgDomain, LDEBUG=False):
global DEBUG
DEBUG = LDEBUG
libraryLoginURL = "https://www.lynda.com/portal/sip"
payload = {"org": orgDomain}
r = s.get(libraryLoginURL, params=payload)
# log(str(r))
# log(r.text)
# log("lib login url: " + r.url)
form = pd(r.text, "form")[1]
seasurf_sec_token = pd(form,
"input",
attrs={"name": "seasurf"},
ret="value")[0].encode("utf-8")
payload = {
"libraryCardNumber": libCardNum,
"libraryCardPin": libCardPin,
"libraryCardPasswordVerify": "",
"org": orgDomain,
"seasurf": seasurf_sec_token
}
# from pprint import pformat
# log(pformat(payload))
r2 = s.post(libraryLoginURL + '?org=' + orgDomain, data=payload)
# log("lib login post url: " + r2.url)
if r2.url != 'http://www.lynda.com/member' and r2.url != 'https://www.lynda.com/member' and r2.url != 'https://www.lynda.com/':
return False
else:
name = getName(r2.text)
return name
def get_categories_letters(s):
r = s.get("http://www.lynda.com/subject/all")
letters_html = pd(r.text, "div", attrs={"class": "letter"})
# print(len(letters))
letter_list = []
for letter in letters_html:
letter_name = pd(letter, "h3")[0]
letter_list.append(letter_name)
return letter_list
def get_categories_letters(s):
r = s.get("http://www.lynda.com/subject/all")
letters_html = pd(r.text, "div", attrs={"class": "letter"})
# print(len(letters))
letter_list = []
for letter in letters_html:
letter_name = pd(letter, "h3")[0]
letter_list.append(letter_name)
return letter_list
def getName(html):
# Tested on members page
try:
drop_menu = pd(html, "span", attrs={"data-qa": "eyebrow_account_menu"})[0]
name = stripTags(drop_menu)[3:]
except:
name = "Can't get name"
return name
def courses_for_category(s, link):
r = s.get(link)
courselist = pd(r.text, "ul", attrs={"class": "course-list"})
# print(repr(courselist))
courses = pd(courselist, "li")
course_ids = pd(courselist, "li", ret="id")
course_thumbs = pd(courselist, "img", ret="data-img-src")
course_descriptions = pd(courselist, "p")
# print("Number of courses found:", len(courses))
course_list = []
for i, course in enumerate(courses):
title_heading = pd(course, "h3")[0]
title = stripTags(pd(title_heading, "a")[0].strip())
# print(title)
courseId = course_ids[i][7:]
thumbURL = course_thumbs[i]
shortDesc = stripTags(course_descriptions[i]).strip()
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
course_list.append(c)
return course_list
def courses_for_category(s, link):
r = s.get(link)
courselist = pd(r.text, "ul", attrs={"class": "course-list"})
# print(repr(courselist))
courses = pd(courselist, "li")
course_ids = pd(courselist, "li", ret="id")
course_thumbs = pd(courselist, "img", ret="data-img-src")
course_descriptions = pd(courselist, "p")
# print("Number of courses found:", len(courses))
course_list = []
for i, course in enumerate(courses):
title_heading = pd(course, "h3")[0]
title = stripTags(pd(title_heading, "a")[0].strip())
# print(title)
courseId = course_ids[i][7:]
thumbURL = course_thumbs[i]
shortDesc = stripTags(course_descriptions[i]).strip()
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
course_list.append(c)
return course_list
def getName(html):
# Tested on members page
try:
drop_menu = pd(html, "span", attrs={"data-qa":
"eyebrow_account_menu"})[0]
name = stripTags(drop_menu)[3:]
except:
name = "Can't get name"
return name
def get_category_letter_software(s, search_letter):
r = s.get("http://www.lynda.com/subject/all")
letters_html = pd(r.text, "div", attrs={"class": "letter"})
softwares = []
for letter in letters_html:
letter_name = pd(letter, "h3")[0]
if letter_name == search_letter:
softwares_html = pd(letter, "div", attrs={"class": "software-name"})
for software_html in softwares_html:
software_name = pd(software_html, "a")[0]
link = pd(software_html, "a", ret="href")[0]
if link[0] == "/":
link = "http://www.lynda.com" + link
num_courses, software_name = software_name.split("<span>")[1].split("</span>")
softwares.append({"name": software_name + " " + num_courses,
"link": link})
break
return softwares
def get_my_courses(s):
my_courses_url = "http://www.lynda.com/CourseHistory"
r = s.get(my_courses_url)
courses_html = pd(r.text, "div", attrs={"class": "row_course"})
course_list = []
for course_html in courses_html:
col_course = pd(course_html, "div", attrs={"class": "col_course"})
courseId = pd(col_course, "a", ret="data-course")[0]
title = pd(col_course, "a")[1].strip()
thumbURL = None
shortDesc = ""
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
course_list.append(c)
return course_list
def get_my_courses(s):
my_courses_url = "http://www.lynda.com/CourseHistory"
r = s.get(my_courses_url)
courses_html = pd(r.text, "div", attrs={"class": "row_course"})
course_list = []
for course_html in courses_html:
col_course = pd(course_html, "div", attrs={"class": "col_course"})
courseId = pd(col_course, "a", ret="data-course")[0]
title = pd(col_course, "a")[1].strip()
thumbURL = None
shortDesc = ""
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
course_list.append(c)
return course_list
def parse_course_lists(html, is_text_search=True):
"""Takes the page html with the list of courses and returns a list of course objects (dicts)"""
if is_text_search:
ul_id = "search-results-list"
course_class = "card card-list-style search-result course"
description_class = "meta-description hidden-xs"
title_el = "h2"
else:
ul_id = "category-courses"
course_class = "card card-list-style course"
description_class = "meta-description hidden-xs dot-ellipsis dot-resize-update"
title_el = "h3"
courselist = pd(html, "ul", attrs={"id": ul_id})
# log("<<<<<<<<<<<<<<<<<DEBUG>>>>>>>>>>>>>>>>>>>>")
# log(repr(courselist))
courses = pd(courselist, "li")
course_list = []
for i, course in enumerate(courses):
search_result = pd(course, "div", attrs={"class": course_class}, ret="id")
if len(search_result) == 0: continue
title = stripTags(pd(course, title_el)[0])
courseId = search_result[0]
thumbnail_el = pd(course, "div", attrs={"class": "thumbnail"})[0]
thumbURL = pd(thumbnail_el, "img", ret="data-lazy-src")[0]
shortDesc = stripTags(pd(course, "div", attrs={"class": description_class})[0]).strip()
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
# log(str(c))
course_list.append(c)
return course_list
def getForm(html, formIndex=0):
formObj = {}
form = pd(html, "form")[formIndex]
try:
formObj['action'] = pd(html, "form", ret="action")[0] # TODO: Use indexed form html
except:
formObj['action'] = None
inputs_html = pd(form, "input")
input_types = pd(form, "input", ret="type")
input_values = pd(form, "input", ret="value")
input_names = pd(form, "input", ret="name")
formObj['input_types'] = input_types
formObj['input_values'] = input_values
formObj['input_names'] = input_names
return formObj
def getForm(html, formIndex=0):
formObj = {}
form = pd(html, "form")[formIndex]
try:
formObj['action'] = pd(html, "form",
ret="action")[0] # TODO: Use indexed form html
except:
formObj['action'] = None
inputs_html = pd(form, "input")
input_types = pd(form, "input", ret="type")
input_values = pd(form, "input", ret="value")
input_names = pd(form, "input", ret="name")
formObj['input_types'] = input_types
formObj['input_values'] = input_values
formObj['input_names'] = input_names
return formObj
def course_search(s, query):
url = "http://www.lynda.com/search"
payload = {"q": query, "f": "producttypeid:2"}
r = s.get(url, params=payload)
page_html = r.text
courselist = pd(page_html,
"ul",
attrs={"class": "course-list search-movies"})
# print(repr(courselist))
courses = pd(courselist, "li")
course_ids = pd(courselist, "li", ret="id")
course_thumbs = pd(courselist, "img", ret="data-img-src")
course_descriptions = pd(courselist, "p", attrs={"class": "highlights"})
# print("Number of courses found:", len(courses))
# print(courses)
course_list = []
for i, course in enumerate(courses):
title = stripTags(pd(course, "a", attrs={"class": "title"})[0])
# print(title)
courseId = course_ids[i][7:]
thumbURL = course_thumbs[i]
shortDesc = stripTags(course_descriptions[i]).strip()
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
course_list.append(c)
return course_list
def course_search(s, query):
url = "http://www.lynda.com/search"
payload = {"q": query,
"f": "producttypeid:2"}
r = s.get(url, params=payload)
page_html = r.text
courselist = pd(page_html, "ul", attrs={"class": "course-list search-movies"})
# print(repr(courselist))
courses = pd(courselist, "li")
course_ids = pd(courselist, "li", ret="id")
course_thumbs = pd(courselist, "img", ret="data-img-src")
course_descriptions = pd(courselist, "p", attrs={"class": "highlights"})
# print("Number of courses found:", len(courses))
# print(courses)
course_list = []
for i, course in enumerate(courses):
title = stripTags( pd(course, "a", attrs={"class": "title"})[0] )
# print(title)
courseId = course_ids[i][7:]
thumbURL = course_thumbs[i]
shortDesc = stripTags(course_descriptions[i]).strip()
c = {
"title": title,
"courseId": courseId,
"thumbURL": thumbURL,
"shortDesc": shortDesc
}
course_list.append(c)
return course_list
