[yahoo] fix GYAO Player extraction and relax title URL regex(closes #24178)(closes #24778)

This commit is contained in:
Remita Amine 2020-04-29 14:56:32 +01:00
parent 700265bfcf
commit 2468a6fa64

View File

@ -12,6 +12,7 @@
) )
from ..utils import ( from ..utils import (
clean_html, clean_html,
ExtractorError,
int_or_none, int_or_none,
mimetype2ext, mimetype2ext,
parse_iso8601, parse_iso8601,
@ -368,31 +369,47 @@ class YahooGyaOPlayerIE(InfoExtractor):
'url': 'https://gyao.yahoo.co.jp/episode/%E3%81%8D%E3%81%AE%E3%81%86%E4%BD%95%E9%A3%9F%E3%81%B9%E3%81%9F%EF%BC%9F%20%E7%AC%AC2%E8%A9%B1%202019%2F4%2F12%E6%94%BE%E9%80%81%E5%88%86/5cb02352-b725-409e-9f8d-88f947a9f682', 'url': 'https://gyao.yahoo.co.jp/episode/%E3%81%8D%E3%81%AE%E3%81%86%E4%BD%95%E9%A3%9F%E3%81%B9%E3%81%9F%EF%BC%9F%20%E7%AC%AC2%E8%A9%B1%202019%2F4%2F12%E6%94%BE%E9%80%81%E5%88%86/5cb02352-b725-409e-9f8d-88f947a9f682',
'only_matching': True, 'only_matching': True,
}] }]
_GEO_BYPASS = False
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url).replace('/', ':') video_id = self._match_id(url).replace('/', ':')
video = self._download_json( headers = self.geo_verification_headers()
'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id, headers['Accept'] = 'application/json'
video_id, query={ resp = self._download_json(
'fields': 'longDescription,title,videoId', 'https://gyao.yahoo.co.jp/apis/playback/graphql', video_id, query={
}, headers={ 'appId': 'dj00aiZpPUNJeDh2cU1RazU3UCZzPWNvbnN1bWVyc2VjcmV0Jng9NTk-',
'X-User-Agent': 'Unknown Pc GYAO!/2.0.0 Web', 'query': '''{
}) content(parameter: {contentId: "%s", logicaAgent: PC_WEB}) {
video {
delivery {
id
}
title
}
}
}''' % video_id,
}, headers=headers)
content = resp['data']['content']
if not content:
msg = resp['errors'][0]['message']
if msg == 'not in japan':
self.raise_geo_restricted(countries=['JP'])
raise ExtractorError(msg)
video = content['video']
return { return {
'_type': 'url_transparent', '_type': 'url_transparent',
'id': video_id, 'id': video_id,
'title': video['title'], 'title': video['title'],
'url': smuggle_url( 'url': smuggle_url(
'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video['videoId'], 'http://players.brightcove.net/4235717419001/SyG5P0gjb_default/index.html?videoId=' + video['delivery']['id'],
{'geo_countries': ['JP']}), {'geo_countries': ['JP']}),
'description': video.get('longDescription'),
'ie_key': BrightcoveNewIE.ie_key(), 'ie_key': BrightcoveNewIE.ie_key(),
} }
class YahooGyaOIE(InfoExtractor): class YahooGyaOIE(InfoExtractor):
IE_NAME = 'yahoo:gyao' IE_NAME = 'yahoo:gyao'
_VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:p|title/[^/]+)|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' _VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:p|title(?:/[^/]+)?)|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TESTS = [{ _TESTS = [{
'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/', 'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
'info_dict': { 'info_dict': {
@ -405,6 +422,9 @@ class YahooGyaOIE(InfoExtractor):
}, { }, {
'url': 'https://gyao.yahoo.co.jp/title/%E3%81%97%E3%82%83%E3%81%B9%E3%81%8F%E3%82%8A007/5b025a49-b2e5-4dc7-945c-09c6634afacf', 'url': 'https://gyao.yahoo.co.jp/title/%E3%81%97%E3%82%83%E3%81%B9%E3%81%8F%E3%82%8A007/5b025a49-b2e5-4dc7-945c-09c6634afacf',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://gyao.yahoo.co.jp/title/5b025a49-b2e5-4dc7-945c-09c6634afacf',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):