From defcd753ef25ea21a2d29a7ef57f4dcf57c77766 Mon Sep 17 00:00:00 2001
From: Petr Novak <petr.novak@cosmoboy.cz>
Date: Sun, 29 Oct 2017 21:40:06 +0100
Subject: [PATCH] [seznamzpravy] Parse HLS and DASH

Includes extension of generic MPD extractor and few more
fixes per dstftw.
---
 youtube_dl/extractor/common.py       |  9 +++++++++
 youtube_dl/extractor/seznamzpravy.py | 21 +++++++++++++++++----
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index a69240693..20abd06f2 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -1979,6 +1979,15 @@ class InfoExtractor(object):
                                     })
                                     segment_index += 1
                             representation_ms_info['fragments'] = fragments
+                        elif 'segment_urls' in representation_ms_info:
+                            # Segment URLs with no SegmentTimeline
+                            # Example: https://www.seznam.cz/zpravy/clanek/cesko-zasahne-vitr-o-sile-vichrice-muze-byt-i-zivotu-nebezpecny-39091
+                            fragments = []
+                            for segment_url in representation_ms_info['segment_urls']:
+                                fragments.append({
+                                    location_key(segment_url): segment_url,
+                                })
+                            representation_ms_info['fragments'] = fragments
                         # NB: MPD manifest may contain direct URLs to unfragmented media.
                         # No fragments key is present in this case.
                         if 'fragments' in representation_ms_info:
diff --git a/youtube_dl/extractor/seznamzpravy.py b/youtube_dl/extractor/seznamzpravy.py
index 869ffafc8..d1ca50479 100644
--- a/youtube_dl/extractor/seznamzpravy.py
+++ b/youtube_dl/extractor/seznamzpravy.py
@@ -16,7 +16,9 @@ class SeznamZpravyIE(InfoExtractor):
     _TESTS = [{
         # video with SDN URL
         'url': 'https://www.seznam.cz/zpravy/clanek/jejich-svet-na-nas-utoci-je-lepsi-branit-se-na-jejich-pisecku-rika-reziser-a-major-v-zaloze-marhoul-35990',
-        'md5': '855f9fed87bd93e48775d59671a3a3e3',
+        'params': {'skip_download': True},
+        # ^ this is here instead of 'file_minsize': 1586, which does not work because
+        #   test_download.py forces expected_minsize to at least 10k when test is running
         'info_dict': {
             'id': '35990',
             'ext': 'mp4',
@@ -37,21 +39,23 @@ class SeznamZpravyIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         data = self._download_json(self._API_URL + 'v1/documents/' + video_id, video_id)
+        title = data['captionTitle']
 
         if 'video' in data['caption']:
             sdn_url = data['caption']['video']['sdn'] + self._MAGIC_SUFFIX
         else:
             sdn_url = self._download_json(data['caption']['liveStreamUrl'] + self._MAGIC_SUFFIX, video_id)['Location']
 
+        sdn_data = self._download_json(sdn_url, video_id)
         formats = []
-        for fmt, fmtdata in self._download_json(sdn_url, video_id)['data']['mp4'].items():
+        for fmt, fmtdata in sdn_data.get('data', {}).get('mp4', {}).items():
             relative_url = fmtdata.get('url')
             if not relative_url:
                 continue
 
             try:
                 width, height = fmtdata.get('resolution')
-            except TypeError:
+            except (TypeError, ValueError):
                 width, height = None, None
 
             formats.append({
@@ -61,11 +65,20 @@ class SeznamZpravyIE(InfoExtractor):
                 'url': urljoin(sdn_url, relative_url),
             })
 
+        playlists = sdn_data.get('pls', {})
+        dash_rel_url = playlists.get('dash', {}).get('url')
+        if dash_rel_url:
+            formats.extend(self._extract_mpd_formats(urljoin(sdn_url, dash_rel_url), video_id, mpd_id='dash', fatal=False))
+
+        hls_rel_url = playlists.get('hls', {}).get('url')
+        if hls_rel_url:
+            formats.extend(self._extract_m3u8_formats(urljoin(sdn_url, hls_rel_url), video_id, ext='mp4', m3u8_id='hls', fatal=False))
+
         self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': data['captionTitle'],
+            'title': title,
             'description': data.get('perex'),
             'formats': formats,
         }