From b02b5b87b3bae22a9c2667c5b1652ddd7e5afbcb Mon Sep 17 00:00:00 2001
From: James Taylor <user234683@users.noreply.github.com>
Date: Mon, 6 Aug 2018 19:25:14 -0700
Subject: list music used in video if available

---
 youtube/shared.css              |  8 ++++++--
 youtube/watch.py                | 30 ++++++++++++++++++++++++++++
 youtube_dl/extractor/youtube.py | 43 +++++++++++++++++++++++++++++++++++++++++
 yt_watch_template.html          | 19 +++++++++++++++++-
 4 files changed, 97 insertions(+), 3 deletions(-)

diff --git a/youtube/shared.css b/youtube/shared.css
index f99baa1..151111d 100644
--- a/youtube/shared.css
+++ b/youtube/shared.css
@@ -227,11 +227,15 @@ address{
         grid-column: 1 / span 2;
         grid-row: 6;
     }
+    .full-item .music-list{
+        grid-row:7;
+        grid-column: 1 / span 2;
+    }
     .full-item .comments{
-        grid-row: 7;
+        grid-row: 8;
     }
     .full-item .more-comments{
-        grid-row: 8;
+        grid-row: 9;
     }
 
 .medium-item-box{
diff --git a/youtube/watch.py b/youtube/watch.py
index c669f5e..cfe827b 100644
--- a/youtube/watch.py
+++ b/youtube/watch.py
@@ -296,6 +296,10 @@ def extract_info(downloader, *args, **kwargs):
     except YoutubeError as e:
         return str(e)
 
+music_list_table_row = Template('''<tr>
+    <td>$attribute</td>
+    <td>$value</td>
+''')
 def get_watch_page(query_string):
         id = urllib.parse.parse_qs(query_string)['v'][0]
         downloader = YoutubeDL(params={'youtube_include_dash_manifest':False})
@@ -343,7 +347,32 @@ def get_watch_page(query_string):
         else:
             related_videos_html = ''
 
+        music_list = info['music_list']
+        if len(music_list) == 0:
+            music_list_html = ''
+        else:
+            music_list_html = '''<hr>
+<table>
+    <caption>Music</caption>
+    <tr>
+        <th>Artist</th>
+        <th>Title</th>
+        <th>Album</th>
+    </tr>
+'''
+            for track in music_list:
+                music_list_html += '''<tr>\n'''
+                for attribute in ('artist', 'title', 'album'):
+                    try:
+                        value = track[attribute]
+                    except KeyError:
+                        music_list_html += '''<td></td>'''
+                    else:
+                        music_list_html += '''<td>''' + html.escape(value) + '''</td>'''
+                music_list_html += '''</tr>\n'''
+            music_list_html += '''</table>\n'''
 
+        
 
         download_options = ''
         for format in info['formats']:
@@ -371,5 +400,6 @@ def get_watch_page(query_string):
             related                 = related_videos_html,
             comments                = comments_html,
             more_comments_button    = more_comments_button,
+            music_list              = music_list_html,
         )
         return page
\ No newline at end of file
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index c120cfb..39e4ca5 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -10,6 +10,7 @@ import random
 import re
 import time
 import traceback
+import html
 
 from .common import InfoExtractor, SearchInfoExtractor
 from ..jsinterp import JSInterpreter
@@ -1479,6 +1480,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             })
         return chapters
 
+    ul_tag_pattern = re.compile(r'(</?ul)')
+    music_info_pattern = re.compile(r'<h4 class="title">\s*(Song|Music|Artist|Album)\s*</h4>\s*<ul class="content watch-info-tag-list">\s*<li>(?:<a[^>]*>)?([^<]*)(?:</a>)?</li>')
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
 
@@ -1528,6 +1531,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         def extract_view_count(v_info):
             return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
 
+        # Related videos
         related_vid_info = self._search_regex(r"""'RELATED_PLAYER_ARGS':\s*(\{.*?\})""", video_webpage, "related_player_args", default='')
 
         if related_vid_info == '':
@@ -1540,6 +1544,44 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 related_vids = (compat_parse_qs(related_item) for related_item in related_vid_info.split(","))
                 related_vids = [{key : value[0] for key,value in vid.items()} for vid in related_vids]
 
+        # Music list
+        # Test case: https://www.youtube.com/watch?v=jbkZdRglnKY
+        music_list = []
+        metadata_start = video_webpage.find('<ul class="watch-extras-section">')
+        if metadata_start != -1:
+            metadata_start += 33
+            tag_index = metadata_start
+            open_tags = 1
+            while open_tags > 0:
+                match = self.ul_tag_pattern.search(video_webpage, tag_index)
+                if match is None:
+                    print("Couldn't match ul tag")
+                    break
+                tag_index = match.end()
+                tag = match.group(1)
+                if tag == "<ul":
+                    open_tags += 1
+                else:
+                    open_tags -= 1
+            else:
+                last_index = 0
+                metadata = video_webpage[metadata_start:tag_index]
+                current_song = None
+                while True:
+                    match = self.music_info_pattern.search(metadata, last_index)
+                    if match is None:
+                        if current_song is not None:
+                            music_list.append(current_song)
+                        break
+                    title, value = match.group(1), html.unescape(match.group(2))
+                    if title in ("Song", "Music"):
+                        if current_song is not None:
+                            music_list.append(current_song)
+                        current_song = {"title": value}
+                    else:
+                        current_song[title.lower()] = value
+                    last_index = match.end()
+
         # Get video info
         embed_webpage = None
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
@@ -2120,6 +2162,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'track': track,
             'artist': artist,
             'related_vids': related_vids,
+            'music_list': music_list,
         }
 
 
diff --git a/yt_watch_template.html b/yt_watch_template.html
index 7d5f4ae..44e5892 100644
--- a/yt_watch_template.html
+++ b/yt_watch_template.html
@@ -23,6 +23,21 @@
                 .full-item{
                     grid-column: 2;                   
                 }
+                .music-list{
+                    background-color: #d0d0d0;
+                }
+                .music-list table,th,td{
+                    border: 1px solid;
+                }
+                .music-list th,td{
+                    padding-left:4px;
+                    padding-right:5px;
+                }
+                .music-list caption{
+                    text-align:left;
+                    font-weight:bold;
+                    margin-bottom:5px;
+                }
                 .comments{
                     grid-column: 1 / span 2;
                     grid-row: 6;
@@ -106,7 +121,9 @@ $download_options
                     <input class="checkbox" name="video_info_list" value="$video_info" form="playlist-edit" type="checkbox">
 
                     <span class="description">$description</span>
-                    
+                    <div class="music-list">
+$music_list
+                    </div>
                     <section class="comments">
 $comments
                     </section>
-- 
cgit v1.2.3