X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/f46044c66663049e286c20ee015db99d47d9dd8a..2b4515201a54c38e34434ea2817d606be134a7c9:/youtube_dl/extractor/laola1tv.py?ds=sidebyside diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py index b459559..3190b18 100644 --- a/youtube_dl/extractor/laola1tv.py +++ b/youtube_dl/extractor/laola1tv.py @@ -1,86 +1,176 @@ -# -*- coding: utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals -import random -import re - from .common import InfoExtractor from ..utils import ( ExtractorError, + unified_strdate, + urlencode_postdata, + xpath_element, xpath_text, + urljoin, + update_url_query, ) -class Laola1TvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P[a-z]+)-(?P[a-z]+)/.*?/(?P[0-9]+)\.html' +class Laola1TvEmbedIE(InfoExtractor): + IE_NAME = 'laola1tv:embed' + _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P\d+)' _TEST = { - 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html', + # flashvars.premium = "false"; + 'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024', 'info_dict': { - 'id': '227883', + 'id': '708065', 'ext': 'mp4', - 'title': 'Straubing Tigers - Kölner Haie', - 'categories': ['Eishockey'], - 'is_live': False, + 'title': 'MA Long CHN - FAN Zhendong CHN', + 'uploader': 'ITTF - International Table Tennis Federation', + 'upload_date': '20161211', }, - 'params': { - 'skip_download': True, - } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - lang = mobj.group('lang') - portal = mobj.group('portal') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - iframe_url = self._search_regex( - r']*?class="main_tv_player"[^>]*?src="([^"]+)"', - webpage, 'iframe URL') + flash_vars = self._search_regex( + r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars') - iframe = self._download_webpage( - iframe_url, video_id, note='Downloading iframe') - flashvars_m = re.findall( - r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe) - flashvars = dict((m[0], m[1]) for m in flashvars_m) + def get_flashvar(x, *args, **kwargs): + flash_var = self._search_regex( + r'%s\s*:\s*"([^"]+)"' % x, + flash_vars, x, default=None) + if not flash_var: + flash_var = self._search_regex([ + r'flashvars\.%s\s*=\s*"([^"]+)"' % x, + r'%s\s*=\s*"([^"]+)"' % x], + webpage, x, *args, **kwargs) + return flash_var - partner_id = self._search_regex( - r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner id') + hd_doc = self._download_xml( + 'http://www.laola1.tv/server/hd_video.php', video_id, query={ + 'play': get_flashvar('streamid'), + 'partner': get_flashvar('partnerid'), + 'portal': get_flashvar('portalid'), + 'lang': get_flashvar('sprache'), + 'v5ident': '', + }) - xml_url = ('http://www.laola1.tv/server/hd_video.php?' + - 'play=%s&partner=%s&portal=%s&v5ident=&lang=%s' % ( - video_id, partner_id, portal, lang)) - hd_doc = self._download_xml(xml_url, video_id) + _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k) + title = _v('title', fatal=True) - title = xpath_text(hd_doc, './/video/title', fatal=True) - flash_url = xpath_text(hd_doc, './/video/url', fatal=True) - uploader = xpath_text(hd_doc, './/video/meta_organistation') - is_live = xpath_text(hd_doc, './/video/islive') == 'true' + token_url = None + premium = get_flashvar('premium', default=None) + if premium: + token_url = update_url_query( + _v('url', fatal=True), { + 'timestamp': get_flashvar('timestamp'), + 'auth': get_flashvar('auth'), + }) + else: + data_abo = urlencode_postdata( + dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))) + token_url = self._download_json( + 'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', + video_id, query={ + 'videoId': _v('id'), + 'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'), + 'label': _v('label'), + 'area': _v('area'), + }, data=data_abo)['data']['stream-access'][0] - categories = xpath_text(hd_doc, './/video/meta_sports') - if categories: - categories = categories.split(',') + token_doc = self._download_xml( + token_url, video_id, 'Downloading token', + headers=self.geo_verification_headers()) - ident = random.randint(10000000, 99999999) - token_url = '%s&ident=%s&klub=0&unikey=0×tamp=%s&auth=%s' % ( - flash_url, ident, flashvars['timestamp'], flashvars['auth']) + token_attrib = xpath_element(token_doc, './/token').attrib - token_doc = self._download_xml( - token_url, video_id, note='Downloading token') - token_attrib = token_doc.find('.//token').attrib - if token_attrib.get('auth') in ('blocked', 'restricted'): + if token_attrib['status'] != '0': raise ExtractorError( - 'Token error: %s' % token_attrib.get('comment'), expected=True) + 'Token error: %s' % token_attrib['comment'], expected=True) - video_url = '%s?hdnea=%s&hdcore=3.2.0' % ( - token_attrib['url'], token_attrib['auth']) + 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 = categories_str.split(',') if categories_str else [] + is_live = _v('islive') == 'true' return { 'id': video_id, - 'is_live': is_live, - 'title': title, - 'url': video_url, - 'uploader': uploader, + 'title': self._live_title(title) if is_live else title, + 'upload_date': unified_strdate(_v('time_date')), + 'uploader': _v('meta_organisation'), 'categories': categories, - 'ext': 'mp4', + 'is_live': is_live, + 'formats': formats, + } + + +class Laola1TvIE(InfoExtractor): + IE_NAME = 'laola1tv' + _VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html', + 'info_dict': { + 'id': '227883', + 'display_id': 'straubing-tigers-koelner-haie', + 'ext': 'flv', + 'title': 'Straubing Tigers - Kölner Haie', + 'upload_date': '20140912', + 'is_live': False, + 'categories': ['Eishockey'], + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie', + 'info_dict': { + 'id': '464602', + 'display_id': 'straubing-tigers-koelner-haie', + 'ext': 'flv', + 'title': 'Straubing Tigers - Kölner Haie', + 'upload_date': '20160129', + 'is_live': False, + 'categories': ['Eishockey'], + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://www.laola1.tv/de-de/livestream/2016-03-22-belogorie-belgorod-trentino-diatec-lde', + 'info_dict': { + 'id': '487850', + 'display_id': '2016-03-22-belogorie-belgorod-trentino-diatec-lde', + 'ext': 'flv', + 'title': 'Belogorie BELGOROD - TRENTINO Diatec', + 'upload_date': '20160322', + 'uploader': 'CEV - Europäischer Volleyball Verband', + 'is_live': True, + 'categories': ['Volleyball'], + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'This live stream has already finished.', + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + if 'Dieser Livestream ist bereits beendet.' in webpage: + raise ExtractorError('This live stream has already finished.', expected=True) + + iframe_url = urljoin(url, self._search_regex( + r']*?id="videoplayer"[^>]*?src="([^"]+)"', + webpage, 'iframe url')) + + return { + '_type': 'url', + 'display_id': display_id, + 'url': iframe_url, + 'ie_key': 'Laola1TvEmbed', }