Prepare upload.

[youtubedl] / youtube_dl / extractor / onet.py

diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py
index fc22ad5eb61b616afa4aaf6895302118fa4f2a50..58da1bc27b120e6636e61237dc1b0b61972bf96e 100644 (file)
--- a/youtube_dl/extractor/onet.py
+++ b/youtube_dl/extractor/onet.py
@@ -11,6 +11,7 @@ from ..utils import (
     get_element_by_class,
     int_or_none,
     js_to_json,
     get_element_by_class,
     int_or_none,
     js_to_json,

+    NO_DEFAULT,

     parse_iso8601,
     remove_start,
     strip_or_none,
     parse_iso8601,
     remove_start,
     strip_or_none,


@@ -23,7 +24,7 @@ class OnetBaseIE(InfoExtractor):
         return self._search_regex(
             r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
 
         return self._search_regex(
             r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
 

-    def _extract_from_id(self, video_id, webpage):
+    def _extract_from_id(self, video_id, webpage=None):

         response = self._download_json(
             'http://qi.ckm.onetapi.pl/', video_id,
             query={
         response = self._download_json(
             'http://qi.ckm.onetapi.pl/', video_id,
             query={


@@ -56,8 +57,8 @@ class OnetBaseIE(InfoExtractor):
                         continue
                     ext = determine_ext(video_url)
                     if format_id == 'ism':
                         continue
                     ext = determine_ext(video_url)
                     if format_id == 'ism':

-                        # TODO: Support Microsoft Smooth Streaming
-                        continue
+                        formats.extend(self._extract_ism_formats(
+                            video_url, video_id, 'mss', fatal=False))

                     elif ext == 'mpd':
                         formats.extend(self._extract_mpd_formats(
                             video_url, video_id, mpd_id='dash', fatal=False))
                     elif ext == 'mpd':
                         formats.extend(self._extract_mpd_formats(
                             video_url, video_id, mpd_id='dash', fatal=False))


@@ -74,8 +75,10 @@ class OnetBaseIE(InfoExtractor):
 
         meta = video.get('meta', {})
 
 
         meta = video.get('meta', {})
 

-        title = self._og_search_title(webpage, default=None) or meta['title']
-        description = self._og_search_description(webpage, default=None) or meta.get('description')
+        title = (self._og_search_title(
+            webpage, default=None) if webpage else None) or meta['title']
+        description = (self._og_search_description(
+            webpage, default=None) if webpage else None) or meta.get('description')

         duration = meta.get('length') or meta.get('lenght')
         timestamp = parse_iso8601(meta.get('addDate'), ' ')
 
         duration = meta.get('length') or meta.get('lenght')
         timestamp = parse_iso8601(meta.get('addDate'), ' ')
 


@@ -89,8 +92,20 @@ class OnetBaseIE(InfoExtractor):
         }
 
 
         }
 
 

+class OnetMVPIE(OnetBaseIE):
+    _VALID_URL = r'onetmvp:(?P<id>\d+\.\d+)'
+
+    _TEST = {
+        'url': 'onetmvp:381027.1509591944',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        return self._extract_from_id(self._match_id(url))
+
+

 class OnetIE(OnetBaseIE):
 class OnetIE(OnetBaseIE):

-    _VALID_URL = 'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
+    _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'

     IE_NAME = 'onet.tv'
 
     _TEST = {
     IE_NAME = 'onet.tv'
 
     _TEST = {


@@ -167,3 +182,69 @@ class OnetChannelIE(OnetBaseIE):
         channel_title = strip_or_none(get_element_by_class('o_channelName', webpage))
         channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage))
         return self.playlist_result(entries, channel_id, channel_title, channel_description)
         channel_title = strip_or_none(get_element_by_class('o_channelName', webpage))
         channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage))
         return self.playlist_result(entries, channel_id, channel_title, channel_description)

+
+
+class OnetPlIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?:onet|businessinsider\.com|plejada)\.pl/(?:[^/]+/)+(?P<id>[0-9a-z]+)'
+    IE_NAME = 'onet.pl'
+
+    _TESTS = [{
+        'url': 'http://eurosport.onet.pl/zimowe/skoki-narciarskie/ziobro-wygral-kwalifikacje-w-pjongczangu/9ckrly',
+        'md5': 'b94021eb56214c3969380388b6e73cb0',
+        'info_dict': {
+            'id': '1561707.1685479',
+            'ext': 'mp4',
+            'title': 'Ziobro wygrał kwalifikacje w Pjongczangu',
+            'description': 'md5:61fb0740084d2d702ea96512a03585b4',
+            'upload_date': '20170214',
+            'timestamp': 1487078046,
+        },
+    }, {
+        # embedded via pulsembed
+        'url': 'http://film.onet.pl/pensjonat-nad-rozlewiskiem-relacja-z-planu-serialu/y428n0',
+        'info_dict': {
+            'id': '501235.965429946',
+            'ext': 'mp4',
+            'title': '"Pensjonat nad rozlewiskiem": relacja z planu serialu',
+            'upload_date': '20170622',
+            'timestamp': 1498159955,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://film.onet.pl/zwiastuny/ghost-in-the-shell-drugi-zwiastun-pl/5q6yl3',
+        'only_matching': True,
+    }, {
+        'url': 'http://moto.onet.pl/jak-wybierane-sa-miejsca-na-fotoradary/6rs04e',
+        'only_matching': True,
+    }, {
+        'url': 'http://businessinsider.com.pl/wideo/scenariusz-na-koniec-swiata-wedlug-nasa/dwnqptk',
+        'only_matching': True,
+    }, {
+        'url': 'http://plejada.pl/weronika-rosati-o-swoim-domniemanym-slubie/n2bq89',
+        'only_matching': True,
+    }]
+
+    def _search_mvp_id(self, webpage, default=NO_DEFAULT):
+        return self._search_regex(
+            r'data-(?:params-)?mvp=["\'](\d+\.\d+)', webpage, 'mvp id',
+            default=default)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        mvp_id = self._search_mvp_id(webpage, default=None)
+
+        if not mvp_id:
+            pulsembed_url = self._search_regex(
+                r'data-src=(["\'])(?P<url>(?:https?:)?//pulsembed\.eu/.+?)\1',
+                webpage, 'pulsembed url', group='url')
+            webpage = self._download_webpage(
+                pulsembed_url, video_id, 'Downloading pulsembed webpage')
+            mvp_id = self._search_mvp_id(webpage)
+
+        return self.url_result(
+            'onetmvp:%s' % mvp_id, OnetMVPIE.ie_key(), video_id=mvp_id)