def download_subtitles(couses, self):
if couses is None:
return
if not couses.has_key('slug'):
return
title = couses['slug']
download_path = self.create_download_directory()
course_path = self.create_course_directory(download_path, title)
data_json = os.path.join(course_path, 'index.json')
with open(data_json, 'wb') as out_file:
json.dump(couses, out_file)
for i, lesson_data in enumerate(couses['lessonData']):
lesson_title = lesson_data['title']
stats_id = lesson_data['statsId']
if stats_id is None:
continue
path = os.path.join(
course_path,
str(i) + "-" + format_filename(lesson_title) + ".vtt")
if not os.path.isfile(path) or os.path.getsize(path) == 0:
print("Downloading subtitle of {0}/{1}".format(
format_filename(lesson_title), path))
lesson_transcript_api = TRANSCRIPTS_PATH + stats_id + ".vtt"
data = requests.get(lesson_transcript_api)
if data is None:
continue
with open(path, 'wb') as local_file:
local_file.writelines(data.iter_lines())
vtt_to_srt(course_path)
def __init__(self, data_dir, query): #Based on https://gist.github.com/bonzanini/af0463b927433c73784d query_fname = helper.format_filename(query) #Handle case where user doesn't want to filter if query_fname == '' : query_fname = 'all' self.outfile = "%s/stream_%s.json" % (data_dir, query_fname) print 'Stream available at : ' + self.outfile
def download_course(url, folder, videos_download, number=None):
course_id, title = get_course_id_and_title(url)
title = helper.format_filename(title)
if number is not None:
title = str(number) + ". " + title
sys.stdout.write(f'{bcolors.BKGREEN} {title} {bcolors.BKENDC}\n')
download_slides(course_id, os.path.join(folder, title))
if videos_download:
download_videos(course_id, os.path.join(folder, title))