v/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2020-11-18 19:53:54 -08:00
Code Issues Releases Wiki Activity

[olympicchannel] add support for episodes of a series, fix video ID extraction

Browse Source
This commit is contained in:
ealgase 2018-12-14 20:12:44 -05:00
parent 54c138bba2
commit 65e9416c74
1 changed files with 56 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
youtube_dl/extractor/olympicchannel.py
View File

@ -8,17 +8,66 @@ import re
class OlympicChannelIE(InfoExtractor):
IE_NAME = 'olympicchannel'
_VALID_URL = r'https?://(?:www\.)?olympicchannel\.com/(?P<language>..)/video/detail/(?P<display_id>.+)/?'
_VALID_URL = r'https?://(?:www\.)?olympicchannel\.com/(?P<language>..)/(original-series|video)/detail/(.+?/.+?/)?(.+?/)?(?P<display_id>.+)/?'
_TESTS = [
{
'url': 'https://www.olympicchannel.com/en/video/detail/news-of-the-week-with-ash-tulloch-x9414/',
'md5': 'aee7e665ad4bf45936e0f5d861e56ac5',
'info_dict': {
'_type': 'video',
'id': 'E18112220',
'ext': 'm3u8',
'title': 'News of the Week with Ash Tulloch',
'thumbnail': 'https://img.olympicchannel.com/images/image/private/t_social_share_thumb/primary/fzcmi2e6kji6cnjjs1xz',
'description': 'Exclusive interviews with Rika Kihira after her Grand Prix finals win, Yuzuru Hanyu&#39;s coach on the injured star, and Valerie Adams on Tokyo.',
}
},
{
'url': 'https://www.olympicchannel.com/en/original-series/detail/fashion-behind-the-games/fashion-behind-the-games-season-1/episodes/past-and-present-field-hockey/',
'md5': '0da7ace7ee712e777e56cdc736edfcb5',
'info_dict': {
'_type': 'video',
'id': 'E17060701',
'ext': 'm3u8',
'title': 'Past and Present – Field hockey',
'thumbnail': 'https://img.olympicchannel.com/images/image/private/t_social_share_thumb/primary/z61ca9vgb4h6t6r2se1f',
'description': 'We reunite a pair of &quot;Las Leonas&quot; and travel back to the early days of field hockey.',
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) # video id isn't included in URL, but is in the URL to the video
display_id = mobj.group('display_id') # display id is in URL, however
webpage = self._download_webpage(url, display_id)
m3u8_url = self._html_search_regex(r'<meta name="video_url" content="(.+?)" />', webpage, 'm3u8_url') # extract URL of video's m3u8 playlist
title = self._html_search_regex(r'<meta name="episode_title" content="(.+?)" />', webpage, 'title') or self._html_search_regex(r'<title>(.+?) \| Olympic Channel</title>', webpage, 'title') # extract title
video_id = self._search_regex(r'_(.........)_', m3u8_url, 'id') # extract unique video id from m3u8
thumbnail_url = self._html_search_regex(r'<meta name="og:image" content="(.+?)" />', webpage, 'thumbnail')
return {
'_type': 'video',
'display_id': display_id,
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'formats': self._extract_m3u8_formats(m3u8_url, video_id),
'thumbnail': thumbnail_url,
}
'''
class OlympicChannelOriginalIE(InfoExtractor):
IE_NAME = 'olympicchannel:original'
_VALID_URL = r'https?://(?:www\.)?olympicchannel\.com/(?P<language>..)/original-series/detail/(?P<series_name>.+)/episodes/(?P<display_id>.+)/?'
_TEST = {
'url': 'https://www.olympicchannel.com/en/video/detail/news-of-the-week-with-ash-tulloch-x9414/',
'md5': 'aee7e665ad4bf45936e0f5d861e56ac5',
'info_dict': {
'_type': 'video',
'id': 'E18112220',
'id': 'E17060701',
'ext': 'm3u8',
'title': 'News of the Week with Ash Tulloch',
'thumbnail': 'https://img.olympicchannel.com/images/image/private/t_social_share_thumb/primary/fzcmi2e6kji6cnjjs1xz',
'description': 'Exclusive interviews with Rika Kihira after her Grand Prix finals win, Yuzuru Hanyu&#39;s coach on the injured star, and Valerie Adams on Tokyo.',
'title': 'Past and Present – Field hockey',
'thumbnail': 'https://img.olympicchannel.com/images/image/private/t_social_share_thumb/primary/z61ca9vgb4h6t6r2se1f',
'description': 'We reunite a pair of &quot;Las Leonas&quot; and travel back to the early days of field hockey.',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
@ -36,7 +85,7 @@ class OlympicChannelIE(InfoExtractor):
video_id = self._search_regex(r'St1-_(.+)_', m3u8_url, 'id') # extract unique video id from m3u8
thumbnail_url = self._html_search_regex(r'<meta name="og:image" content="(.+?)" />', webpage, 'thumbnail')
return {
'_type': 'video',
'_type': 'multi_video',
'display_id': display_id,
'id': video_id,
'title': title,
@ -44,3 +93,4 @@ class OlympicChannelIE(InfoExtractor):
'formats': self._extract_m3u8_formats(m3u8_url, video_id),
'thumbnail': thumbnail_url,
}
'''