Merge pull request #8061 from dstftw/introduce-chapter-and-series-fields

Introduce chapter and series fields
This commit is contained in:
Sergey M 2016-01-03 03:54:22 +06:00
commit 3f3343cd3e
3 changed files with 96 additions and 5 deletions

View file

@ -201,6 +201,26 @@ class InfoExtractor(object):
end_time: Time in seconds where the reproduction should end, as
specified in the URL.
The following fields should only be used when the video belongs to some logical
chapter or section:
chapter: Name or title of the chapter the video belongs to.
chapter_number: Number of the chapter the video belongs to, as an integer.
chapter_id: Id of the chapter the video belongs to, as a unicode string.
The following fields should only be used when the video is an episode of some
series or programme:
series: Title of the series or programme the video episode belongs to.
season: Title of the season the video episode belongs to.
season_number: Number of the season the video episode belongs to, as an integer.
season_id: Id of the season the video episode belongs to, as a unicode string.
episode: Title of the video episode. Unlike mandatory video title field,
this field should denote the exact title of the video episode
without any kind of decoration.
episode_number: Number of the video episode within a season, as an integer.
episode_id: Id of the video episode, as a unicode string.
Unless mentioned otherwise, the fields should be Unicode strings.
Unless mentioned otherwise, None is equivalent to absence of information.

View file

@ -244,10 +244,25 @@ def _real_extract(self, url):
'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,
course_id, 'Downloading course curriculum')
entries = [
self.url_result(
'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), 'Udemy')
for asset in response if asset.get('assetType') or asset.get('asset_type') == 'Video'
]
entries = []
chapter, chapter_number = None, None
for asset in response:
asset_type = asset.get('assetType') or asset.get('asset_type')
if asset_type == 'Video':
asset_id = asset.get('id')
if asset_id:
entry = {
'_type': 'url_transparent',
'url': 'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']),
'ie_key': UdemyIE.ie_key(),
}
if chapter_number:
entry['chapter_number'] = chapter_number
if chapter:
entry['chapter'] = chapter
entries.append(entry)
elif asset.get('type') == 'chapter':
chapter_number = asset.get('index') or asset.get('object_index')
chapter = asset.get('title')
return self.playlist_result(entries, course_id, course_title)

View file

@ -23,11 +23,56 @@ class VideomoreIE(InfoExtractor):
'ext': 'flv',
'title': 'В гостях Алексей Чумаков и Юлия Ковальчук',
'description': 'В гостях лучшие романтические комедии года, «Выживший» Иньярриту и «Стив Джобс» Дэнни Бойла.',
'series': 'Кино в деталях',
'episode': 'В гостях Алексей Чумаков и Юлия Ковальчук',
'episode_number': None,
'season': 'Сезон 2015',
'season_number': 5,
'thumbnail': 're:^https?://.*\.jpg',
'duration': 2910,
'age_limit': 16,
'view_count': int,
},
}, {
'url': 'http://videomore.ru/embed/259974',
'info_dict': {
'id': '259974',
'ext': 'flv',
'title': '80 серия',
'description': '«Медведей» ждет решающий матч. Макеев выясняет отношения со Стрельцовым. Парни узнают подробности прошлого Макеева.',
'series': 'Молодежка',
'episode': '80 серия',
'episode_number': 40,
'season': '2 сезон',
'season_number': 2,
'thumbnail': 're:^https?://.*\.jpg',
'duration': 2809,
'age_limit': 16,
'view_count': int,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://videomore.ru/molodezhka/sezon_promo/341073',
'info_dict': {
'id': '341073',
'ext': 'flv',
'title': 'Команда проиграла из-за Бакина?',
'description': 'Молодежка 3 сезон скоро',
'series': 'Молодежка',
'episode': 'Команда проиграла из-за Бакина?',
'episode_number': None,
'season': 'Промо',
'season_number': 99,
'thumbnail': 're:^https?://.*\.jpg',
'duration': 29,
'age_limit': 16,
'view_count': int,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://videomore.ru/elki_3?track_id=364623',
'only_matching': True,
@ -81,10 +126,21 @@ def _real_extract(self, url):
'url': thumbnail,
} for thumbnail in data.get('big_thumbnail_urls', [])]
series = data.get('project_title')
episode = data.get('title')
episode_number = int_or_none(data.get('episode_of_season') or None)
season = data.get('season_title')
season_number = int_or_none(data.get('season_pos') or None)
return {
'id': video_id,
'title': title,
'description': description,
'series': series,
'episode': episode,
'episode_number': episode_number,
'season': season,
'season_number': season_number,
'thumbnails': thumbnails,
'timestamp': timestamp,
'duration': duration,