debian/watch: Skip pgpsigurlmangle for the moment.

[youtubedl] / youtube_dl / extractor / laola1tv.py

diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py
index 263f687736c3f7fe3e980d79a10971a6dc4df5b2..5d8ebbeb3d6c01fc5493751b7a89623877bba7c3 100644 (file)
--- a/youtube_dl/extractor/laola1tv.py
+++ b/youtube_dl/extractor/laola1tv.py
@@ -1,77 +1,125 @@
+# 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,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    sanitized_Request,
+    unified_strdate,
+    urlencode_postdata,
+    xpath_element,
+    xpath_text,
+)

 
 
 class Laola1TvIE(InfoExtractor):
 
 
 class Laola1TvIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
-    _TEST = {
-        'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html',
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/[^/]+/(?P<slug>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',

         'info_dict': {
         'info_dict': {

-            'id': '250019',
-            'ext': 'mp4',
-            'title': 'Bitburger Open Grand Prix Gold - Court 1',
-            'categories': ['Badminton'],
-            'uploader': 'BWF - Badminton World Federation',
-            'is_live': True,
+            '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,
         }
         },
         'params': {
             'skip_download': True,
         }

-    }
-
-    _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
+    }, {
+        '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,
+        }
+    }]

 
     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')

         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)
+

         iframe_url = self._search_regex(
         iframe_url = self._search_regex(

-            r'<iframe[^>]*?class="main_tv_player"[^>]*?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)
-
-        xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
-                   'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
-                       video_id, portal, lang))
-        hd_doc = self._download_xml(xml_url, video_id)
-
-        title = hd_doc.find('.//video/title').text
-        flash_url = hd_doc.find('.//video/url').text
-        categories = hd_doc.find('.//video/meta_sports').text.split(',')
-        uploader = hd_doc.find('.//video/meta_organistation').text
-
-        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') == 'blocked':
-            raise ExtractorError('Token error: ' % token_attrib.get('comment'))
-
-        video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
-            token_attrib['url'], token_attrib['auth'])
+            r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
+            webpage, 'iframe url')
+
+        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(
+            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)
+
+        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': '2',
+                'label': 'laola1tv',
+                '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(
+                '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')
+
+        categories_str = _v('meta_sports')
+        categories = categories_str.split(',') if categories_str else []

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

-            'is_live': True,
+            '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,

         }
         }

-