From e029c43bd43ddde448b150b1e0f226e4dd8c9b90 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 20 Dec 2016 18:22:57 +0100 Subject: [PATCH] [laola1] add support for another extraction scenario(closes #11460) --- youtube_dl/extractor/laola1tv.py | 56 +++++++++++++++++++++++++------- 1 file changed, 45 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py index 37e38dba0e..3190b187c9 100644 --- a/youtube_dl/extractor/laola1tv.py +++ b/youtube_dl/extractor/laola1tv.py @@ -9,18 +9,41 @@ xpath_element, xpath_text, urljoin, + update_url_query, ) class Laola1TvEmbedIE(InfoExtractor): + IE_NAME = 'laola1tv:embed' _VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P\d+)' + _TEST = { + # flashvars.premium = "false"; + 'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024', + 'info_dict': { + 'id': '708065', + 'ext': 'mp4', + 'title': 'MA Long CHN - FAN Zhendong CHN', + 'uploader': 'ITTF - International Table Tennis Federation', + 'upload_date': '20161211', + }, + } def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) flash_vars = self._search_regex( r'(?s)flashvars\s*=\s*({.+?});', webpage, 'flash vars') - get_flashvar = lambda x: self._search_regex(r'%s\s*:\s*"([^"]+)"' % x, flash_vars, x) + + 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 hd_doc = self._download_xml( 'http://www.laola1.tv/server/hd_video.php', video_id, query={ @@ -34,16 +57,26 @@ def _real_extract(self, url): _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k) title = _v('title', fatal=True) - 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] + 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] + token_doc = self._download_xml( token_url, video_id, 'Downloading token', headers=self.geo_verification_headers()) @@ -75,6 +108,7 @@ def _real_extract(self, url): 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',