[noovo] Fix extraction (closes #14214)
This commit is contained in:
parent
6be44a50ed
commit
a4245acef8
1 changed files with 32 additions and 29 deletions
|
@ -6,6 +6,7 @@ from .common import InfoExtractor
|
||||||
from ..compat import compat_str
|
from ..compat import compat_str
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
int_or_none,
|
int_or_none,
|
||||||
|
js_to_json,
|
||||||
smuggle_url,
|
smuggle_url,
|
||||||
try_get,
|
try_get,
|
||||||
)
|
)
|
||||||
|
@ -24,8 +25,6 @@ class NoovoIE(InfoExtractor):
|
||||||
'timestamp': 1491399228,
|
'timestamp': 1491399228,
|
||||||
'upload_date': '20170405',
|
'upload_date': '20170405',
|
||||||
'uploader_id': '618566855001',
|
'uploader_id': '618566855001',
|
||||||
'creator': 'vtele',
|
|
||||||
'view_count': int,
|
|
||||||
'series': 'RPM+',
|
'series': 'RPM+',
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
|
@ -37,13 +36,11 @@ class NoovoIE(InfoExtractor):
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '5395865725001',
|
'id': '5395865725001',
|
||||||
'title': 'Épisode 13 : Les retrouvailles',
|
'title': 'Épisode 13 : Les retrouvailles',
|
||||||
'description': 'md5:336d5ebc5436534e61d16e63ddfca327',
|
'description': 'md5:888c3330f0c1b4476c5bc99a1c040473',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'timestamp': 1492019320,
|
'timestamp': 1492019320,
|
||||||
'upload_date': '20170412',
|
'upload_date': '20170412',
|
||||||
'uploader_id': '618566855001',
|
'uploader_id': '618566855001',
|
||||||
'creator': 'vtele',
|
|
||||||
'view_count': int,
|
|
||||||
'series': "L'amour est dans le pré",
|
'series': "L'amour est dans le pré",
|
||||||
'season_number': 5,
|
'season_number': 5,
|
||||||
'episode': 'Épisode 13',
|
'episode': 'Épisode 13',
|
||||||
|
@ -58,40 +55,46 @@ class NoovoIE(InfoExtractor):
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
data = self._download_json(
|
webpage = self._download_webpage(url, video_id)
|
||||||
'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id,
|
|
||||||
video_id)['data']
|
|
||||||
|
|
||||||
content = try_get(data, lambda x: x['contents'][0])
|
bc_url = BrightcoveNewIE._extract_url(self, webpage)
|
||||||
|
|
||||||
brightcove_id = data.get('brightcoveId') or content['brightcoveId']
|
data = self._parse_json(
|
||||||
|
self._search_regex(
|
||||||
|
r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data',
|
||||||
|
default='{}'),
|
||||||
|
video_id, transform_source=js_to_json, fatal=False)
|
||||||
|
|
||||||
|
title = try_get(
|
||||||
|
data, lambda x: x['video']['nom'],
|
||||||
|
compat_str) or self._html_search_meta(
|
||||||
|
'dcterms.Title', webpage, 'title', fatal=True)
|
||||||
|
|
||||||
|
description = self._html_search_meta(
|
||||||
|
('dcterms.Description', 'description'), webpage, 'description')
|
||||||
|
|
||||||
series = try_get(
|
series = try_get(
|
||||||
data, (
|
data, lambda x: x['emission']['nom']) or self._search_regex(
|
||||||
lambda x: x['show']['title'],
|
r'<div[^>]+class="banner-card__subtitle h4"[^>]*>([^<]+)',
|
||||||
lambda x: x['season']['show']['title']),
|
webpage, 'series', default=None)
|
||||||
compat_str)
|
|
||||||
|
|
||||||
episode = None
|
season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {}
|
||||||
og = data.get('og')
|
season = try_get(season_el, lambda x: x['nom'], compat_str)
|
||||||
if isinstance(og, dict) and og.get('type') == 'video.episode':
|
season_number = int_or_none(try_get(season_el, lambda x: x['numero']))
|
||||||
episode = og.get('title')
|
|
||||||
|
|
||||||
video = content or data
|
episode_el = try_get(season_el, lambda x: x['episode'], dict) or {}
|
||||||
|
episode = try_get(episode_el, lambda x: x['nom'], compat_str)
|
||||||
|
episode_number = int_or_none(try_get(episode_el, lambda x: x['numero']))
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'_type': 'url_transparent',
|
'_type': 'url_transparent',
|
||||||
'ie_key': BrightcoveNewIE.ie_key(),
|
'ie_key': BrightcoveNewIE.ie_key(),
|
||||||
'url': smuggle_url(
|
'url': smuggle_url(bc_url, {'geo_countries': ['CA']}),
|
||||||
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
|
'title': title,
|
||||||
{'geo_countries': ['CA']}),
|
'description': description,
|
||||||
'id': brightcove_id,
|
|
||||||
'title': video.get('title'),
|
|
||||||
'creator': video.get('source'),
|
|
||||||
'view_count': int_or_none(video.get('viewsCount')),
|
|
||||||
'series': series,
|
'series': series,
|
||||||
'season_number': int_or_none(try_get(
|
'season': season,
|
||||||
data, lambda x: x['season']['seasonNumber'])),
|
'season_number': season_number,
|
||||||
'episode': episode,
|
'episode': episode,
|
||||||
'episode_number': int_or_none(data.get('episodeNumber')),
|
'episode_number': episode_number,
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue