[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / ceskatelevize.py

diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py
index 0daee313fb12434db7bc903235185cefea4cc57f..7cb4efb746b5f7eae929ccd16993e530122d9ed3 100644 (file)
--- a/youtube_dl/extractor/ceskatelevize.py
+++ b/youtube_dl/extractor/ceskatelevize.py
@@ -12,6 +12,8 @@ from ..utils import (
     ExtractorError,
     float_or_none,
     sanitized_Request,
+    unescapeHTML,
+    update_url_query,
     urlencode_postdata,
     USER_AGENTS,
 )
@@ -106,7 +108,7 @@ class CeskaTelevizeIE(InfoExtractor):
 
         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')
@@ -145,6 +147,8 @@ class CeskaTelevizeIE(InfoExtractor):
                 is_live = item.get('type') == 'LIVE'
                 formats = []
                 for format_id, stream_url in item.get('streamUrls', {}).items():
+                    if 'drmOnly=true' in stream_url:
+                        continue
                     if 'playerType=flash' in stream_url:
                         stream_formats = self._extract_m3u8_formats(
                             stream_url, playlist_id, 'mp4', 'm3u8_native',
@@ -153,7 +157,7 @@ class CeskaTelevizeIE(InfoExtractor):
                         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
@@ -232,3 +236,54 @@ class CeskaTelevizeIE(InfoExtractor):
                     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())