Merge 1e7153125b into f2a4983df7

Closes #11526
Authored by: jshumphrey

yt_dlp/extractor/archiveorg.py

@@ -205,6 +205,26 @@ class ArchiveOrgIE(InfoExtractor):
                 },
             },
         ],
+    }, {
+        # The reviewbody is None for one of the reviews; just need to extract data without crashing
+        'url': 'https://archive.org/details/gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
+        'info_dict': {
+            'id': 'gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
+            'ext': 'mp3',
+            'title': 'Stuck Inside of Mobile with the Memphis Blues Again',
+            'creators': ['Grateful Dead'],
+            'duration': 338.31,
+            'track': 'Stuck Inside of Mobile with the Memphis Blues Again',
+            'description': 'md5:764348a470b986f1217ffd38d6ac7b72',
+            'display_id': 'gd95-04-02d1t04.shn',
+            'location': 'Pyramid Arena',
+            'uploader': 'jon@archive.org',
+            'album': '1995-04-02 - Pyramid Arena',
+            'upload_date': '20040519',
+            'track_number': 4,
+            'release_date': '19950402',
+            'timestamp': 1084927901,
+        },
     }]
 
     @staticmethod
@@ -335,7 +355,7 @@ class ArchiveOrgIE(InfoExtractor):
                 info['comments'].append({
                     'id': review.get('review_id'),
                     'author': review.get('reviewer'),
-                    'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'),
+                    'text': join_nonempty('reviewtitle', 'reviewbody', from_dict=review, delim='\n\n'),
                     'timestamp': unified_timestamp(review.get('createdate')),
                     'parent': 'root'})
 

yt_dlp/extractor/facebook.py

@@ -563,13 +563,13 @@ class FacebookIE(InfoExtractor):
                 return extract_video_data(try_get(
                     js_data, lambda x: x['jsmods']['instances'], list) or [])
 
-        def extract_dash_manifest(video, formats):
+        def extract_dash_manifest(vid_data, formats, mpd_url=None):
             dash_manifest = traverse_obj(
-                video, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', expected_type=str)
+                vid_data, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', 'manifest_xml', expected_type=str)
             if dash_manifest:
                 formats.extend(self._parse_mpd_formats(
                     compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)),
-                    mpd_url=url_or_none(video.get('dash_manifest_url'))))
+                    mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url))
 
         def process_formats(info):
             # Downloads with browser's User-Agent are rate limited. Working around
@@ -619,9 +619,12 @@ class FacebookIE(InfoExtractor):
                         video = video['creation_story']
                         video['owner'] = traverse_obj(video, ('short_form_video_context', 'video_owner'))
                         video.update(reel_info)
-                    fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
+
                     formats = []
                     q = qualities(['sd', 'hd'])
+
+                    # Legacy formats extraction
+                    fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
                     for key, format_id in (('playable_url', 'sd'), ('playable_url_quality_hd', 'hd'),
                                            ('playable_url_dash', ''), ('browser_native_hd_url', 'hd'),
                                            ('browser_native_sd_url', 'sd')):
@@ -629,7 +632,7 @@ class FacebookIE(InfoExtractor):
                         if not playable_url:
                             continue
                         if determine_ext(playable_url) == 'mpd':
-                            formats.extend(self._extract_mpd_formats(playable_url, video_id))
+                            formats.extend(self._extract_mpd_formats(playable_url, video_id, fatal=False))
                         else:
                             formats.append({
                                 'format_id': format_id,
@@ -638,6 +641,28 @@ class FacebookIE(InfoExtractor):
                                 'url': playable_url,
                             })
                     extract_dash_manifest(fmt_data, formats)
+
+                    # New videoDeliveryResponse formats extraction
+                    fmt_data = traverse_obj(video, ('videoDeliveryResponseFragment', 'videoDeliveryResponseResult'))
+                    mpd_urls = traverse_obj(fmt_data, ('dash_manifest_urls', ..., 'manifest_url', {url_or_none}))
+                    dash_manifests = traverse_obj(fmt_data, ('dash_manifests', lambda _, v: v['manifest_xml']))
+                    for idx, dash_manifest in enumerate(dash_manifests):
+                        extract_dash_manifest(dash_manifest, formats, mpd_url=traverse_obj(mpd_urls, idx))
+                    if not dash_manifests:
+                        # Only extract from MPD URLs if the manifests are not already provided
+                        for mpd_url in mpd_urls:
+                            formats.extend(self._extract_mpd_formats(mpd_url, video_id, fatal=False))
+                    for prog_fmt in traverse_obj(fmt_data, ('progressive_urls', lambda _, v: v['progressive_url'])):
+                        format_id = traverse_obj(prog_fmt, ('metadata', 'quality', {str.lower}))
+                        formats.append({
+                            'format_id': format_id,
+                            # sd, hd formats w/o resolution info should be deprioritized below DASH
+                            'quality': q(format_id) - 3,
+                            'url': prog_fmt['progressive_url'],
+                        })
+                    for m3u8_url in traverse_obj(fmt_data, ('hls_playlist_urls', ..., 'hls_playlist_url', {url_or_none})):
+                        formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False, m3u8_id='hls'))
+
                     if not formats:
                         # Do not append false positive entry w/o any formats
                         return

yt_dlp/extractor/pbs.py

@@ -188,7 +188,7 @@ class PBSIE(InfoExtractor):
            # Direct video URL
            (?:{})/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
            # Article with embedded player (or direct video)
-           (?:www\.)?pbs\.org/(?:[^/]+/){{1,5}}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
+           (?:www\.)?(thirteen|pbs)\.org/(?:[^/]+/){{1,5}}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
            (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)
         )
@@ -198,25 +198,37 @@ class PBSIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
-            'md5': '173dc391afd361fa72eab5d3d918968d',
+            'url': 'https://www.thirteen.org/programs/the-woodwrights-shop/carving-away-with-mary-may-tioglz/',
             'info_dict': {
-                'id': '2365006249',
+                'id': '3004803331',
                 'ext': 'mp4',
-                'title': 'Constitution USA with Peter Sagal - A More Perfect Union',
-                'description': 'md5:31b664af3c65fd07fa460d306b837d00',
-                'duration': 3190,
+                'title': "The Woodwright's Shop - Carving Away with Mary May",
+                'description': 'md5:7cbaaaa8b9bcc78bd8f0e31911644e28',
+                'duration': 1606,
+                'display_id': 'carving-away-with-mary-may-tioglz',
+                'chapters': [],
+                'thumbnail': 'https://image.pbs.org/video-assets/NcnTxNl-asset-mezzanine-16x9-K0Keoyv.jpg',
             },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
-            'md5': '6f722cb3c3982186d34b0f13374499c7',
+            'md5': '372b12b670070de39438b946474df92f',
             'info_dict': {
                 'id': '2365297690',
                 'ext': 'mp4',
                 'title': 'FRONTLINE - Losing Iraq',
                 'description': 'md5:5979a4d069b157f622d02bff62fbe654',
                 'duration': 5050,
+                'chapters': [
+                    {'start_time': 0.0, 'end_time': 1234.0, 'title': 'After Saddam, Chaos'},
+                    {'start_time': 1233.0, 'end_time': 1719.0, 'title': 'The Insurgency Takes Root'},
+                    {'start_time': 1718.0, 'end_time': 2461.0, 'title': 'A Light Footprint'},
+                    {'start_time': 2460.0, 'end_time': 3589.0, 'title': 'The Surge '},
+                    {'start_time': 3588.0, 'end_time': 4355.0, 'title': 'The Withdrawal '},
+                    {'start_time': 4354.0, 'end_time': 5051.0, 'title': 'ISIS on the March '},
+                ],
+                'display_id': 'losing-iraq',
+                'thumbnail': 'https://image.pbs.org/video-assets/pbs/frontline/138098/images/mezzanine_401.jpg',
             },
         },
         {
@@ -463,6 +475,7 @@ class PBSIE(InfoExtractor):
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
                 r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
+                r'.*class="passportcoveplayer"[^>]+data-media="(\d+)',  # https://www.thirteen.org/programs/the-woodwrights-shop/who-wrote-the-book-of-sloyd-fggvvq/
                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
                 r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
                 r'<div[^>]+\bdata-cove-id=["\'](\d+)"',  # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/