def build_pdf_topics(main_topic, sections, lang_code):
"""
Adds the documents from the sections tree to the `main_topic`.
- CASE A = no children => add as DocumentNode
- CASE B = has children => add as TopicNode and add all children as DocumentNode
"""
LICENSE = get_license("CC BY-NC-SA", copyright_holder=POINTB)
for i, section in enumerate(sections):
# CASE A: All sections except Section 2
if 'children' not in section:
title = section['title']
abspath = section['path']
filename = os.path.basename(abspath)
doc_node = DocumentNode(
title=title,
description=
'Chapter from A GUIDE TO BECOMING A 21ST CENTURY TEACHER',
source_id='%s-%s' % (filename, lang_code),
license=LICENSE,
aggregator=LE,
language=lang_code,
role=roles.COACH,
files=[DocumentFile(path=abspath, language=lang_code)])
main_topic.add_child(doc_node)
# CASE B: Section 2
else:
section_topic = TopicNode(title=section['title'],
source_id="pointb_section_" + str(i))
main_topic.add_child(section_topic)
for subsection in section['children']:
title = subsection['title']
abspath = subsection['path']
filename = os.path.basename(abspath)
subsection_doc_node = DocumentNode(
title=title,
description='',
source_id='%s-%s' % (filename, lang_code),
license=LICENSE,
aggregator=LE,
language=lang_code,
role=roles.COACH,
files=[DocumentFile(path=abspath, language=lang_code)])
section_topic.add_child(subsection_doc_node)
return main_topic
def googleNode(url):
#Get doc id
id = getIdFromUrl(url)
#Call proper google download function
if (url.find('document') != -1):
print("Found Document")
#Uses download function to get pdf of document, returns filename
fileName = downloadDocument(id)
elif (url.find('presentation') != -1):
print("Found Presentation")
#Uses download function to get pdf of powerpoint, returns filename
fileName = downloadPowerpoint(id)
elif (url.find('spreadsheets') != -1):
print("Found Spreadsheet")
fileName = downloadSpreadsheet(id)
#Use download and filename to create node
googleNode = DocumentNode(
source_id=id,
title=fileName,
language="en",
description="",
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
files=[DocumentFile(
path=fileName,
language="en",
)],
)
return googleNode
def invalid_video_file():
local_path = os.path.join("tests", "testcontent", "generated",
"invalid_video.mp4")
if not os.path.exists(local_path):
with open(local_path, 'wb') as f:
f.write(b'this is an invalid video file')
return DocumentFile(local_path)
def invalid_audio_file():
local_path = os.path.join("tests", "testcontent", "generated",
"invalid_audio.mp3")
if not os.path.exists(local_path):
with open(local_path, 'wb') as f:
f.write(b'invalid MP3')
return DocumentFile(local_path)
def document_file():
source_url = "https://ia802506.us.archive.org/8/items/generalmanual_000075878/generalmanual_000075878.pdf"
local_path = os.path.join("tests", "testcontent", "downloaded",
"testdocument.pdf")
download_fixture_file(source_url, local_path)
assert os.path.exists(local_path)
return DocumentFile(local_path)
def pdfNode(infoDict):
#Get response from converted-to-pdf path
response = requests.get(infoDict['pdfPath'], auth=auth)
global pdfCopy
if os.path.exists(infoDict['pdfTitle']):
infoDict['pdfTitle'] = infoDict['pdfTitle'].replace(
".pdf",
str(pdfCopy) + ".pdf")
pdfCopy += 1
#Write pdf to local file
with open(infoDict['pdfTitle'], 'wb') as f:
f.write(response.content)
filesCreated.append(infoDict['pdfTitle'])
#Create Document Node
pdfNode = DocumentNode(
source_id=str(infoDict['id']),
title=infoDict['pdfTitle'],
language="en",
description="",
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
files=[DocumentFile(
path=infoDict['pdfTitle'],
language="en",
)],
)
return pdfNode
def invalid_document_file():
local_path = os.path.join("tests", "testcontent", "generated",
"invalid_document.pdf")
if not os.path.exists(local_path):
with open(local_path, 'wb') as f:
f.write(b'invalid PDF')
return DocumentFile(local_path)
def get_file(name, directory, filename, title=None):
filepath = os.path.join(directory, filename)
if title is None:
title = name
source_id = "{}/{}".format(name, filename)
node = None
if filename.endswith(".pdf"):
node = DocumentNode(
title=title,
description="Documentación de {}".format(name),
source_id=source_id,
license=AIEP_License,
language="es",
files=[DocumentFile(
path=filepath,
language="es",
)],
)
elif filename.endswith("h5p"):
mp4_file = get_video_from_h5p(filepath)
if mp4_file is None:
classNode = H5PAppNode
classFile = H5PFile
else:
classNode = VideoNode
classFile = VideoFile
filepath = mp4_file
node = classNode(
title=get_title_from_video(title, filename),
description="Vídeo explicativo de la {}".format(name),
source_id=source_id,
license=AIEP_License,
language="es",
files=[classFile(
path=filepath,
language="es",
)],
)
elif filename.endswith("xls"):
node = ExerciseNode(
source_id=source_id,
title="Ejercicios de {}".format(name),
author="Equipo de AIEP",
description="Preguntas de la unidad 1",
language="es",
license=AIEP_License,
thumbnail=None,
exercise_data={
"mastery_model": exercises.M_OF_N, # \
"m": 2, # learners must get 2/3 questions correct to complete
"n": 3, # /
"randomize": True, # show questions in random order
},
questions=leer_preguntas(filepath),
)
return node
def add_resources(resources, node, role=LEARNER):
for title, url in resources:
pdf_node = DocumentNode(source_id = "pdf_"+url,
title = title,
license = LICENCE,
files = [DocumentFile(path=url)],
role = role
)
node.add_child(pdf_node)
def test_non_existent_epub_fails(self):
node = DocumentNode('doc-src-id',
"Document",
licenses.PUBLIC_DOMAIN,
thumbnail=None)
non_existent_path = 'does/not/exist.epub'
document_file = DocumentFile(non_existent_path, language='en')
node.add_file(document_file)
config.THUMBNAILS = True
filenames = node.process_files()
assert filenames == [None], 'expected one None (the non existent epub)'
assert len(config.FAILED_FILES) == 1, 'expected one failed file'
def construct_channel(self, *args, **kwargs):
"""
This method is reponsible for creating a `ChannelNode` object and
populating it with `TopicNode` and `ContentNode` children.
"""
# Create channel
########################################################################
channel = self.get_channel(*args, **kwargs) # uses self.channel_info
# Create topics to add to your channel
########################################################################
teen_topic = TopicNode(source_id="topic-teen", title="K-12 Resources")
adult_topic = TopicNode(source_id="topic-adult",
title="Adult Continue Education Resources")
channel.add_child(teen_topic)
channel.add_child(adult_topic)
level_map = {}
for index, teen_level in enumerate(teen_levels):
level_map[teen_level] = TopicNode(source_id="topic-teen-" +
teen_level,
title=teen_level)
for index, adult_level in enumerate(adult_levels):
level_map[adult_level] = TopicNode(source_id="topic-adult-" +
adult_level,
title=adult_level)
for level, subtopics in parse_website().items():
for subtopic, resources in subtopics.items():
subtopic_node = TopicNode(source_id=subtopic, title=subtopic)
for resource in resources:
resource_file = DocumentFile(path=resource['link'])
resource_pdf = DocumentNode(title=resource['title'],
source_id=resource['title'],
files=[resource_file],
license=get_license(
licenses.PUBLIC_DOMAIN))
subtopic_node.add_child(resource_pdf)
level_map[level].add_child(subtopic_node)
for key, value in level_map.items():
if key in teen_levels:
teen_topic.add_child(value)
elif key in adult_levels:
adult_topic.add_child(value)
# the `construct_channel` method returns a ChannelNode that will be
# processed by the ricecooker framework
return channel
def doc_node(doc, title):
if type(doc) == bytes:
doc = doc.decode('utf-8')
files = [DocumentFile(doc)]
if str(doc) in done_nodes:
return None
done_nodes.append(str(doc))
return DocumentNode(
source_id="doc " + str(doc),
title=title,
license=LICENCE,
copyright_holder="nashmi.net",
files=files,
)
def add_documents(topic, chapters, language):
for idx, chapter in enumerate(chapters):
# if chapter has 'children'
if 'children' in chapter.keys():
doc_title = chapter['title']
child_topic_node = TopicNode(title=doc_title,
source_id=language + doc_title,
thumbnail=DOWNLOADS_FOLDER +
'/thumbnail.png')
for child in chapter['children']:
child_doc_title = child['title']
doc_node = DocumentNode(
title=child_doc_title,
description=f'Chapter {idx} from {doc_title}',
source_id=language + child_doc_title,
license=get_license('CC BY', copyright_holder='NC-SA 4.0'),
language=language,
thumbnail=DOWNLOADS_FOLDER + '/thumbnail.png',
files=[
DocumentFile(path=child['path'], language=language)
],
)
child_topic_node.add_child(doc_node)
topic.add_child(child_topic_node)
else:
doc_title = chapter['title']
doc_node = DocumentNode(
title=doc_title,
description=f'Chapter {idx} from 21ST CENTURY GUIDE',
source_id=language + doc_title,
license=get_license('CC BY', copyright_holder='NC-SA 4.0'),
language=language,
thumbnail=DOWNLOADS_FOLDER + '/thumbnail.png',
files=[DocumentFile(path=chapter['path'], language=language)],
)
topic.add_child(doc_node)
def documentAssignment(material):
docPath = "documents/" + slugify(
material["driveFile"]["driveFile"]["title"]) + ".pdf"
document_node = DocumentNode(
source_id=material["driveFile"]["driveFile"]["id"],
title=material["driveFile"]["driveFile"]["title"],
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
derive_thumbnail=True,
thumbnail=None,
files=[DocumentFile(path=str(docPath), language=getlang('en').id)])
print(courseDataCopy["Assignments"])
return document_node
def construct_channel(self, **kwargs):
channel = self.get_channel(**kwargs)
potato_topic = TopicNode(title="Potatoes!", source_id="<potatos_id>")
channel.add_child(potato_topic)
doc_node = DocumentNode(
title='Growing potatoes',
description='An article about growing potatoes on your rooftop.',
source_id='pubs/mafri-potatoe',
license=get_license('CC BY', copyright_holder='University of Alberta'),
language='en',
files=[DocumentFile(path='https://www.gov.mb.ca/inr/pdf/pubs/mafri-potatoe.pdf',
language='en')],
)
potato_topic.add_child(doc_node)
return channel
def get_contents(parent, path):
doc = get_page(path)
try:
menu_row = doc.find('div', {'id': 'row-exu'})
except Exception as e:
LOGGER.error('get_contents: %s : %s' % (e, doc))
return
for content in menu_row.find_all('div', {'class': 'col-md-3'}):
try:
title = content.find('div', {'class': 'txtline'}).get_text()
thumbnail = content.find('a').find('img')['src']
thumbnail = get_absolute_path(thumbnail)
main_file, master_file, source_id = get_content_link(content)
LOGGER.info(' content: %s: %s' % (source_id, title))
if main_file.endswith('mp4'):
video = VideoNode(title=title,
source_id=source_id,
license=licenses.PUBLIC_DOMAIN,
thumbnail=thumbnail,
files=[VideoFile(main_file)])
parent.add_child(video)
elif main_file.endswith('pdf'):
pdf = DocumentNode(title=title,
source_id=source_id,
license=licenses.PUBLIC_DOMAIN,
thumbnail=thumbnail,
files=[DocumentFile(main_file)])
parent.add_child(pdf)
elif main_file.endswith('html') and master_file.endswith('zip'):
zippath = get_zip_file(master_file, main_file)
if zippath:
html5app = HTML5AppNode(
title=title,
source_id=source_id,
license=licenses.PUBLIC_DOMAIN,
thumbnail=thumbnail,
files=[HTMLZipFile(zippath)],
)
parent.add_child(html5app)
else:
LOGGER.error('Content not supported: %s, %s' %
(main_file, master_file))
except Exception as e:
LOGGER.error('get_contents: %s : %s' % (e, content))
def construct_channel(self, **kwargs):
channel = self.get_channel(**kwargs)
potato_topic = TopicNode(title="Potatoes!", source_id="<potatoes_id>")
channel.add_child(potato_topic)
document_node = DocumentNode(
title="Growing potatoes",
description="An article about growing potatoes on your rooftop.",
source_id="pubs/mafri-potatoe",
license=get_license("CC BY",
copyright_holder="University of Alberta"),
language="en",
files=[
DocumentFile(
path="https://www.gov.mb.ca/inr/pdf/pubs/mafri-potatoe.pdf",
language="en",
)
],
)
potato_topic.add_child(document_node)
return channel
def construct_channel(self, **kwargs):
channel = self.get_channel(**kwargs)
# Soupify goalkicker main page
gk_url = 'https://' + self.channel_info['CHANNEL_SOURCE_DOMAIN'] + '/'
gk_soup = get_soup(gk_url)
# Get urls for each goalkicker book
els_with_page_urls = gk_soup.find_all(class_='bookContainer')
page_urls = [
gk_url + el.find('a')['href'] for el in els_with_page_urls
]
for page_url in page_urls:
# Soupify book page
page_soup = get_soup(page_url)
# Extract and construct book info
book_info = parse_book_info(page_soup)
book_info['absolute_url'] = page_url + book_info['relative_url']
# Add book to channel tree
topic_node_source_id = 'topic/' + book_info['subject']
page_topic_node = TopicNode(title=book_info['subject'],
source_id=topic_node_source_id)
channel.add_child(page_topic_node)
doc_node = DocumentNode(
title=book_info['title'],
description=book_info['description'],
source_id=book_info['source_id'],
license=get_license('CC BY-SA',
copyright_holder='Creative Commons'),
language='en',
files=[
DocumentFile(path=book_info['absolute_url'], language='en')
],
)
page_topic_node.add_child(doc_node)
return channel
def construct_channel(self, *args, **kwargs):
"""
This method is reponsible for creating a `ChannelNode` object and
populating it with `TopicNode` and `ContentNode` children.
"""
# Create channel
########################################################################
channel = self.get_channel(*args, **kwargs) # uses self.channel_info
# Create topics to add to your channel
########################################################################
# Here we are creating a topic named 'Example Topic'
exampletopic = TopicNode(source_id="topic-1", title="Example Topic")
# TODO: Create your topic here
# Now we are adding 'Example Topic' to our channel
channel.add_child(exampletopic)
# TODO: Add your topic to channel here
# You can also add subtopics to topics
# Here we are creating a subtopic named 'Example Subtopic'
examplesubtopic = TopicNode(source_id="topic-1a",
title="Example Subtopic")
# TODO: Create your subtopic here
# Now we are adding 'Example Subtopic' to our 'Example Topic'
exampletopic.add_child(examplesubtopic)
# TODO: Add your subtopic to your topic here
# Content
# You can add documents (pdfs and ePubs), videos, audios, and other content
########################################################################
# let's create a document file called 'Example PDF'
document_file = DocumentFile(
path="http://www.pdf995.com/samples/pdf.pdf")
examplepdf = DocumentNode(title="Example PDF",
source_id="example-pdf",
files=[document_file],
license=get_license(licenses.PUBLIC_DOMAIN))
# TODO: Create your pdf file here (use any url to a .pdf file)
# We are also going to add a video file called 'Example Video'
video_file = VideoFile(
path=
"https://ia600209.us.archive.org/27/items/RiceChef/Rice Chef.mp4")
fancy_license = get_license(
licenses.SPECIAL_PERMISSIONS,
description='Special license for ricecooker fans only.',
copyright_holder='The chef video makers')
examplevideo = VideoNode(title="Example Video",
source_id="example-video",
files=[video_file],
license=fancy_license)
# TODO: Create your video file here (use any url to a .mp4 file)
# Finally, we are creating an audio file called 'Example Audio'
audio_file = AudioFile(
path=
"https://ia802508.us.archive.org/5/items/testmp3testfile/mpthreetest.mp3"
)
exampleaudio = AudioNode(title="Example Audio",
source_id="example-audio",
files=[audio_file],
license=get_license(licenses.PUBLIC_DOMAIN))
# TODO: Create your audio file here (use any url to a .mp3 file)
# Now that we have our files, let's add them to our channel
channel.add_child(examplepdf) # Adding 'Example PDF' to your channel
exampletopic.add_child(
examplevideo) # Adding 'Example Video' to 'Example Topic'
examplesubtopic.add_child(
exampleaudio) # Adding 'Example Audio' to 'Example Subtopic'
# TODO: Add your pdf file to your channel
# TODO: Add your video file to your topic
# TODO: Add your audio file to your subtopic
# the `construct_channel` method returns a ChannelNode that will be
# processed by the ricecooker framework
return channel
def make_random_subtree(parent, depth):
for i in range(45):
istr = str(i)
title = ''.join(
random.choice(string.ascii_uppercase + string.digits)
for _ in range(10))
description = ''.join(
random.choice(string.ascii_uppercase + string.digits)
for _ in range(100))
typ = random.choice("tttttttvadh")
if typ == 't':
topic = TopicNode(
source_id=title + istr,
title=title,
description=description,
author=None,
language=getlang('en').id,
thumbnail=None,
)
parent.add_child(topic)
if depth > 0:
make_random_subtree(topic, depth - 1)
elif typ == 'a':
content11a = AudioNode(
source_id='940ac8ff' + istr,
title='Whale sounds',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=None,
files=[],
)
parent.add_child(content11a)
audio_file = AudioFile(
path='./content/ricecooker-channel-files/Whale_sounds.mp3',
language=getlang('en').id)
content11a.add_file(audio_file)
elif typ == 'd':
content12a = DocumentNode(
source_id='80b7136f' + istr,
title=
'The Supreme Court\u2019s Ruling in Brown vs. Board of Education',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=None,
files=[
DocumentFile(
path=
'./content/ricecooker-channel-files/commonlit_the-supreme-court-s-ruling-in-brown-vs-board-of-education_student.pdf',
language=getlang('en').id)
])
parent.add_child(content12a)
elif typ == 'h':
content13a = HTML5AppNode(
source_id='302723b4' + istr,
title='Sample React app',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail='./content/ricecooker-channel-files/html5_react.jpg',
files=[
HTMLZipFile(
path=
'./content/ricecooker-channel-files/html5_react.zip',
language=getlang('en').id)
])
parent.add_child(content13a)
elif type == 'v':
content14a = VideoNode(
source_id='9e355995',
title='Wave particle duality explained in 2 mins',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
derive_thumbnail=True, # video-specicig flag
thumbnail=None,
files=[
VideoFile(
path=
'./content/ricecooker-channel-files/Wave_particle_duality.mp4',
language=getlang('en').id)
])
parent.add_child(content14a)
def construct_channel(self, **kwargs):
channel = self.get_channel(**kwargs)
# Soupify goalkicker main page
gk_url = 'https://' + self.channel_info['CHANNEL_SOURCE_DOMAIN'] + '/'
gk_soup = get_soup(gk_url)
# Get urls for each goalkicker book
els_with_page_urls = gk_soup.find_all(class_='bookContainer')
page_urls = [
gk_url + el.find('a')['href'] for el in els_with_page_urls
]
for book_counter, page_url in enumerate(page_urls):
# Soupify book page
page_soup = get_soup(page_url)
# Extract and construct book info
book_info = parse_book_info(page_soup)
book_info['absolute_url'] = page_url + book_info['relative_url']
# Add book to channel tree
book_node_source_id = 'topic/' + book_info['subject']
book_node = TopicNode(title=book_info['subject'],
source_id=book_node_source_id)
channel.add_child(book_node)
# Use separate download directory for each book's pdf chunks. Avoids name conflicts between books
download_dir = 'downloads/book_' + str(book_counter).rjust(
2, '0') + '--' + book_info['subject']
# Get chapters info
pdf_path = book_info['absolute_url']
with PDFParser(pdf_path, directory=download_dir) as pdfparser:
chapters = pdfparser.split_chapters()
# Add chapter nodes
for i, chapter in enumerate(chapters):
chapter_node_source_id = book_info[
'source_id'] + '/' + chapter['title']
if chapter['title'].startswith('Chapter'):
chapter_num = re.search('Chapter (\d+)',
chapter['title']).group(1)
chapter_description = 'Chapter ' + chapter_num + ' of the Goalkicker book on ' + book_info[
'subject']
else:
chapter_description = '"' + chapter[
'title'] + '" section of the Goalkicker book on ' + book_info[
'subject']
chapter_node = DocumentNode(
title=chapter['title'],
description=chapter_description,
source_id=chapter_node_source_id,
license=get_license('CC BY-SA',
copyright_holder='Stack Overflow'),
language='en',
files=[DocumentFile(path=chapter['path'], language='en')],
)
book_node.add_child(chapter_node)
return channel
def construct_channel(*args, **kwargs):
""" Start by creating your channel """
# Let's start by creating your own channel (replace <placeholders> with your own values)
channel = ChannelNode(
source_domain="vuzy.com", # (e.g. "jamiealexandre.com")
source_id="apprentice", # (e.g. "my-sushi-chef")
title="My First Try", # (e.g. "My Sushi Chef Channel")
)
""" Create topics to add to your channel """
# Here we are creating a topic named 'Example Topic'
exampletopic = TopicNode(source_id="topic-1", title="Example Topic")
# TODO: Create your topic here
# Now we are adding 'Example Topic' to our channel
channel.add_child(exampletopic)
# TODO: Add your topic to channel here
""" You can also add subtopics to topics """
# Here we are creating a subtopic named 'Example Subtopic'
examplesubtopic = TopicNode(source_id="topic-1a", title="Example Subtopic")
# TODO: Create your subtopic here
# Now we are adding 'Example Subtopic' to our 'Example Topic'
exampletopic.add_child(examplesubtopic)
# TODO: Add your subtopic to your topic here
""" You can also add pdfs, videos, and audio files to your channel """
# Next, let's create a document file called 'Example PDF'
examplepdf = DocumentNode(
title="Example PDF",
source_id="example-pdf",
files=[DocumentFile(path="http://www.pdf995.com/samples/pdf.pdf")],
license=licenses.CC_BY_SA)
# TODO: Create your pdf file here (use any url to a .pdf file)
# We are also going to add a video file called 'Example Video'
examplevideo = VideoNode(
title="Example Video",
source_id="example-video",
files=[
VideoFile(
path=
"https://ia600209.us.archive.org/27/items/RiceChef/Rice Chef.mp4"
)
],
license=licenses.CC_BY_SA)
# TODO: Create your video file here (use any url to a .mp4 file)
# Finally, we are creating an audio file called 'Example Audio'
exampleaudio = AudioNode(
title="Example Audio",
source_id="example-audio",
files=[
AudioFile(
path=
"https://ia802508.us.archive.org/5/items/testmp3testfile/mpthreetest.mp3"
)
],
license=licenses.CC_BY_SA)
# TODO: Create your audio file here (use any url to a .mp3 file)
# Now that we have our files, let's add them to our channel
channel.add_child(examplepdf) # Adding 'Example PDF' to your channel
exampletopic.add_child(
examplevideo) # Adding 'Example Video' to 'Example Topic'
examplesubtopic.add_child(
exampleaudio) # Adding 'Example Audio' to 'Example Subtopic'
# TODO: Add your pdf file to your channel
# TODO: Add your video file to your topic
# TODO: Add your audio file to your subtopic
return channel
def create_content_nodes(self, channel):
"""
This function uses the methods `add_child` and `add_file` to build the
hierarchy of topic nodes and content nodes. Every content node is associated
with the underlying file node.
"""
content_nodes_folder = TopicNode(
source_id='121232ms',
title='Content Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
channel.add_child(content_nodes_folder)
# AUDIO
audio_nodes_folder = TopicNode(
source_id='138iuh23iu',
title='Audio Files',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(audio_nodes_folder)
audio_node = AudioNode(
source_id='940ac8ff',
title='Whale sounds',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=None,
files=[],
)
audio_nodes_folder.add_child(audio_node)
audio_file = AudioFile(
path='./content/ricecooker-channel-files/Whale_sounds.mp3',
language=getlang('en').id)
audio_node.add_file(audio_file)
# DOCUMENTS
documents_folder = TopicNode(
source_id='asanlksnaklsn',
title='Document Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(documents_folder)
document_node = DocumentNode(
source_id='80b7136f',
title=
'The Supreme Court\u2019s Ruling in Brown vs. Board of Education',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=None,
files=[
DocumentFile(
path=
'./content/ricecooker-channel-files/commonlit_the-supreme-court-s-ruling-in-brown-vs-board-of-education_student.pdf',
language=getlang('en').id)
])
documents_folder.add_child(document_node)
# HTML5 APPS
html5apps_folder = TopicNode(
source_id='asasa331',
title='HTML5App Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(html5apps_folder)
html5_node_a = HTML5AppNode(
source_id='302723b4',
title='Sample React app',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail='./content/ricecooker-channel-files/html5_react.jpg',
files=[
HTMLZipFile(
path='./content/ricecooker-channel-files/html5_react.zip',
language=getlang('en').id)
])
html5apps_folder.add_child(html5_node_a)
html5_node_b = HTML5AppNode(
source_id='3f91184e',
title='Sample Vue.js app',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail='./content/ricecooker-channel-files/html5_vuejs.jpg',
files=[
HTMLZipFile(
path='./content/ricecooker-channel-files/html5_vuejs.zip',
language=getlang('en').id)
])
html5apps_folder.add_child(html5_node_b)
html5_node_c = HTML5AppNode(
source_id='0aec4296',
title='Sample wget-scraped web content',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=
'./content/ricecooker-channel-files/html5_wget_scraped.jpg',
files=[
HTMLZipFile(
path=
'./content/ricecooker-channel-files/html5_wget_scraped.zip',
language=getlang('en').id)
])
html5apps_folder.add_child(html5_node_c)
# VIDEOS
videos_folder = TopicNode(
source_id='121213m3m3',
title='Video Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(videos_folder)
video_node = VideoNode(
source_id='9e355995',
title='Wave particle duality explained in 2 mins',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
derive_thumbnail=True, # video-specicig flag
thumbnail=None,
files=[
VideoFile(
path=
'./content/ricecooker-channel-files/Wave_particle_duality.mp4',
language=getlang('en').id)
])
videos_folder.add_child(video_node)
def add_node_document(booklist, level_topic, as_booklist):
"""
Add books as DocumentNode under a specific level of reading.
Parameters:
* booklist - The list of books to be added as DocumentNodes
* level_topic - The TopicNode regarding current level that the DocumentNodes
will be attached to
* as_booklist - The list of books from African Storybooks
"""
for item in booklist:
# Initialize the source domain and content_id
domain = uuid.uuid5(uuid.NAMESPACE_DNS, "storyweaver.org.in")
book_id = str(item["source_id"])
# If the publisher is AS and the book is found,
# then change the source_domain and content_id
if item["publisher"] == "African Storybook Initiative":
check = check_if_story_in_AS(as_booklist, item["title"])
if check[0]:
domain = uuid.uuid5(uuid.NAMESPACE_DNS,
"www.africanstorybook.org")
book_id = check[1]
# Given that StoryWeaver provides the link to a zip file,
# we will download the zip file and extract the pdf file from it
with tempfile.NamedTemporaryFile(suffix=".zip") as tempf:
try:
resp = downloader.make_request(item["link"],
clear_cookies=False)
resp.raise_for_status()
tempf.write(resp.content)
except Exception as e:
# Do not create the node if download fails
LOGGER.info("Error: {} when downloading {}".format(
e, item["link"]))
continue
filename = ""
with zipfile.ZipFile(tempf.name, "r") as f:
for zipped_file in f.namelist():
if os.path.splitext(zipped_file)[1][1:] == "pdf":
tempdir = os.path.dirname(tempf.name)
f.extract(zipped_file, path=tempdir)
filename = os.path.join(tempdir, zipped_file)
break
# If no pdf file has been found in the zip, do not create the node
if not filename:
continue
# Create the document node with given information
document_file = DocumentFile(path=filename)
language_obj = getlang_by_name(item["language"])
book = DocumentNode(
title=item["title"],
source_id=book_id,
author=item["author"],
provider=item["publisher"],
files=[document_file],
license=get_license(licenses.CC_BY,
copyright_holder="StoryWeaver"),
thumbnail=item.get("thumbnail"),
description=item["description"],
domain_ns=domain,
language=language_obj,
)
level_topic.add_child(book)
def document_file(base_file_path):
return DocumentFile(base_file_path)
def create_content_nodes(self, channel):
"""
This function uses the methods `add_child` and `add_file` to build the
hierarchy of topic nodes (nested folder structure) and content nodes.
Every content node is associated with one or more files.
"""
content_nodes_folder = TopicNode(
source_id='uniqid001',
title='Content Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
channel.add_child(content_nodes_folder)
# AUDIO
audio_nodes_folder = TopicNode(
source_id='uniqid002',
title='Audio Files Folder',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(audio_nodes_folder)
audio_node = AudioNode(
source_id='uniqid003',
title='Whale sounds',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=None,
files=[],
)
audio_nodes_folder.add_child(audio_node)
audio_file = AudioFile(
path=
'./content/ricecooker-channel-files/Whale_sounds.mp3', # note path can also be a URL
language=getlang('en').id)
audio_node.add_file(audio_file)
# DOCUMENTS
documents_folder = TopicNode(
source_id='uniqid004',
title='Document Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(documents_folder)
document_node = DocumentNode(
source_id='uniqid005',
title=
'The Supreme Court\u2019s Ruling in Brown vs. Board of Education',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail=None,
files=[
DocumentFile(
path=
'./content/ricecooker-channel-files/brown-vs-board-of-education.pdf',
language=getlang('en').id)
])
documents_folder.add_child(document_node)
# HTML5 APPS
html5apps_folder = TopicNode(
source_id='uniqid006',
title='HTML5App Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(html5apps_folder)
html5_node = HTML5AppNode(
source_id='uniqid007',
title='HTMLWeb capabilities test',
author='First Last (author\'s name)',
description=
'Tests different HTML/JS capabilities. What capabilities are allowed and disallowed by the sandboxed iframe used to render HTML5App nodes on Kolibri.',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail='./content/ricecooker-channel-files/html5_tests.jpg',
files=[
HTMLZipFile(
path='./content/ricecooker-channel-files/html5_tests.zip',
language=getlang('en').id)
])
html5apps_folder.add_child(html5_node)
html5_node2 = HTML5AppNode(
source_id='uniqid008',
title='Sample Vue.js app',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
thumbnail='./content/ricecooker-channel-files/html5_vuejs.jpg',
files=[
HTMLZipFile(
path='./content/ricecooker-channel-files/html5_vuejs.zip',
language=getlang('en').id)
])
html5apps_folder.add_child(html5_node2)
# VIDEOS
videos_folder = TopicNode(
source_id='uniqid009',
title='Video Nodes',
description='Put folder description here',
author=None,
language=getlang('en').id,
thumbnail=None,
)
content_nodes_folder.add_child(videos_folder)
video_node = VideoNode(
source_id='uniqid010',
title='Wave particle duality explained in 2 mins',
author='First Last (author\'s name)',
description='Put file description here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Copyright holder name'),
derive_thumbnail=True, # video-specicig flag
thumbnail=None,
files=[
VideoFile(
path=
'./content/ricecooker-channel-files/Wave_particle_duality.mp4',
language=getlang('en').id)
])
videos_folder.add_child(video_node)
youtube_id = 'VJyk81HmcZQ'
video_node2 = VideoNode(
source_id=youtube_id, # usually set source_id to youtube_id
title='Estimating division that results in non whole numbers',
author='Sal Khan',
description='Video description would go here',
language=getlang('en').id,
license=get_license(licenses.CC_BY,
copyright_holder='Khan Academy'),
derive_thumbnail=True, # video-specicig flag
thumbnail=None,
files=[
YouTubeVideoFile(youtube_id=youtube_id,
high_resolution=False,
language='en'),
YouTubeSubtitleFile(youtube_id=youtube_id, language='ko')
])
videos_folder.add_child(video_node2)