From a4245acef85ac2414e77cf2cda4cb39adb617241 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Fri, 15 Sep 2017 23:12:19 +0700
Subject: [PATCH] [noovo] Fix extraction (closes #14214)
---
youtube_dl/extractor/noovo.py | 61 ++++++++++++++++++-----------------
1 file changed, 32 insertions(+), 29 deletions(-)
diff --git a/youtube_dl/extractor/noovo.py b/youtube_dl/extractor/noovo.py
index f7fa098a5..974de3c3e 100644
--- a/youtube_dl/extractor/noovo.py
+++ b/youtube_dl/extractor/noovo.py
@@ -6,6 +6,7 @@ from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
+ js_to_json,
smuggle_url,
try_get,
)
@@ -24,8 +25,6 @@ class NoovoIE(InfoExtractor):
'timestamp': 1491399228,
'upload_date': '20170405',
'uploader_id': '618566855001',
- 'creator': 'vtele',
- 'view_count': int,
'series': 'RPM+',
},
'params': {
@@ -37,13 +36,11 @@ class NoovoIE(InfoExtractor):
'info_dict': {
'id': '5395865725001',
'title': 'Épisode 13 : Les retrouvailles',
- 'description': 'md5:336d5ebc5436534e61d16e63ddfca327',
+ 'description': 'md5:888c3330f0c1b4476c5bc99a1c040473',
'ext': 'mp4',
'timestamp': 1492019320,
'upload_date': '20170412',
'uploader_id': '618566855001',
- 'creator': 'vtele',
- 'view_count': int,
'series': "L'amour est dans le pré",
'season_number': 5,
'episode': 'Épisode 13',
@@ -58,40 +55,46 @@ class NoovoIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
- data = self._download_json(
- 'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id,
- video_id)['data']
+ webpage = self._download_webpage(url, video_id)
- 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(
- data, (
- lambda x: x['show']['title'],
- lambda x: x['season']['show']['title']),
- compat_str)
+ data, lambda x: x['emission']['nom']) or self._search_regex(
+ r'<div[^>]+class="banner-card__subtitle h4"[^>]*>([^<]+)',
+ webpage, 'series', default=None)
- episode = None
- og = data.get('og')
- if isinstance(og, dict) and og.get('type') == 'video.episode':
- episode = og.get('title')
+ season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {}
+ season = try_get(season_el, lambda x: x['nom'], compat_str)
+ season_number = int_or_none(try_get(season_el, lambda x: x['numero']))
- 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 {
'_type': 'url_transparent',
'ie_key': BrightcoveNewIE.ie_key(),
- 'url': smuggle_url(
- self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
- {'geo_countries': ['CA']}),
- 'id': brightcove_id,
- 'title': video.get('title'),
- 'creator': video.get('source'),
- 'view_count': int_or_none(video.get('viewsCount')),
+ 'url': smuggle_url(bc_url, {'geo_countries': ['CA']}),
+ 'title': title,
+ 'description': description,
'series': series,
- 'season_number': int_or_none(try_get(
- data, lambda x: x['season']['seasonNumber'])),
+ 'season': season,
+ 'season_number': season_number,
'episode': episode,
- 'episode_number': int_or_none(data.get('episodeNumber')),
+ 'episode_number': episode_number,
}