def add_files(node, file_list):
for f in file_list:
path = f.get('path')
if path is not None:
abspath = get_abspath(path) # NEW: expand content:// --> ./content/ in file paths
else:
abspath = None
file_type = guess_file_type(node.kind, filepath=abspath, youtube_id=f.get('youtube_id'), web_url=f.get('web_url'), encoding=f.get('encoding'))
if file_type == FileTypes.AUDIO_FILE:
node.add_file(files.AudioFile(path=abspath, language=f.get('language')))
elif file_type == FileTypes.THUMBNAIL:
node.add_file(files.ThumbnailFile(path=abspath))
elif file_type == FileTypes.DOCUMENT_FILE:
node.add_file(files.DocumentFile(path=abspath, language=f.get('language')))
elif file_type == FileTypes.HTML_ZIP_FILE:
node.add_file(files.HTMLZipFile(path=abspath, language=f.get('language')))
elif file_type == FileTypes.VIDEO_FILE:
node.add_file(files.VideoFile(path=abspath, language=f.get('language'), ffmpeg_settings=f.get('ffmpeg_settings')))
elif file_type == FileTypes.SUBTITLE_FILE:
node.add_file(files.SubtitleFile(path=abspath, language=f['language']))
elif file_type == FileTypes.BASE64_FILE:
node.add_file(files.Base64ImageFile(encoding=f['encoding']))
elif file_type == FileTypes.WEB_VIDEO_FILE:
node.add_file(files.WebVideoFile(web_url=f['web_url'], high_resolution=f.get('high_resolution')))
elif file_type == FileTypes.YOUTUBE_VIDEO_FILE:
node.add_file(files.YouTubeVideoFile(youtube_id=f['youtube_id'], high_resolution=f.get('high_resolution')))
node.add_file(files.YouTubeSubtitleFile(youtube_id=f['youtube_id'], language='en'))
else:
raise UnknownFileTypeError("Unrecognized file type '{0}'".format(f['path']))
def scrape_iversity(channel):
url = "{}/en/my/courses/rethinking-us-them-integration-and-diversity-in-europe/lesson_units".format(
BASE_URL)
LOGGER.info(" Scraping Migration Matters at {}".format(url))
source = read_source(url)
chapters = source.find_all('div', {'class': 'chapter-units-wrapper'})
for chapter in chapters:
title = str(chapter.find('div', {'class': 'chapter-title'}).string)
source_id = title.strip().replace(" ", "_")
topic = nodes.TopicNode(source_id=source_id, title=title)
lessons = chapter.find_all('a', {'class': 'unit-wrapper'})
for lesson in lessons:
video_exists = lesson.find('i', {'class': 'unit_video'})
video_title = str(
lesson.find('span', {
'class': 'unit-title'
}).string).strip()
if video_exists:
video_source_id = video_title.replace(" ", "_")
video_url = "{}{}".format(BASE_URL, lesson.attrs["href"])
video_source = read_source(video_url)
video_info = video_source.find('video')
video_subtitle_path = video_info.find('track', {
'kind': 'subtitles'
}).attrs["src"]
video_subtitle = files.SubtitleFile(
path=video_subtitle_path,
language=languages.getlang('en').code)
video_link = video_info.find('source', {
'res': '480'
}).attrs["src"]
video_file = files.VideoFile(
path=video_link, language=languages.getlang('en').code)
video_node = nodes.VideoNode(
source_id=video_source_id,
title=video_title,
files=[video_file, video_subtitle],
license=CHANNEL_LICENSE,
copyright_holder=COPYRIGHT_HOLDER)
LOGGER.info(" Uploading video - {}".format(
video_title.strip()))
topic.add_child(video_node)
else:
LOGGER.info(
"Format of the file is not supported by the sushi chef : {}"
.format(video_title))
channel.add_child(topic)
def add_files(node, file_list):
EXPECTED_FILE_TYPES = [
VIDEO_FILE, AUDIO_FILE, DOCUMENT_FILE, HTML5_FILE, THUMBNAIL_FILE,
SUBTITLES_FILE
]
for f in file_list:
file_type = f.get('file_type')
if file_type not in EXPECTED_FILE_TYPES:
LOGGER.critical(file_type)
raise NotImplementedError(
'Unexpected File type found in channel json.')
path = f.get('path') # path can be an URL or a local path (or None)
# handle different types of files
if file_type == VIDEO_FILE:
# handle three types of video files
if 'youtube_id' in f:
video_file = files.YouTubeVideoFile(
youtube_id=f['youtube_id'],
download_settings=f.get('download_settings', None),
high_resolution=f.get('high_resolution', True),
maxheight=f.get('maxheight', None),
language=f.get('language', None),
)
elif 'web_url' in f:
video_file = files.WebVideoFile(
web_url=f['web_url'],
download_settings=f.get('download_settings', None),
high_resolution=f.get('high_resolution', True),
maxheight=f.get('maxheight', None),
language=f.get('language', None),
)
else:
video_file = files.VideoFile(
path=f['path'],
language=f.get('language', None),
ffmpeg_settings=f.get('ffmpeg_settings'),
)
node.add_file(video_file)
elif file_type == AUDIO_FILE:
node.add_file(
files.AudioFile(path=f['path'],
language=f.get('language', None)))
elif file_type == DOCUMENT_FILE:
node.add_file(
files.DocumentFile(path=path, language=f.get('language',
None)))
elif file_type == HTML5_FILE:
node.add_file(
files.HTMLZipFile(path=path, language=f.get('language', None)))
elif file_type == THUMBNAIL_FILE:
if 'encoding' in f:
node.add_file(files.Base64ImageFile(encoding=f['encoding'], ))
else:
node.add_file(
files.ThumbnailFile(
path=path,
language=f.get('language', None),
))
elif file_type == SUBTITLES_FILE:
if 'youtube_id' in f:
node.add_file(
files.YouTubeSubtitleFile(youtube_id=f['youtube_id'],
language=f['language']))
else:
node.add_file(
files.SubtitleFile(path=path, language=f['language']))
else:
raise UnknownFileTypeError("Unrecognized file type '{0}'".format(
f['path']))
def crawl_each_post(post_url):
resp = requests.get(post_url, headers=HEADERS)
soup = BeautifulSoup(resp.content, "html.parser")
wrapper = soup.find('div', {'class': 'wpb_wrapper'})
course_name = wrapper.find('div', {
'class': 'vc_custom_heading'
}).getText().strip()
delimiters = " OF ", " FROM "
regex_pattern = '|'.join(map(re.escape, delimiters))
course = re.split(regex_pattern, course_name)[1]
wpb_video_wrapper = wrapper.find_all('div', {'class': 'wpb_video_wrapper'})
if wpb_video_wrapper:
for each_wrapper in wpb_video_wrapper:
video_url = each_wrapper.find('iframe').attrs["src"].split(
"?feature")[0]
video_id = video_url.split("/")[-1]
ydl = youtube_dl.YoutubeDL({
'outtmpl': './downloads/%(id)s.%(ext)s',
'writeautomaticsub': True,
'logger': LOGGER
})
with ydl:
result = ydl.extract_info(
"http://www.youtube.com/watch?v={}".format(video_id),
download=True)
if 'entries' in result:
video = result['entries'][0]
else:
video = result
video_title = video["title"]
video_source_id = video_title.strip().replace(" ", "_")
video_path = "{}/{}.mp4".format(DOWNLOAD_DIRECTORY, video_id)
video_subtitle_path = "{}/{}.en.vtt".format(
DOWNLOAD_DIRECTORY, video_id)
video_file = files.VideoFile(path=video_path,
language=languages.getlang('en').code)
video_subtitle = files.SubtitleFile(
path=video_subtitle_path,
language=languages.getlang('en').code)
video_node = nodes.VideoNode(
source_id=video_source_id,
title=video_title,
files=[video_file, video_subtitle],
license=CHANNEL_LICENSE,
copyright_holder=COPYRIGHT_HOLDER,
)
if course not in EPISODE_DICT:
EPISODE_DICT[course] = [video_node]
else:
EPISODE_DICT[course].append(video_node)
LOGGER.info(" Uploading video - {}".format(video_title.strip()))
else:
LOGGER.info(
"Format of the file is not supported by the sushi chef : {}".
format(course_name))