Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 06:02:51 +08:00
Code Issues Releases Wiki Activity

[ellentube] Implement code review changes.

Browse Source
This commit is contained in:
Alexander Seiler 2017-11-15 18:18:31 +01:00
parent 196b0d7a36
commit 6d006044bc
2 changed files with 57 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

99
youtube_dl/extractor/ellentube.py
View File

@ -5,14 +5,31 @@ from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
urljoin,
)
class EllenTubeBaseIE(InfoExtractor):
API_URL = 'https://api-prod.ellentube.com/'
class EllenTubeIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
https://api-prod\.ellentube\.com/ellenapi/api/item/
|ellentube:
)
(?P<id>
[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}
)'''
def _extract_video_from_json(self, data, video_id, display_id=None):
_TESTS = [{
'url': 'https://api-prod.ellentube.com/ellenapi/api/item/75c64c16-aefd-4558-b4f5-3de09b22e6fc',
'match_only': True,
}, {
'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0',
'match_only': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, video_id)
title = data['title']
description = data.get('description')
publish_time = int_or_none(data.get('publishTime'))
@ -31,21 +48,43 @@ class EllenTubeBaseIE(InfoExtractor):
'id': video_id,
'title': title,
'description': description,
'display_id': display_id,
'duration': duration,
'thumbnail': thumbnail,
'timestamp': publish_time,
'formats': formats,
}
def _extract_playlist_entries_from_json(self, data, display_id):
return [self._extract_video_from_json(elem, elem['id'])
for elem in data if elem.get('type') == 'VIDEO']
def _extract_from_video_id(self, video_id, display_id=None):
api_data = self._download_json(
urljoin(self.API_URL, 'ellenapi/api/item/%s' % video_id), video_id)
return self._extract_video_from_json(api_data, video_id, display_id)
class EllenTubeVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+)\.html'
_TEST = {
'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
'md5': '2fabc277131bddafdd120e0fc0f974c9',
'info_dict': {
'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
'ext': 'mp4',
'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
'duration': 514,
'timestamp': 1508505120000,
'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'(?s)<!--\s*CONTENT\s*-->.*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
webpage, 'video id')
return self.url_result('ellentube:%s' % video_id)
class EllenTubePlaylistIE(InfoExtractor):
def _extract_videos_from_json(self, data, display_id):
return [self.url_result('ellentube:%s' % elem['id'], 'EllenTube')
for elem in data if elem.get('type') == 'VIDEO']
def _extract_playlist(self, url, display_id, extract_description=True):
webpage = self._download_webpage(url, display_id)
@ -59,40 +98,14 @@ class EllenTubeBaseIE(InfoExtractor):
api_search = self._search_regex(
r'"filter"\s*:\s*"(.+?)"', playlist_data, 'playlist api request')
api_data = self._download_json(
urljoin(self.API_URL, 'ellenapi/api/feed/?%s' % api_search), display_id)
'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' % api_search,
display_id)
return self.playlist_result(
self._extract_playlist_entries_from_json(api_data, display_id),
self._extract_videos_from_json(api_data, display_id),
display_id, playlist_title, playlist_description)
class EllenTubeVideoIE(EllenTubeBaseIE):
_VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+)\.html'
_TEST = {
'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html',
'md5': '2fabc277131bddafdd120e0fc0f974c9',
'info_dict': {
'id': '0822171c-3829-43bf-b99f-d77358ae75e3',
'ext': 'mp4',
'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck',
'description': 'md5:76e3355e2242a78ad9e3858e5616923f',
'display_id': 'ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck',
'duration': 514,
'timestamp': 1508505120000,
'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'(?s)<!--\s*CONTENT\s*-->.*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
webpage, 'video id')
return self._extract_from_video_id(video_id, display_id)
class EllenTubeEpisodeIE(EllenTubeBaseIE):
class EllenTubeEpisodeIE(EllenTubePlaylistIE):
_VALID_URL = r'https?://(?:www\.)?ellentube\.com/episode/(?P<id>.+)\.html'
_TEST = {
@ -110,7 +123,7 @@ class EllenTubeEpisodeIE(EllenTubeBaseIE):
return self._extract_playlist(url, display_id)
class EllenTubeStudioIE(EllenTubeBaseIE):
class EllenTubeStudioIE(EllenTubePlaylistIE):
_VALID_URL = r'https?://(?:www\.)?ellentube\.com/studios/(?P<id>.+)\.html'
_TEST = {

1
youtube_dl/extractor/extractors.py
View File

@ -309,6 +309,7 @@ from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE
from .eitb import EitbIE
from .ellentube import (
EllenTubeIE,
EllenTubeEpisodeIE,
EllenTubeStudioIE,
EllenTubeVideoIE,