[cartoonnetwork] fix extraction(closes #15664)(closes #17224)

This commit is contained in:
Remita Amine 2019-01-17 23:56:37 +01:00
parent 79fec976b0
commit e2dd132f05
1 changed files with 38 additions and 18 deletions

View File

@ -1,20 +1,19 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .turner import TurnerBaseIE from .turner import TurnerBaseIE
from ..utils import int_or_none
class CartoonNetworkIE(TurnerBaseIE): class CartoonNetworkIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html' _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
_TEST = { _TEST = {
'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html', 'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html',
'info_dict': { 'info_dict': {
'id': '8a250ab04ed07e6c014ef3f1e2f9016c', 'id': '6e3375097f63874ebccec7ef677c1c3845fa850e',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Starfire the Cat Lady', 'title': 'How to Draw Upgrade',
'description': 'Robin decides to become a cat so that Starfire will finally love him.', 'description': 'md5:2061d83776db7e8be4879684eefe8c0f',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -25,18 +24,39 @@ class CartoonNetworkIE(TurnerBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups()
query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False):
return self._extract_cvp_info( metadata_re = ''
'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, { if content_re:
'secure': { metadata_re = r'|video_metadata\.content_' + content_re
'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big', return self._search_regex(
'tokenizer_src': 'https://token.vgtf.net/token/token_mobile', r'(?:_cnglobal\.currentVideo\.%s%s)\s*=\s*"(%s)";' % (global_re, metadata_re, value_re),
}, webpage, name, fatal=fatal)
}, {
media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True)
title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True)
info = self._extract_ngtv_info(
media_id, {'networkId': 'cartoonnetwork'}, {
'url': url, 'url': url,
'site_name': 'CartoonNetwork', 'site_name': 'CartoonNetwork',
'auth_required': self._search_regex( 'auth_required': find_field('authType', 'auth type') != 'unauth',
r'_cnglobal\.cvpFullOrPreviewAuth\s*=\s*(true|false);',
webpage, 'auth required', default='false') == 'true',
}) })
series = find_field(
'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage)
info.update({
'id': media_id,
'display_id': display_id,
'title': title,
'description': self._html_search_meta('description', webpage),
'series': series,
'episode': title,
})
for field in ('season', 'episode'):
field_name = field + 'Number'
info[field + '_number'] = int_or_none(find_field(
field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage))
return info