[extractor/globo:article] Remove false positives (#4396)

Authored by: Bricio
This commit is contained in:
Bricio 2022-07-20 01:37:13 -03:00 committed by GitHub
parent 81bf0943ea
commit c40f327a16
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 6 deletions

View File

@ -178,12 +178,12 @@ class GloboArticleIE(InfoExtractor):
_VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/.]+)(?:\.html)?' _VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/.]+)(?:\.html)?'
_VIDEOID_REGEXES = [ _VIDEOID_REGEXES = [
r'\bdata-video-id=["\'](\d{7,})', r'\bdata-video-id=["\'](\d{7,})["\']',
r'\bdata-player-videosids=["\'](\d{7,})', r'\bdata-player-videosids=["\'](\d{7,})["\']',
r'\bvideosIDs\s*:\s*["\']?(\d{7,})', r'\bvideosIDs\s*:\s*["\']?(\d{7,})',
r'\bdata-id=["\'](\d{7,})', r'\bdata-id=["\'](\d{7,})["\']',
r'<div[^>]+\bid=["\'](\d{7,})', r'<div[^>]+\bid=["\'](\d{7,})["\']',
r'<bs-player[^>]+\bvideoid=["\'](\d{8,})', r'<bs-player[^>]+\bvideoid=["\'](\d{8,})["\']',
] ]
_TESTS = [{ _TESTS = [{
@ -219,6 +219,14 @@ class GloboArticleIE(InfoExtractor):
'description': 'md5:2d089d036c4c9675117d3a56f8c61739', 'description': 'md5:2d089d036c4c9675117d3a56f8c61739',
}, },
'playlist_count': 1, 'playlist_count': 1,
}, {
'url': 'https://redeglobo.globo.com/rpc/meuparana/noticia/a-producao-de-chocolates-no-parana.ghtml',
'info_dict': {
'id': 'a-producao-de-chocolates-no-parana',
'title': 'A produção de chocolates no Paraná',
'description': 'md5:f2e3daf00ffd1dc0e9a8a6c7cfb0a89e',
},
'playlist_count': 2,
}] }]
@classmethod @classmethod
@ -234,6 +242,6 @@ class GloboArticleIE(InfoExtractor):
entries = [ entries = [
self.url_result('globo:%s' % video_id, GloboIE.ie_key()) self.url_result('globo:%s' % video_id, GloboIE.ie_key())
for video_id in orderedSet(video_ids)] for video_id in orderedSet(video_ids)]
title = self._og_search_title(webpage) title = self._og_search_title(webpage).strip()
description = self._html_search_meta('description', webpage) description = self._html_search_meta('description', webpage)
return self.playlist_result(entries, display_id, title, description) return self.playlist_result(entries, display_id, title, description)