Subtitle extraction from streaming media manifests #247

Authored by fstirlitz
Modified from: https://github.com/ytdl-org/youtube-dl/pull/6144

Closes: #73
Fixes:
https://github.com/ytdl-org/youtube-dl/issues/6106
https://github.com/ytdl-org/youtube-dl/issues/14977
https://github.com/ytdl-org/youtube-dl/issues/21438
https://github.com/ytdl-org/youtube-dl/issues/23609
https://github.com/ytdl-org/youtube-dl/issues/28132

Might also fix (untested):
https://github.com/ytdl-org/youtube-dl/issues/15424
https://github.com/ytdl-org/youtube-dl/issues/18267
https://github.com/ytdl-org/youtube-dl/issues/23899
https://github.com/ytdl-org/youtube-dl/issues/24375
https://github.com/ytdl-org/youtube-dl/issues/24595
https://github.com/ytdl-org/youtube-dl/issues/27899

Related:
https://github.com/ytdl-org/youtube-dl/issues/22379
https://github.com/ytdl-org/youtube-dl/pull/24517
https://github.com/ytdl-org/youtube-dl/pull/24886
https://github.com/ytdl-org/youtube-dl/pull/27215

Notes:
* The functions `extractor.common._extract_..._formats` are still kept for compatibility
* Only some extractors have currently been moved to using `_extract_..._formats_and_subtitles`
* Direct subtitle manifests (without a master) are not supported and are wrongly identified as containing video formats
* AES support is untested
* The fragmented TTML subtitles extracted from DASH/ISM are valid, but are unsupported by `ffmpeg` and most video players
    * Their XML fragments can be dumped using `ffmpeg -i in.mp4 -f data -map 0 -c copy out.ttml`.
        Once the unnecessary headers are stripped out of this, it becomes a valid self-contained ttml file
    * The ttml subs downloaded from DASH manifests can also be directly opened with <https://github.com/SubtitleEdit>
* Fragmented WebVTT files extracted from DASH/ISM are also unsupported by most tools
    * Unlike the ttml files, the XML fragments of these cannot be dumped using `ffmpeg`
    * The webtt subs extracted from DASH can be parsed by <https://github.com/gpac/gpac>
    * But validity of the those extracted from ISM are untested

1 files changed, 17 insertions, 65 deletions

diff --git a/yt_dlp/extractor/elonet.py b/yt_dlp/extractor/elonet.py
index 3647c0a9c..eefba4e24 100644
--- a/yt_dlp/extractor/elonet.py
+++ b/yt_dlp/extractor/elonet.py
@@ -1,9 +1,7 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import os
 import re
-import tempfile
 
 from .common import InfoExtractor
 from ..utils import (
@@ -12,12 +10,12 @@ from ..utils import (
     try_get,
 )
 from ..compat import compat_str
-from ..downloader.hls import HlsFD
 
 
 class ElonetIE(InfoExtractor):
     _VALID_URL = r'https?://elonet\.finna\.fi/Record/kavi\.elonet_elokuva_(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
+        # m3u8 with subtitles
         'url': 'https://elonet.finna.fi/Record/kavi.elonet_elokuva_107867',
         'md5': '8efc954b96c543711707f87de757caea',
         'info_dict': {
@@ -27,62 +25,17 @@ class ElonetIE(InfoExtractor):
             'description': 'Valkoinen peura (1952) on Erik Blombergin ohjaama ja yhdessä Mirjami Kuosmasen kanssa käsikirjoittama tarunomainen kertomus valkoisen peuran hahmossa lii...',
             'thumbnail': 'https://elonet.finna.fi/Cover/Show?id=kavi.elonet_elokuva_107867&index=0&size=large',
         },
-    }
-
-    def _download_m3u8_chunked_subtitle(self, chunklist_url):
-        """
-        Download VTT subtitles from pieces in manifest URL.
-        Return a string containing joined chunks with extra headers removed.
-        """
-        with tempfile.NamedTemporaryFile(delete=True) as outfile:
-            fname = outfile.name
-        hlsdl = HlsFD(self._downloader, {})
-        hlsdl.download(compat_str(fname), {"url": chunklist_url})
-        with open(fname, 'r') as fin:
-            # Remove (some) headers
-            fdata = re.sub(r'X-TIMESTAMP-MAP.*\n+|WEBVTT\n+', '', fin.read())
-        os.remove(fname)
-        return "WEBVTT\n\n" + fdata
-
-    def _parse_m3u8_subtitles(self, m3u8_doc, m3u8_url):
-        """
-        Parse subtitles from HLS / m3u8 manifest.
-        """
-        subtitles = {}
-        baseurl = m3u8_url[:m3u8_url.rindex('/') + 1]
-        for line in m3u8_doc.split('\n'):
-            if 'EXT-X-MEDIA:TYPE=SUBTITLES' in line:
-                lang = self._search_regex(
-                    r'LANGUAGE="(.+?)"', line, 'lang', default=False)
-                uri = self._search_regex(
-                    r'URI="(.+?)"', line, 'uri', default=False)
-                if lang and uri:
-                    data = self._download_m3u8_chunked_subtitle(baseurl + uri)
-                    subtitles[lang] = [{'ext': 'vtt', 'data': data}]
-        return subtitles
-
-    def _parse_mpd_subtitles(self, mpd_doc):
-        """
-        Parse subtitles from MPD manifest.
-        """
-        ns = '{urn:mpeg:dash:schema:mpd:2011}'
-        subtitles = {}
-        for aset in mpd_doc.findall(".//%sAdaptationSet[@mimeType='text/vtt']" % (ns)):
-            lang = aset.attrib.get('lang', 'unk')
-            url = aset.find("./%sRepresentation/%sBaseURL" % (ns, ns)).text
-            subtitles[lang] = [{'ext': 'vtt', 'url': url}]
-        return subtitles
-
-    def _get_subtitles(self, fmt, doc, url):
-        if fmt == 'm3u8':
-            subs = self._parse_m3u8_subtitles(doc, url)
-        elif fmt == 'mpd':
-            subs = self._parse_mpd_subtitles(doc)
-        else:
-            self.report_warning(
-                "Cannot download subtitles from '%s' streams." % (fmt))
-            subs = {}
-        return subs
+    }, {
+        # DASH with subtitles
+        'url': 'https://elonet.finna.fi/Record/kavi.elonet_elokuva_116539',
+        'info_dict': {
+            'id': '116539',
+            'ext': 'mp4',
+            'title': 'Minulla on tiikeri',
+            'description': 'Pienellä pojalla, joka asuu kerrostalossa, on kotieläimenä tiikeri. Se on kuitenkin salaisuus. Kerrostalon räpätäti on Kotilaisen täti, joka on aina vali...',
+            'thumbnail': 'https://elonet.finna.fi/Cover/Show?id=kavi.elonet_elokuva_116539&index=0&size=large&source=Solr',
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -101,8 +54,8 @@ class ElonetIE(InfoExtractor):
             self._parse_json(json_s, video_id),
             lambda x: x[0]["src"], compat_str)
         formats = []
+        subtitles = {}
         if re.search(r'\.m3u8\??', src):
-            fmt = 'm3u8'
             res = self._download_webpage_handle(
                 # elonet servers have certificate problems
                 src.replace('https:', 'http:'), video_id,
@@ -111,11 +64,10 @@ class ElonetIE(InfoExtractor):
             if res:
                 doc, urlh = res
                 url = urlh.geturl()
-                formats = self._parse_m3u8_formats(doc, url)
+                formats, subtitles = self._parse_m3u8_formats_and_subtitles(doc, url)
                 for f in formats:
                     f['ext'] = 'mp4'
         elif re.search(r'\.mpd\??', src):
-            fmt = 'mpd'
             res = self._download_xml_handle(
                 src, video_id,
                 note='Downloading MPD manifest',
@@ -123,7 +75,7 @@ class ElonetIE(InfoExtractor):
             if res:
                 doc, urlh = res
                 url = base_url(urlh.geturl())
-                formats = self._parse_mpd_formats(doc, mpd_base_url=url)
+                formats, subtitles = self._parse_mpd_formats_and_subtitles(doc, mpd_base_url=url)
         else:
             raise ExtractorError("Unknown streaming format")
 
@@ -133,5 +85,5 @@ class ElonetIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'formats': formats,
-            'subtitles': self.extract_subtitles(fmt, doc, url),
+            'subtitles': subtitles,
         }