debian/README.source: Update with instructions relative to GitHub.

[youtubedl] / youtube_dl / extractor / tvp.py

diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py
index 2abfb78307186a2007e7f375bccb7a26ff0713ca..3954f0b93812e5bd58d950e8401c954d0ea0a7c6 100644 (file)
--- a/youtube_dl/extractor/tvp.py
+++ b/youtube_dl/extractor/tvp.py
@@ -15,16 +15,16 @@ from ..utils import (
 class TVPIE(InfoExtractor):
     IE_NAME = 'tvp'
     IE_DESC = 'Telewizja Polska'
 class TVPIE(InfoExtractor):
     IE_NAME = 'tvp'
     IE_DESC = 'Telewizja Polska'

-    _VALID_URL = r'https?://[^/]+\.tvp\.(?:pl|info)/(?:(?!\d+/)[^/]+/)*(?P<id>\d+)'
+    _VALID_URL = r'https?://[^/]+\.tvp\.(?:pl|info)/(?:video/(?:[^,\s]*,)*|(?:(?!\d+/)[^/]+/)*)(?P<id>\d+)'

 
     _TESTS = [{
 
     _TESTS = [{

-        'url': 'http://vod.tvp.pl/194536/i-seria-odc-13',
+        'url': 'https://vod.tvp.pl/video/czas-honoru,i-seria-odc-13,194536',

         'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
         'info_dict': {
             'id': '194536',
             'ext': 'mp4',
             'title': 'Czas honoru, I seria – odc. 13',
         'md5': '8aa518c15e5cc32dfe8db400dc921fbb',
         'info_dict': {
             'id': '194536',
             'ext': 'mp4',
             'title': 'Czas honoru, I seria – odc. 13',

-            'description': 'md5:76649d2014f65c99477be17f23a4dead',
+            'description': 'md5:381afa5bca72655fe94b05cfe82bf53d',

         },
     }, {
         'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
         },
     }, {
         'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',


@@ -37,12 +37,13 @@ class TVPIE(InfoExtractor):
         },
     }, {
         # page id is not the same as video id(#7799)
         },
     }, {
         # page id is not the same as video id(#7799)

-        'url': 'http://vod.tvp.pl/22704887/08122015-1500',
-        'md5': 'cf6a4705dfd1489aef8deb168d6ba742',
+        'url': 'https://wiadomosci.tvp.pl/33908820/28092017-1930',
+        'md5': '84cd3c8aec4840046e5ab712416b73d0',

         'info_dict': {
         'info_dict': {

-            'id': '22680786',
+            'id': '33908820',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Wiadomości, 08.12.2015, 15:00',
+            'title': 'Wiadomości, 28.09.2017, 19:30',
+            'description': 'Wydanie główne codziennego serwisu informacyjnego.'

         },
     }, {
         'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
         },
     }, {
         'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',


@@ -69,7 +70,8 @@ class TVPIE(InfoExtractor):
         webpage = self._download_webpage(url, page_id)
         video_id = self._search_regex([
             r'<iframe[^>]+src="[^"]*?object_id=(\d+)',
         webpage = self._download_webpage(url, page_id)
         video_id = self._search_regex([
             r'<iframe[^>]+src="[^"]*?object_id=(\d+)',

-            "object_id\s*:\s*'(\d+)'"], webpage, 'video id')
+            r"object_id\s*:\s*'(\d+)'",
+            r'data-video-id="(\d+)"'], webpage, 'video id', default=page_id)

         return {
             '_type': 'url_transparent',
             'url': 'tvp:' + video_id,
         return {
             '_type': 'url_transparent',
             'url': 'tvp:' + video_id,


@@ -138,6 +140,9 @@ class TVPEmbedIE(InfoExtractor):
             # formats.extend(self._extract_mpd_formats(
             #     video_url_base + '.ism/video.mpd',
             #     video_id, mpd_id='dash', fatal=False))
             # formats.extend(self._extract_mpd_formats(
             #     video_url_base + '.ism/video.mpd',
             #     video_id, mpd_id='dash', fatal=False))

+            formats.extend(self._extract_ism_formats(
+                video_url_base + '.ism/Manifest',
+                video_id, 'mss', fatal=False))

             formats.extend(self._extract_f4m_formats(
                 video_url_base + '.ism/video.f4m',
                 video_id, f4m_id='hds', fatal=False))
             formats.extend(self._extract_f4m_formats(
                 video_url_base + '.ism/video.f4m',
                 video_id, f4m_id='hds', fatal=False))


@@ -146,8 +151,7 @@ class TVPEmbedIE(InfoExtractor):
                 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
             self._sort_formats(m3u8_formats)
             m3u8_formats = list(filter(
                 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
             self._sort_formats(m3u8_formats)
             m3u8_formats = list(filter(

-                lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
-                m3u8_formats))
+                lambda f: f.get('vcodec') != 'none', m3u8_formats))

             formats.extend(m3u8_formats)
             for i, m3u8_format in enumerate(m3u8_formats, 2):
                 http_url = '%s-%d.mp4' % (video_url_base, i)
             formats.extend(m3u8_formats)
             for i, m3u8_format in enumerate(m3u8_formats, 2):
                 http_url = '%s-%d.mp4' % (video_url_base, i)