Merge ab6ade9c4c0c0ef3f3c5ceb3f3c03619d1899309 into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/YoutubeDL.py

@@ -266,11 +266,13 @@ class YoutubeDL(object):
                        postprocessor.
     progress_hooks:    A list of functions that get called on download
                        progress, with a dictionary with the entries
-                       * status: One of "downloading", "error", or "finished".
+                       * status: One of "downloading", "error", "finished",
+                                 or "postprocessed".
                                  Check this first and ignore unknown values.
 
-                       If status is one of "downloading", or "finished", the
+                       If status is one of "downloading", "finished", or
-                       following properties may also be present:
+                       "postprocessed", the following properties may also be
+                       present:
                        * filename: The final filename (always present)
                        * tmpfilename: The filename we're currently writing to
                        * downloaded_bytes: Bytes on disk
@@ -285,6 +287,9 @@ class YoutubeDL(object):
                                          downloaded video fragment.
                        * fragment_count: The number of fragments (= individual
                                          files that will be merged)
+                       * postprocessor: The specific postprocessor that ran.
+                                        See youtube_dl/postprocessor/__init__.py
+                                        for a list of possibilities.
 
                        Progress hooks are guaranteed to be called at least once
                        (with status "finished") if the download is successful.
@@ -2318,6 +2323,8 @@ class YoutubeDL(object):
             pps_chain.extend(ie_info['__postprocessors'])
         pps_chain.extend(self._pps)
         for pp in pps_chain:
+            for ph in self._progress_hooks:
+                pp.add_progress_hook(ph)
             files_to_delete = []
             try:
                 files_to_delete, info = pp.run(info)

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError:

youtube_dl/postprocessor/common.py

@@ -33,6 +33,7 @@ class PostProcessor(object):
 
     def __init__(self, downloader=None):
         self._downloader = downloader
+        self._progress_hooks = []
 
     def set_downloader(self, downloader):
         """Sets the downloader for this PP."""
@@ -64,6 +65,15 @@ class PostProcessor(object):
     def _configuration_args(self, default=[]):
         return cli_configuration_args(self._downloader.params, 'postprocessor_args', default)
 
+    def _hook_progress(self, status):
+        for ph in self._progress_hooks:
+            ph(status)
+
+    def add_progress_hook(self, ph):
+        # See YoutubeDl.py (search for progress_hooks) for a description of
+        # this interface
+        self._progress_hooks.append(ph)
+
 
 class AudioConversionError(PostProcessingError):
     pass

youtube_dl/postprocessor/embedthumbnail.py

@@ -130,4 +130,12 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
         else:
             raise EmbedThumbnailPPError('Only mp3 and m4a/mp4 are supported for thumbnail embedding for now.')
 
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': encodeFilename(filename),
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
+
         return [], info

youtube_dl/postprocessor/execafterdownload.py

@@ -27,5 +27,9 @@ class ExecAfterDownloadPP(PostProcessor):
         if retCode != 0:
             raise PostProcessingError(
                 'Command returned error code %d' % retCode)
+        self._hook_progress({
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
 
         return [], information

youtube_dl/postprocessor/ffmpeg.py

@@ -342,6 +342,14 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
                 new_path, time.time(), information['filetime'],
                 errnote='Cannot update utime of audio file')
 
+        fsize = os.path.getsize(new_path)
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': new_path,
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
+
         return [path], information
 
 
@@ -365,6 +373,13 @@ class FFmpegVideoConvertorPP(FFmpegPostProcessor):
         information['filepath'] = outpath
         information['format'] = self._preferedformat
         information['ext'] = self._preferedformat
+        fsize = os.path.getsize(outpath)
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': outpath,
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
         return [path], information
 
 
@@ -422,6 +437,13 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
         self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': encodeFilename(filename),
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
 
         return sub_filenames, information
 
@@ -507,6 +529,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
             os.remove(metadata_filename)
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': encodeFilename(filename),
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
         return [], info
 
 
@@ -518,6 +547,13 @@ class FFmpegMergerPP(FFmpegPostProcessor):
         self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename)
         self.run_ffmpeg_multiple_files(info['__files_to_merge'], temp_filename, args)
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': encodeFilename(filename),
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
         return info['__files_to_merge'], info
 
     def can_merge(self):
@@ -553,6 +589,13 @@ class FFmpegFixupStretchedPP(FFmpegPostProcessor):
 
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': encodeFilename(filename),
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
 
         return [], info
 
@@ -571,6 +614,13 @@ class FFmpegFixupM4aPP(FFmpegPostProcessor):
 
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'total_bytes': fsize,
+            'filename': encodeFilename(filename),
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
 
         return [], info
 
@@ -587,6 +637,14 @@ class FFmpegFixupM3u8PP(FFmpegPostProcessor):
 
             os.remove(encodeFilename(filename))
             os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
+            fsize = os.path.getsize(encodeFilename(filename))
+            self._hook_progress({
+                'total_bytes': fsize,
+                'filename': encodeFilename(filename),
+                'status': 'postprocessed',
+                'postprocessor': self.__class__.__name__
+            })
         return [], info
 
 
@@ -650,4 +708,9 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
                     'data': f.read(),
                 }
 
+        self._hook_progress({
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
+
         return sub_filenames, info

youtube_dl/postprocessor/metadatafromtitle.py

@@ -46,5 +46,9 @@ class MetadataFromTitlePP(PostProcessor):
             self._downloader.to_screen(
                 '[fromtitle] parsed %s: %s'
                 % (attribute, value if value is not None else 'NA'))
+        self._hook_progress({
+            'status': 'postprocessed',
+            'postprocessor': self.__class__.__name__
+        })
 
         return [], info

youtube_dl/postprocessor/xattrpp.py

@@ -55,6 +55,11 @@ class XAttrMetadataPP(PostProcessor):
                     write_xattr(filename, xattrname, byte_value)
                     num_written += 1
 
+            self._hook_progress({
+                'status': 'postprocessed',
+                'postprocessor': self.__class__.__name__
+            })
+
             return [], info
 
         except XAttrUnavailableError as e: