debian/README.source: Change 'markup'.

[youtubedl] / youtube_dl / extractor / ceskatelevize.py

diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py
index b1dfacf8094f92493ad6cc95b6fe758b3b81f4fc..1ec58f7d8d40d92eacb0aa723e49f189f118ffcd 100644 (file)
--- a/youtube_dl/extractor/ceskatelevize.py
+++ b/youtube_dl/extractor/ceskatelevize.py
@@ -12,13 +12,15 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
     ExtractorError,
     float_or_none,
     sanitized_Request,

+    unescapeHTML,
+    update_url_query,

     urlencode_postdata,
     USER_AGENTS,
 )
 
 
 class CeskaTelevizeIE(InfoExtractor):
     urlencode_postdata,
     USER_AGENTS,
 )
 
 
 class CeskaTelevizeIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'

     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {
     _TESTS = [{
         'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
         'info_dict': {


@@ -62,40 +64,12 @@ class CeskaTelevizeIE(InfoExtractor):
         },
         'skip': 'Georestricted to Czech Republic',
     }, {
         },
         'skip': 'Georestricted to Czech Republic',
     }, {

-        # video with 18+ caution trailer
-        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
-        'info_dict': {
-            'id': '215562210900007-bogotart',
-            'title': 'Queer: Bogotart',
-            'description': 'Alternativní průvodce současným queer světem',
-        },
-        'playlist': [{
-            'info_dict': {
-                'id': '61924494876844842',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Varování 18+)',
-                'duration': 10.2,
-            },
-        }, {
-            'info_dict': {
-                'id': '61924494877068022',
-                'ext': 'mp4',
-                'title': 'Queer: Bogotart (Queer)',
-                'thumbnail': r're:^https?://.*\.jpg',
-                'duration': 1558.3,
-            },
-        }],
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
+        'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
-
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)

 
         webpage = self._download_webpage(url, playlist_id)
 
 
         webpage = self._download_webpage(url, playlist_id)
 


@@ -103,13 +77,28 @@ class CeskaTelevizeIE(InfoExtractor):
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 
         if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
             raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
 

-        typ = self._html_search_regex(
-            r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
-        episode_id = self._html_search_regex(
-            r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
+        type_ = None
+        episode_id = None
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'getPlaylistUrl\(\[({.+?})\]', webpage, 'playlist',
+                default='{}'), playlist_id)
+        if playlist:
+            type_ = playlist.get('type')
+            episode_id = playlist.get('id')
+
+        if not type_:
+            type_ = self._html_search_regex(
+                r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],',
+                webpage, 'type')
+        if not episode_id:
+            episode_id = self._html_search_regex(
+                r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],',
+                webpage, 'episode_id')

 
         data = {
 
         data = {

-            'playlist[0][type]': typ,
+            'playlist[0][type]': type_,

             'playlist[0][id]': episode_id,
             'requestUrl': compat_urllib_parse_urlparse(url).path,
             'requestSource': 'iVysilani',
             'playlist[0][id]': episode_id,
             'requestUrl': compat_urllib_parse_urlparse(url).path,
             'requestSource': 'iVysilani',


@@ -119,7 +108,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         for user_agent in (None, USER_AGENTS['Safari']):
             req = sanitized_Request(
 
         for user_agent in (None, USER_AGENTS['Safari']):
             req = sanitized_Request(

-                'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
+                'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',

                 data=urlencode_postdata(data))
 
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
                 data=urlencode_postdata(data))
 
             req.add_header('Content-type', 'application/x-www-form-urlencoded')


@@ -160,14 +149,13 @@ class CeskaTelevizeIE(InfoExtractor):
                 for format_id, stream_url in item.get('streamUrls', {}).items():
                     if 'playerType=flash' in stream_url:
                         stream_formats = self._extract_m3u8_formats(
                 for format_id, stream_url in item.get('streamUrls', {}).items():
                     if 'playerType=flash' in stream_url:
                         stream_formats = self._extract_m3u8_formats(

-                            stream_url, playlist_id, 'mp4',
-                            entry_protocol='m3u8' if is_live else 'm3u8_native',
+                            stream_url, playlist_id, 'mp4', 'm3u8_native',

                             m3u8_id='hls-%s' % format_id, fatal=False)
                     else:
                         stream_formats = self._extract_mpd_formats(
                             stream_url, playlist_id,
                             mpd_id='dash-%s' % format_id, fatal=False)
                             m3u8_id='hls-%s' % format_id, fatal=False)
                     else:
                         stream_formats = self._extract_mpd_formats(
                             stream_url, playlist_id,
                             mpd_id='dash-%s' % format_id, fatal=False)

-                    # See https://github.com/rg3/youtube-dl/issues/12119#issuecomment-280037031
+                    # See https://github.com/ytdl-org/youtube-dl/issues/12119#issuecomment-280037031

                     if format_id == 'audioDescription':
                         for f in stream_formats:
                             f['source_preference'] = -10
                     if format_id == 'audioDescription':
                         for f in stream_formats:
                             f['source_preference'] = -10


@@ -246,3 +234,54 @@ class CeskaTelevizeIE(InfoExtractor):
                     yield line
 
         return '\r\n'.join(_fix_subtitle(subtitles))
                     yield line
 
         return '\r\n'.join(_fix_subtitle(subtitles))

+
+
+class CeskaTelevizePoradyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
+    _TESTS = [{
+        # video with 18+ caution trailer
+        'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
+        'info_dict': {
+            'id': '215562210900007-bogotart',
+            'title': 'Queer: Bogotart',
+            'description': 'Alternativní průvodce současným queer světem',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '61924494876844842',
+                'ext': 'mp4',
+                'title': 'Queer: Bogotart (Varování 18+)',
+                'duration': 10.2,
+            },
+        }, {
+            'info_dict': {
+                'id': '61924494877068022',
+                'ext': 'mp4',
+                'title': 'Queer: Bogotart (Queer)',
+                'thumbnail': r're:^https?://.*\.jpg',
+                'duration': 1558.3,
+            },
+        }],
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # iframe embed
+        'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        data_url = update_url_query(unescapeHTML(self._search_regex(
+            (r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+             r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
+            webpage, 'iframe player url', group='url')), query={
+                'autoStart': 'true',
+        })
+
+        return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())