[laola1tv] fix extraction(closes #12880)

This commit is contained in:
Remita Amine 2017-05-04 16:06:21 +01:00
parent ff6f9a6704
commit 4fe14732a2

View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
@ -10,6 +12,7 @@ from ..utils import (
xpath_text, xpath_text,
urljoin, urljoin,
update_url_query, update_url_query,
js_to_json,
) )
@ -28,6 +31,29 @@ class Laola1TvEmbedIE(InfoExtractor):
}, },
} }
def _extract_token_url(self, stream_access_url, video_id, data):
return self._download_json(
stream_access_url, video_id, headers={
'Content-Type': 'application/json',
}, data=json.dumps(data).encode())['data']['stream-access'][0]
def _extract_formats(self, token_url, video_id):
token_doc = self._download_xml(
token_url, video_id, 'Downloading token',
headers=self.geo_verification_headers())
token_attrib = xpath_element(token_doc, './/token').attrib
if token_attrib['status'] != '0':
raise ExtractorError(
'Token error: %s' % token_attrib['comment'], expected=True)
formats = self._extract_akamai_formats(
'%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
video_id)
self._sort_formats(formats)
return formats
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
@ -68,29 +94,16 @@ class Laola1TvEmbedIE(InfoExtractor):
else: else:
data_abo = urlencode_postdata( data_abo = urlencode_postdata(
dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))) dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
token_url = self._download_json( stream_access_url = update_url_query(
'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', 'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', {
video_id, query={
'videoId': _v('id'), 'videoId': _v('id'),
'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'), 'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
'label': _v('label'), 'label': _v('label'),
'area': _v('area'), 'area': _v('area'),
}, data=data_abo)['data']['stream-access'][0] })
token_url = self._extract_token_url(stream_access_url, video_id, data_abo)
token_doc = self._download_xml( formats = self._extract_formats(token_url, video_id)
token_url, video_id, 'Downloading token',
headers=self.geo_verification_headers())
token_attrib = xpath_element(token_doc, './/token').attrib
if token_attrib['status'] != '0':
raise ExtractorError(
'Token error: %s' % token_attrib['comment'], expected=True)
formats = self._extract_akamai_formats(
'%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
video_id)
self._sort_formats(formats)
categories_str = _v('meta_sports') categories_str = _v('meta_sports')
categories = categories_str.split(',') if categories_str else [] categories = categories_str.split(',') if categories_str else []
@ -107,7 +120,7 @@ class Laola1TvEmbedIE(InfoExtractor):
} }
class Laola1TvIE(InfoExtractor): class Laola1TvIE(Laola1TvEmbedIE):
IE_NAME = 'laola1tv' IE_NAME = 'laola1tv'
_VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
_TESTS = [{ _TESTS = [{
@ -164,13 +177,42 @@ class Laola1TvIE(InfoExtractor):
if 'Dieser Livestream ist bereits beendet.' in webpage: if 'Dieser Livestream ist bereits beendet.' in webpage:
raise ExtractorError('This live stream has already finished.', expected=True) raise ExtractorError('This live stream has already finished.', expected=True)
iframe_url = urljoin(url, self._search_regex( conf = self._parse_json(self._search_regex(
r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"', r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
webpage, 'iframe url')) display_id, js_to_json)
video_id = conf['videoid']
config = self._download_json(conf['configUrl'], video_id, query={
'videoid': video_id,
'partnerid': conf['partnerid'],
'language': conf.get('language', ''),
'portal': conf.get('portalid', ''),
})
error = config.get('error')
if error:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
video_data = config['video']
title = video_data['title']
is_live = video_data.get('isLivestream') and video_data.get('isLive')
meta = video_data.get('metaInformation')
sports = meta.get('sports')
categories = sports.split(',') if sports else []
token_url = self._extract_token_url(
video_data['streamAccess'], video_id,
video_data['abo']['required'])
formats = self._extract_formats(token_url, video_id)
return { return {
'_type': 'url', 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'url': iframe_url, 'title': self._live_title(title) if is_live else title,
'ie_key': 'Laola1TvEmbed', 'description': video_data.get('description'),
'thumbnail': video_data.get('image'),
'categories': categories,
'formats': formats,
'is_live': is_live,
} }