def getResourceUrl(source):
'''Returns the resource url from the resourceWorkaroundPageSource'''
elems = scraptools.getElementsFromHTML(source, '.resourceworkaround>a')
if len(elems) == 0: # The resource is probably embedded in the page
container = scraptools.getElementsFromHTML(source, 'object')
if len(container) == 0: # Some other type of container
container = scraptools.getElementsFromHTML(source, 'frame')
href = container[1].get('src')
else:
href = container[0].get('data')
else:
href = elems[0].get('href')
return href
def getResourceUrl(source):
'''Returns the resource url from the resourceWorkaroundPageSource'''
elems = scraptools.getElementsFromHTML(source, '.resourceworkaround>a')
if len(elems) == 0: # The resource is probably embedded in the page
container = scraptools.getElementsFromHTML(source, 'object')
if len(container) == 0: # Some other type of container
container = scraptools.getElementsFromHTML(source, 'frame')
href = container[1].get('src')
else:
href = container[0].get('data')
else:
href = elems[0].get('href')
return href
def getResourceUrl(source):
"""Returns the resource url from the resourceWorkaroundPageSource"""
elems = scraptools.getElementsFromHTML(source, ".resourceworkaround>a")
if len(elems) == 0: # The resource is probably embedded in the page
container = scraptools.getElementsFromHTML(source, "object")
if len(container) == 0: # Some other type of container
container = scraptools.getElementsFromHTML(source, "frame")
href = container[1].get("src")
else:
href = container[0].get("data")
else:
href = elems[0].get("href")
return href
def extractResources(self):
pageSource = connection.getUrlData(self.url)
resourceElems = scraptools.getElementsFromHTML(pageSource, '#region-main a')
print len(resourceElems), 'files found in folder', self.folderName
for a in resourceElems:
self.resources.append(Resource(a.get('href'), a.text))
def extractResources(self):
pageSource = connection.getUrlData(self.url)
resourceElems = scraptools.getElementsFromHTML(pageSource,
'#region-main a')
print len(resourceElems), 'files found in folder', self.folderName
for a in resourceElems:
self.resources.append(Resource(a.get('href'), a.text))
def extractResources(self):
'''Extracts the resources from a course page'''
pageSource = connection.getUrlData(self.pageUrl)
resourceElems = scraptools.getElementsFromHTML(pageSource, '.resource')
print len(resourceElems), 'Direct resources found'
self.resources = []
for element in resourceElems:
url, instanceName = self.getUrlAndInstanceName(element)
self.resources.append(Resource(url, instanceName))
# Look for folders
folderElems = scraptools.getElementsFromHTML(pageSource, '.folder')
print len(folderElems), 'Folders found'
for folder in folderElems:
url, instanceName = self.getUrlAndInstanceName(folder)
self.resources.append(ResourceFolder(connection, url, instanceName))
def extractResources(self):
'''Extracts the resources from a course page'''
pageSource = connection.getUrlData(self.pageUrl)
resourceElems = scraptools.getElementsFromHTML(pageSource, '.resource')
print len(resourceElems), 'Direct resources found'
self.resources = []
for element in resourceElems:
url, instanceName = self.getUrlAndInstanceName(element)
self.resources.append(Resource(url, instanceName))
# Look for folders
folderElems = scraptools.getElementsFromHTML(pageSource, '.folder')
print len(folderElems), 'Folders found'
for folder in folderElems:
url, instanceName = self.getUrlAndInstanceName(folder)
self.resources.append(ResourceFolder(connection, url,
instanceName))
def __init__(self, moodleConnection):
pageSource = moodleConnection.main_page
# Find course boxes
elems = scraptools.getElementsFromHTML(pageSource, '.course_title a')
genieRe = '[A-Z]{1,4}-?([A-Z]{3})?'
numRe = '[0-9]{3,4}[A-Z]?'
sigleRe = '(' + genieRe + numRe + ')'
self.coursePages = []
for e in elems:
courseDescription = e.text
match = re.match(sigleRe, courseDescription)
if match: #We have a course box with a valid sigle
sigle = match.group(1)
pageUrl = e.get('href')
self.coursePages.append(MoodleCoursePage(moodleConnection, pageUrl, sigle))
def __init__(self, moodleConnection):
pageSource = moodleConnection.main_page
# Find course boxes
elems = scraptools.getElementsFromHTML(pageSource, ".course_title a")
genieRe = "[A-Z]{1,4}-?([A-Z]{3})?"
numRe = "[0-9]{3,4}[A-Z]?"
sigleRe = "(" + genieRe + numRe + ")"
self.coursePages = []
for e in elems:
courseDescription = e.text
match = re.match(sigleRe, courseDescription)
# Automatic course discovery or Check sigles in args (manual)
if len(sys.argv) <= 1 and match or isInArgv(courseDescription):
sigle = match.group(1)
pageUrl = e.get("href")
self.coursePages.append(MoodleCoursePage(moodleConnection, pageUrl, sigle))
def __init__(self, moodleConnection):
pageSource = moodleConnection.main_page
# Find course boxes
elems = scraptools.getElementsFromHTML(pageSource, '.course_title a')
genieRe = '[A-Z]{1,4}-?([A-Z]{3})?'
numRe = '[0-9]{3,4}[A-Z]?'
sigleRe = '(' + genieRe + numRe + ')'
self.coursePages = []
for e in elems:
courseDescription = e.text
match = re.match(sigleRe, courseDescription)
#Automatic course discovery or Check sigles in args (manual)
if len(sys.argv) <=1 and match or \
isInArgv(courseDescription):
sigle = match.group(1)
pageUrl = e.get('href')
self.coursePages.append(
MoodleCoursePage(moodleConnection, pageUrl, sigle))
