Update upstream source from tag 'upstream/2020.06.16.1'

[youtubedl] / youtube_dl / extractor / pbs.py

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 3e51b4dd746d88ead54bc9ca469113f1f3cf14d2..4dbe661be892dfaf7ff5799f274bfd7a5ef5fa31 100644 (file)
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -4,14 +4,18 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
 from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,

+    float_or_none,

     js_to_json,
     js_to_json,

+    orderedSet,

     strip_jsonp,
     strip_or_none,
     unified_strdate,
     strip_jsonp,
     strip_or_none,
     unified_strdate,

+    url_or_none,

     US_RATINGS,
 )
 
     US_RATINGS,
 )
 


@@ -185,9 +189,9 @@ class PBSIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?:
            # Direct video URL
     _VALID_URL = r'''(?x)https?://
         (?:
            # Direct video URL

-           (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+           (?:%s)/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |

            # Article with embedded player (or direct video)
            # Article with embedded player (or direct video)

-           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
+           (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |

            # Player
            (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
            # Player
            (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )


@@ -263,6 +267,13 @@ class PBSIE(InfoExtractor):
             },
             'playlist_count': 2,
         },
             },
             'playlist_count': 2,
         },

+        {
+            'url': 'http://www.pbs.org/wgbh/americanexperience/films/great-war/',
+            'info_dict': {
+                'id': 'great-war',
+            },
+            'playlist_count': 3,
+        },

         {
             'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
             'info_dict': {
         {
             'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
             'info_dict': {


@@ -294,7 +305,7 @@ class PBSIE(InfoExtractor):
         {
             # Video embedded in iframe containing angle brackets as attribute's value (e.g.
             # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
         {
             # Video embedded in iframe containing angle brackets as attribute's value (e.g.
             # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see

-            # https://github.com/rg3/youtube-dl/issues/7059)
+            # https://github.com/ytdl-org/youtube-dl/issues/7059)

             'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
             'md5': '59b0ef5009f9ac8a319cc5efebcd865e',
             'info_dict': {
             'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
             'md5': '59b0ef5009f9ac8a319cc5efebcd865e',
             'info_dict': {


@@ -336,6 +347,65 @@ class PBSIE(InfoExtractor):
                 'formats': 'mincount:8',
             },
         },
                 'formats': 'mincount:8',
             },
         },

+        {
+            # https://github.com/ytdl-org/youtube-dl/issues/13801
+            'url': 'https://www.pbs.org/video/pbs-newshour-full-episode-july-31-2017-1501539057/',
+            'info_dict': {
+                'id': '3003333873',
+                'ext': 'mp4',
+                'title': 'PBS NewsHour - full episode July 31, 2017',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'duration': 3265,
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/',
+            'info_dict': {
+                'id': '2365936247',
+                'ext': 'mp4',
+                'title': 'Antiques Roadshow - Indianapolis, Hour 2',
+                'description': 'md5:524b32249db55663e7231b6b8d1671a2',
+                'duration': 3180,
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 403: Forbidden'],
+        },
+        {
+            'url': 'https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/',
+            'info_dict': {
+                'id': '3007193718',
+                'ext': 'mp4',
+                'title': "Victoria - A Soldier's Daughter / The Green-Eyed Monster",
+                'description': 'md5:37efbac85e0c09b009586523ec143652',
+                'duration': 6292,
+                'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 403: Forbidden'],
+        },
+        {
+            'url': 'https://player.pbs.org/partnerplayer/tOz9tM5ljOXQqIIWke53UA==/',
+            'info_dict': {
+                'id': '3011407934',
+                'ext': 'mp4',
+                'title': 'Stories from the Stage - Road Trip',
+                'duration': 1619,
+                'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'expected_warnings': ['HTTP Error 403: Forbidden'],
+        },

         {
             'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
             'only_matching': True,
         {
             'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
             'only_matching': True,


@@ -343,6 +413,10 @@ class PBSIE(InfoExtractor):
         {
             'url': 'http://watch.knpb.org/video/2365616055/',
             'only_matching': True,
         {
             'url': 'http://watch.knpb.org/video/2365616055/',
             'only_matching': True,

+        },
+        {
+            'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
+            'only_matching': True,

         }
     ]
     _ERRORS = {
         }
     ]
     _ERRORS = {


@@ -381,10 +455,10 @@ class PBSIE(InfoExtractor):
             # tabbed frontline videos
             MULTI_PART_REGEXES = (
                 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"',
             # tabbed frontline videos
             MULTI_PART_REGEXES = (
                 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"',

-                r'<a[^>]+href=["\']#video-\d+["\'][^>]+data-coveid=["\'](\d+)',
+                r'<a[^>]+href=["\']#(?:video-|part)\d+["\'][^>]+data-cove[Ii]d=["\'](\d+)',

             )
             for p in MULTI_PART_REGEXES:
             )
             for p in MULTI_PART_REGEXES:

-                tabbed_videos = re.findall(p, webpage)
+                tabbed_videos = orderedSet(re.findall(p, webpage))

                 if tabbed_videos:
                     return tabbed_videos, presumptive_id, upload_date, description
 
                 if tabbed_videos:
                     return tabbed_videos, presumptive_id, upload_date, description
 


@@ -393,6 +467,9 @@ class PBSIE(InfoExtractor):
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
                 r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
                 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
                 r'<section[^>]+data-coveid="(\d+)"',                    # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
                 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/
+                r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)',  # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/

             ]
 
             media_id = self._search_regex(
             ]
 
             media_id = self._search_regex(


@@ -424,7 +501,11 @@ class PBSIE(InfoExtractor):
                 if url:
                     break
 
                 if url:
                     break
 

-            mobj = re.match(self._VALID_URL, url)
+            if not url:
+                url = self._og_search_url(webpage)
+
+            mobj = re.match(
+                self._VALID_URL, self._proto_relative_url(url.strip()))

 
         player_id = mobj.group('player_id')
         if not display_id:
 
         player_id = mobj.group('player_id')
         if not display_id:


@@ -434,13 +515,27 @@ class PBSIE(InfoExtractor):
                 url, display_id, note='Downloading player page',
                 errnote='Could not download player page')
             video_id = self._search_regex(
                 url, display_id, note='Downloading player page',
                 errnote='Could not download player page')
             video_id = self._search_regex(

-                r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
+                r'<div\s+id=["\']video_(\d+)', player_page, 'video ID',
+                default=None)
+            if not video_id:
+                video_info = self._extract_video_data(
+                    player_page, 'video data', display_id)
+                video_id = compat_str(
+                    video_info.get('id') or video_info['contentID'])

         else:
             video_id = mobj.group('id')
             display_id = video_id
 
         return video_id, display_id, None, description
 
         else:
             video_id = mobj.group('id')
             display_id = video_id
 
         return video_id, display_id, None, description
 

+    def _extract_video_data(self, string, name, video_id, fatal=True):
+        return self._parse_json(
+            self._search_regex(
+                [r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
+                 r'window\.videoBridge\s*=\s*({.+?});'],
+                string, name, default='{}'),
+            video_id, transform_source=js_to_json, fatal=fatal)
+

     def _real_extract(self, url):
         video_id, display_id, upload_date, description = self._extract_webpage(url)
 
     def _real_extract(self, url):
         video_id, display_id, upload_date, description = self._extract_webpage(url)
 


@@ -463,22 +558,45 @@ class PBSIE(InfoExtractor):
                 if redirect_url and redirect_url not in redirect_urls:
                     redirects.append(redirect)
                     redirect_urls.add(redirect_url)
                 if redirect_url and redirect_url not in redirect_urls:
                     redirects.append(redirect)
                     redirect_urls.add(redirect_url)

-
+            encodings = info.get('encodings')
+            if isinstance(encodings, list):
+                for encoding in encodings:
+                    encoding_url = url_or_none(encoding)
+                    if encoding_url and encoding_url not in redirect_urls:
+                        redirects.append({'url': encoding_url})
+                        redirect_urls.add(encoding_url)
+
+        chapters = []

         # Player pages may also serve different qualities
         for page in ('widget/partnerplayer', 'portalplayer'):
             player = self._download_webpage(
                 'http://player.pbs.org/%s/%s' % (page, video_id),
                 display_id, 'Downloading %s page' % page, fatal=False)
             if player:
         # Player pages may also serve different qualities
         for page in ('widget/partnerplayer', 'portalplayer'):
             player = self._download_webpage(
                 'http://player.pbs.org/%s/%s' % (page, video_id),
                 display_id, 'Downloading %s page' % page, fatal=False)
             if player:

-                video_info = self._parse_json(
-                    self._search_regex(
-                        r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
-                        player, '%s video data' % page, default='{}'),
-                    display_id, transform_source=js_to_json, fatal=False)
+                video_info = self._extract_video_data(
+                    player, '%s video data' % page, display_id, fatal=False)

                 if video_info:
                     extract_redirect_urls(video_info)
                     if not info:
                         info = video_info
                 if video_info:
                     extract_redirect_urls(video_info)
                     if not info:
                         info = video_info

+                if not chapters:
+                    raw_chapters = video_info.get('chapters') or []
+                    if not raw_chapters:
+                        for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player):
+                            chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False)
+                            if not chapter:
+                                continue
+                            raw_chapters.append(chapter)
+                    for chapter in raw_chapters:
+                        start_time = float_or_none(chapter.get('start_time'), 1000)
+                        duration = float_or_none(chapter.get('duration'), 1000)
+                        if start_time is None or duration is None:
+                            continue
+                        chapters.append({
+                            'start_time': start_time,
+                            'end_time': start_time + duration,
+                            'title': chapter.get('title'),
+                        })

 
         formats = []
         http_url = None
 
         formats = []
         http_url = None


@@ -515,7 +633,7 @@ class PBSIE(InfoExtractor):
                     http_url = format_url
         self._remove_duplicate_formats(formats)
         m3u8_formats = list(filter(
                     http_url = format_url
         self._remove_duplicate_formats(formats)
         m3u8_formats = list(filter(

-            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
+            lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',

             formats))
         if http_url:
             for m3u8_format in m3u8_formats:
             formats))
         if http_url:
             for m3u8_format in m3u8_formats:


@@ -524,7 +642,7 @@ class PBSIE(InfoExtractor):
                 # we won't try extracting them.
                 # Since summer 2016 higher quality formats (4500k and 6500k) are also available
                 # albeit they are not documented in [2].
                 # we won't try extracting them.
                 # Since summer 2016 higher quality formats (4500k and 6500k) are also available
                 # albeit they are not documented in [2].

-                # 1. https://github.com/rg3/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656
+                # 1. https://github.com/ytdl-org/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656

                 # 2. https://projects.pbs.org/confluence/display/coveapi/COVE+Video+Specifications
                 if not bitrate or int(bitrate) < 400:
                     continue
                 # 2. https://projects.pbs.org/confluence/display/coveapi/COVE+Video+Specifications
                 if not bitrate or int(bitrate) < 400:
                     continue


@@ -588,4 +706,5 @@ class PBSIE(InfoExtractor):
             'upload_date': upload_date,
             'formats': formats,
             'subtitles': subtitles,
             'upload_date': upload_date,
             'formats': formats,
             'subtitles': subtitles,

+            'chapters': chapters,

         }
         }