From 5e19323ed91a2ac3014c8f803fa65d2774a6a4f4 Mon Sep 17 00:00:00 2001 From: Jens Wille Date: Tue, 9 Feb 2016 16:25:30 +0100 Subject: [PATCH] [laola1tv] Fixes for changed site layout. * Fixed valid URLs (w/ tests). * Fixed iframe URL extraction. * Fixed token URL extraction. * Fixed variable extraction. * Fixed uploader spelling. * Added upload_date to result dictionary. --- youtube_dl/extractor/laola1tv.py | 91 +++++++++++++++++++++----------- 1 file changed, 59 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py index b459559b0..c1f248b6b 100644 --- a/youtube_dl/extractor/laola1tv.py +++ b/youtube_dl/extractor/laola1tv.py @@ -1,86 +1,113 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import random import re from .common import InfoExtractor from ..utils import ( + compat_urlparse, ExtractorError, + sanitized_Request, + xpath_element, xpath_text, + unified_strdate, + urlencode_postdata, ) class Laola1TvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P[a-z]+)-(?P[a-z]+)/.*?/(?P[0-9]+)\.html' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P[a-z]+)-(?P[a-z]+)/.*?/(?P[\w-]+)' + _TESTS = [{ 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html', 'info_dict': { + 'categories': ['Eishockey'], + 'ext': 'flv', 'id': '227883', - 'ext': 'mp4', + 'is_live': False, 'title': 'Straubing Tigers - Kölner Haie', + 'upload_date': '20140912', + }, + 'params': { + 'skip_download': True, + } + }, { + 'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie', + 'info_dict': { 'categories': ['Eishockey'], + 'ext': 'flv', + 'id': '464602', 'is_live': False, + 'title': 'Straubing Tigers - Kölner Haie', + 'upload_date': '20160129', }, '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') - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, mobj.group('slug')) iframe_url = self._search_regex( - r']*?class="main_tv_player"[^>]*?src="([^"]+)"', + r']*?id="videoplayer"[^>]*?src="([^"]+)"', webpage, 'iframe URL') - 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) + video_id = self._search_regex( + r'videoid=(\d+)', iframe_url, 'video ID') + + iframe = self._download_webpage(compat_urlparse.urljoin( + url, iframe_url), video_id, note='Downloading iframe') partner_id = self._search_regex( - r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner id') + r'partnerid\s*:\s*"([^"]+)"', iframe, 'partner ID') 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) - 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' + _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k) + title = _v('title', fatal=True) - categories = xpath_text(hd_doc, './/video/meta_sports') + categories = _v('meta_sports') if categories: categories = categories.split(',') - 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']) + time_date = _v('time_date') + time_start = _v('time_start') + upload_date = None + if time_date and time_start: + upload_date = unified_strdate(time_date + ' ' + time_start) + json_url = ('https://club.laola1.tv/sp/laola1/api/v3/user/session' + + '/premium/player/stream-access?videoId=%s&target=2' + + '&label=laola1tv&area=%s') % (video_id, _v('area')) + req = sanitized_Request(json_url, urlencode_postdata( + dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))) + + token_url = self._download_json(req, video_id)['data']['stream-access'][0] 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'): + + token_attrib = xpath_element(token_doc, './/token').attrib + token_auth = token_attrib['auth'] + + if token_auth in ('blocked', 'restricted'): 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']) + video_url = '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth) return { + 'categories': categories, + 'formats': self._extract_f4m_formats( + video_url, video_id, f4m_id='hds'), 'id': video_id, - 'is_live': is_live, + 'is_live': _v('islive') == 'true', 'title': title, - 'url': video_url, - 'uploader': uploader, - 'categories': categories, - 'ext': 'mp4', + 'upload_date': upload_date, + 'uploader': _v('meta_organisation'), }