[rudo] remove extractor(closes #18430)(closes #18474)

Covered by generic extractor
This commit is contained in:
Remita Amine 2019-07-12 22:31:11 +01:00
parent 82f68e4a01
commit 0441d6266c
3 changed files with 12 additions and 61 deletions

View File

@ -6,7 +6,6 @@
ExtractorError, ExtractorError,
remove_end, remove_end,
) )
from .rudo import RudoIE
class BioBioChileTVIE(InfoExtractor): class BioBioChileTVIE(InfoExtractor):
@ -41,11 +40,15 @@ class BioBioChileTVIE(InfoExtractor):
}, { }, {
'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml', 'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
'info_dict': { 'info_dict': {
'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos', 'id': 'b4xd0LK3SK',
'ext': 'mp4', 'ext': 'mp4',
'uploader': '(none)', # TODO: fix url_transparent information overriding
'upload_date': '20160708', # 'uploader': 'Juan Pablo Echenique',
'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos', 'title': 'Comentario Oscar Cáceres',
},
'params': {
# empty m3u8 manifest
'skip_download': True,
}, },
}, { }, {
'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml', 'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
@ -60,7 +63,9 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
rudo_url = RudoIE._extract_url(webpage) rudo_url = self._search_regex(
r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
webpage, 'embed URL', None, group='url')
if not rudo_url: if not rudo_url:
raise ExtractorError('No videos found') raise ExtractorError('No videos found')
@ -68,7 +73,7 @@ def _real_extract(self, url):
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>', r'<a[^>]+href=["\'](?:https?://(?:busca|www)\.biobiochile\.cl)?/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
return { return {

View File

@ -967,7 +967,6 @@
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
from .rtvnh import RTVNHIE from .rtvnh import RTVNHIE
from .rtvs import RTVSIE from .rtvs import RTVSIE
from .rudo import RudoIE
from .ruhd import RUHDIE from .ruhd import RUHDIE
from .rutube import ( from .rutube import (
RutubeIE, RutubeIE,

View File

@ -1,53 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
get_element_by_class,
unified_strdate,
)
class RudoIE(InfoExtractor):
_VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)'
_TEST = {
'url': 'http://rudo.video/vod/oTzw0MGnyG',
'md5': '2a03a5b32dd90a04c83b6d391cf7b415',
'info_dict': {
'id': 'oTzw0MGnyG',
'ext': 'mp4',
'title': 'Comentario Tomás Mosciatti',
'upload_date': '20160617',
},
}
@classmethod
def _extract_url(cls, webpage):
mobj = re.search(
r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, encoding='iso-8859-1')
jwplayer_data = self._parse_json(self._search_regex(
r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id,
transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s)))
info_dict = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False, m3u8_id='hls', mpd_id='dash')
info_dict.update({
'title': self._og_search_title(webpage),
'upload_date': unified_strdate(get_element_by_class('date', webpage)),
})
return info_dict