[globo:article] Add support for multiple videos (Closes #10653)

This commit is contained in:
Sergey M․ 2016-09-17 23:34:10 +07:00
parent 30d0b549be
commit 26394d021d
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import random import random
import re
import math import math
from .common import InfoExtractor from .common import InfoExtractor
@ -14,6 +15,7 @@
ExtractorError, ExtractorError,
float_or_none, float_or_none,
int_or_none, int_or_none,
orderedSet,
str_or_none, str_or_none,
) )
@ -63,6 +65,9 @@ class GloboIE(InfoExtractor):
}, { }, {
'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html', 'url': 'http://canaloff.globo.com/programas/desejar-profundo/videos/4518560.html',
'only_matching': True, 'only_matching': True,
}, {
'url': 'globo:3607726',
'only_matching': True,
}] }]
class MD5(object): class MD5(object):
@ -396,7 +401,7 @@ def _real_extract(self, url):
class GloboArticleIE(InfoExtractor): 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,})',
@ -408,15 +413,20 @@ class GloboArticleIE(InfoExtractor):
_TESTS = [{ _TESTS = [{
'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html', 'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html',
'md5': '307fdeae4390ccfe6ba1aa198cf6e72b',
'info_dict': { 'info_dict': {
'id': '3652183', 'id': 'novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes',
'ext': 'mp4', 'title': 'Novidade na fiscalização de bagagem pela Receita provoca discussões',
'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião', 'description': 'md5:c3c4b4d4c30c32fce460040b1ac46b12',
'duration': 110.711, },
'uploader': 'Rede Globo', 'playlist_count': 1,
'uploader_id': '196', }, {
} 'url': 'http://g1.globo.com/pr/parana/noticia/2016/09/mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato.html',
'info_dict': {
'id': 'mpf-denuncia-lula-marisa-e-mais-seis-na-operacao-lava-jato',
'title': "Lula era o 'comandante máximo' do esquema da Lava Jato, diz MPF",
'description': 'md5:8aa7cc8beda4dc71cc8553e00b77c54c',
},
'playlist_count': 6,
}, { }, {
'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html', 'url': 'http://gq.globo.com/Prazeres/Poder/noticia/2015/10/all-o-desafio-assista-ao-segundo-capitulo-da-serie.html',
'only_matching': True, 'only_matching': True,
@ -435,5 +445,12 @@ def suitable(cls, url):
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)
video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id') video_ids = []
return self.url_result('globo:%s' % video_id, 'Globo') for video_regex in self._VIDEOID_REGEXES:
video_ids.extend(re.findall(video_regex, webpage))
entries = [
self.url_result('globo:%s' % video_id, GloboIE.ie_key())
for video_id in orderedSet(video_ids)]
title = self._og_search_title(webpage, fatal=False)
description = self._html_search_meta('description', webpage)
return self.playlist_result(entries, display_id, title, description)