Merge tag 'upstream/2016.12.01'

[youtubedl] / youtube_dl / extractor / laola1tv.py

diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py
index b459559b0349bcae6c8d658c2fb120c2cb81d37e..2fab38079aac0c5f20a1772d52fa52642cb520bf 100644 (file)
--- a/youtube_dl/extractor/laola1tv.py
+++ b/youtube_dl/extractor/laola1tv.py
@@ -1,86 +1,151 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import random

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import (
+    compat_urllib_parse_urlencode,
+    compat_urlparse,
+)

 from ..utils import (
     ExtractorError,
 from ..utils import (
     ExtractorError,

+    sanitized_Request,
+    unified_strdate,
+    urlencode_postdata,
+    xpath_element,

     xpath_text,
 )
 
 
 class Laola1TvIE(InfoExtractor):
     xpath_text,
 )
 
 
 class Laola1TvIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/(?P<kind>[^/]+)/(?P<slug>[^/?#&]+)'
+    _TESTS = [{

         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
             'id': '227883',
         'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
         'info_dict': {
             'id': '227883',

-            'ext': 'mp4',
+            'display_id': 'straubing-tigers-koelner-haie',
+            'ext': 'flv',

             'title': 'Straubing Tigers - Kölner Haie',
             'title': 'Straubing Tigers - Kölner Haie',

+            'upload_date': '20140912',
+            'is_live': False,

             'categories': ['Eishockey'],
             '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,
             'is_live': False,

+            'categories': ['Eishockey'],

         },
         'params': {
             'skip_download': True,
         },
         '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):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('id')
+        display_id = mobj.group('slug')
+        kind = mobj.group('kind')

         lang = mobj.group('lang')
         portal = mobj.group('portal')
 
         lang = mobj.group('lang')
         portal = mobj.group('portal')
 

-        webpage = self._download_webpage(url, video_id)
+        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 = self._search_regex(
         iframe_url = self._search_regex(

-            r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
-            webpage, 'iframe URL')
+            r'<iframe[^>]*?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), display_id, 'Downloading iframe')

 
         partner_id = self._search_regex(
 
         partner_id = self._search_regex(

-            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'
-
-        categories = xpath_text(hd_doc, './/video/meta_sports')
-        if categories:
-            categories = categories.split(',')
-
-        ident = random.randint(10000000, 99999999)
-        token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
-            flash_url, ident, flashvars['timestamp'], flashvars['auth'])
-
-        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'):
+            r'partnerid\s*:\s*(["\'])(?P<partner_id>.+?)\1',
+            iframe, 'partner id', group='partner_id')
+
+        hd_doc = self._download_xml(
+            'http://www.laola1.tv/server/hd_video.php?%s'
+            % compat_urllib_parse_urlencode({
+                'play': video_id,
+                'partner': partner_id,
+                'portal': portal,
+                'lang': lang,
+                'v5ident': '',
+            }), display_id)
+
+        _v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
+        title = _v('title', fatal=True)
+
+        VS_TARGETS = {
+            'video': '2',
+            'livestream': '17',
+        }
+
+        req = sanitized_Request(
+            'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
+            compat_urllib_parse_urlencode({
+                'videoId': video_id,
+                'target': VS_TARGETS.get(kind, '2'),
+                'label': _v('label'),
+                'area': _v('area'),
+            }),
+            urlencode_postdata(
+                dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(',')))))
+
+        token_url = self._download_json(req, display_id)['data']['stream-access'][0]
+        token_doc = self._download_xml(token_url, display_id, 'Downloading token')
+
+        token_attrib = xpath_element(token_doc, './/token').attrib
+        token_auth = token_attrib['auth']
+
+        if token_auth in ('blocked', 'restricted', 'error'):

             raise ExtractorError(
             raise ExtractorError(

-                'Token error: %s' % token_attrib.get('comment'), expected=True)
+                'Token error: %s' % token_attrib['comment'], expected=True)
+
+        formats = self._extract_f4m_formats(
+            '%s?hdnea=%s&hdcore=3.2.0' % (token_attrib['url'], token_auth),
+            video_id, f4m_id='hds')
+        self._sort_formats(formats)

 
 

-        video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
-            token_attrib['url'], token_attrib['auth'])
+        categories_str = _v('meta_sports')
+        categories = categories_str.split(',') if categories_str else []

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'is_live': is_live,
+            'display_id': display_id,

             'title': title,
             'title': title,

-            'url': video_url,
-            'uploader': uploader,
+            'upload_date': unified_strdate(_v('time_date')),
+            'uploader': _v('meta_organisation'),

             'categories': categories,
             'categories': categories,

-            'ext': 'mp4',
+            'is_live': _v('islive') == 'true',
+            'formats': formats,

         }
         }