dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[nowness] Simplify

This commit is contained in:
Sergey M․ 2015-09-13 19:18:57 +06:00
parent d5d38d16ae
commit 82c18e2a53
2 changed files with 57 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
youtube_dl/extractor/__init__.py
View File

@ -408,7 +408,7 @@ from .novamov import NovaMovIE
from .nowness import ( from .nowness import (
NownessIE, NownessIE,
NownessPlaylistIE, NownessPlaylistIE,
NownessSerieIE, NownessSeriesIE,
) )
from .nowtv import NowTVIE from .nowtv import NowTVIE
from .nowvideo import NowVideoIE from .nowvideo import NowVideoIE

107
youtube_dl/extractor/nowness.py
View File

@ -4,11 +4,14 @@ from __future__ import unicode_literals
from .brightcove import BrightcoveIE from .brightcove import BrightcoveIE
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ExtractorError from ..utils import ExtractorError
from ..compat import compat_urllib_request from ..compat import (
compat_str,
compat_urllib_request,
)
class NownessBaseIE(InfoExtractor): class NownessBaseIE(InfoExtractor):
def extract_url_result(self, post): def _extract_url_result(self, post):
if post['type'] == 'video': if post['type'] == 'video':
for media in post['media']: for media in post['media']:
if media['type'] == 'video': if media['type'] == 'video':
@ -18,7 +21,7 @@ class NownessBaseIE(InfoExtractor):
player_code = self._download_webpage( player_code = self._download_webpage(
'http://www.nowness.com/iframe?id=%s' % video_id, video_id, 'http://www.nowness.com/iframe?id=%s' % video_id, video_id,
note='Downloading player JavaScript', note='Downloading player JavaScript',
errnote='Player download failed') errnote='Unable to download player JavaScript')
bc_url = BrightcoveIE._extract_brightcove_url(player_code) bc_url = BrightcoveIE._extract_brightcove_url(player_code)
if bc_url is None: if bc_url is None:
raise ExtractorError('Could not find player definition') raise ExtractorError('Could not find player definition')
@ -32,50 +35,46 @@ class NownessBaseIE(InfoExtractor):
# return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique') # return self.url_result('http://cinematique.com/embed/%s' % video_id, 'Cinematique')
pass pass
def api_request(self, url, request_path): def _api_request(self, url, request_path):
display_id = self._match_id(url) display_id = self._match_id(url)
request = compat_urllib_request.Request(
lang = 'zh-cn' if 'cn.nowness.com' in url else 'en-us' 'http://api.nowness.com/api/' + request_path % display_id,
request = compat_urllib_request.Request('http://api.nowness.com/api/' + request_path % display_id, headers={ headers={
'X-Nowness-Language': lang, 'X-Nowness-Language': 'zh-cn' if 'cn.nowness.com' in url else 'en-us',
}) })
json_data = self._download_json(request, display_id) return display_id, self._download_json(request, display_id)
return display_id, json_data
class NownessIE(NownessBaseIE): class NownessIE(NownessBaseIE):
IE_NAME = 'nowness' IE_NAME = 'nowness'
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])' _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/(?:story|(?:series|category)/[^/]+)/(?P<id>[^/]+?)(?:$|[?#])'
_TESTS = [ _TESTS = [{
{ 'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation',
'url': 'https://www.nowness.com/story/candor-the-art-of-gesticulation', 'md5': '068bc0202558c2e391924cb8cc470676',
'md5': '068bc0202558c2e391924cb8cc470676', 'info_dict': {
'info_dict': { 'id': '2520295746001',
'id': '2520295746001', 'ext': 'mp4',
'ext': 'mp4', 'title': 'Candor: The Art of Gesticulation',
'title': 'Candor: The Art of Gesticulation', 'description': 'Candor: The Art of Gesticulation',
'description': 'Candor: The Art of Gesticulation', 'thumbnail': 're:^https?://.*\.jpg',
'thumbnail': 're:^https?://.*\.jpg', 'uploader': 'Nowness',
'uploader': 'Nowness', }
} }, {
}, 'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
{ 'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr', 'info_dict': {
'md5': 'e79cf125e387216f86b2e0a5b5c63aa3', 'id': '3716354522001',
'info_dict': { 'ext': 'mp4',
'id': '3716354522001', 'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'ext': 'mp4', 'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', 'thumbnail': 're:^https?://.*\.jpg',
'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR', 'uploader': 'Nowness',
'thumbnail': 're:^https?://.*\.jpg', }
'uploader': 'Nowness', }]
}
},
]
def _real_extract(self, url): def _real_extract(self, url):
display_id, post = self.api_request(url, 'post/getBySlug/%s') _, post = self._api_request(url, 'post/getBySlug/%s')
return self.extract_url_result(post) return self._extract_url_result(post)
class NownessPlaylistIE(NownessBaseIE): class NownessPlaylistIE(NownessBaseIE):
@ -83,33 +82,39 @@ class NownessPlaylistIE(NownessBaseIE):
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)' _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/playlist/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues', 'url': 'https://www.nowness.com/playlist/3286/i-guess-thats-why-they-call-it-the-blues',
'info_dict': 'info_dict': {
{
'id': '3286', 'id': '3286',
}, },
'playlist_mincount': 8, 'playlist_mincount': 8,
} }
def _real_extract(self, url): def _real_extract(self, url):
playlist_id, playlist = self.api_request(url, 'post?PlaylistId=%s') playlist_id, playlist = self._api_request(url, 'post?PlaylistId=%s')
entries = [self.extract_url_result(item) for item in playlist['items']] entries = [self._extract_url_result(item) for item in playlist['items']]
return self.playlist_result(entries, playlist_id) return self.playlist_result(entries, playlist_id)
class NownessSerieIE(NownessBaseIE): class NownessSeriesIE(NownessBaseIE):
IE_NAME = 'nowness:serie' IE_NAME = 'nowness:series'
_VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])' _VALID_URL = r'https?://(?:(?:www|cn)\.)?nowness\.com/series/(?P<id>[^/]+?)(?:$|[?#])'
_TEST = { _TEST = {
'url': 'https://www.nowness.com/series/60-seconds', 'url': 'https://www.nowness.com/series/60-seconds',
'info_dict': 'info_dict': {
{
'id': '60', 'id': '60',
'title': '60 Seconds',
'description': 'One-minute wisdom in a new NOWNESS series',
}, },
'playlist_mincount': 4, 'playlist_mincount': 4,
} }
def _real_extract(self, url): def _real_extract(self, url):
display_id, serie = self.api_request(url, 'series/getBySlug/%s') display_id, series = self._api_request(url, 'series/getBySlug/%s')
serie_id = str(serie['id']) entries = [self._extract_url_result(post) for post in series['posts']]
entries = [self.extract_url_result(post) for post in serie['posts']] series_title = None
return self.playlist_result(entries, serie_id) series_description = None
translations = series.get('translations', [])
if translations:
series_title = translations[0].get('title') or translations[0]['seoTitle']
series_description = translations[0].get('seoDescription')
return self.playlist_result(
entries, compat_str(series['id']), series_title, series_description)