Extraction: Move playlist extraction to yt_data_extract

3 files changed, 38 insertions, 19 deletions

diff --git a/youtube/playlist.py b/youtube/playlist.py
index 3e5b0d2..2f7abdc 100644
--- a/youtube/playlist.py
+++ b/youtube/playlist.py
@@ -89,28 +89,20 @@ def get_playlist_page():
         )
         gevent.joinall(tasks)
         first_page_json, this_page_json = tasks[0].value, tasks[1].value
-    
-    try:    # first page
-        video_list = this_page_json['response']['contents']['singleColumnBrowseResultsRenderer']['tabs'][0]['tabRenderer']['content']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents'][0]['playlistVideoListRenderer']['contents']
-    except KeyError:    # other pages
-        video_list = this_page_json['response']['continuationContents']['playlistVideoListContinuation']['contents']
-
-    parsed_video_list = [yt_data_extract.parse_info_prepare_for_html(video_json) for video_json in video_list]
-
-
-    metadata = yt_data_extract.renderer_info(first_page_json['response']['header'])
-    yt_data_extract.prefix_urls(metadata)
 
-    if 'description' not in metadata:
-        metadata['description'] = ''
+    info = yt_data_extract.extract_playlist_info(this_page_json)
+    if page != '1':
+        info['metadata'] = yt_data_extract.extract_playlist_metadata(first_page_json)
 
-    video_count = int(metadata['size'].replace(',', ''))
-    metadata['size'] += ' videos'
+    yt_data_extract.prefix_urls(info['metadata'])
+    for item in info['items']:
+        yt_data_extract.prefix_urls(item)
+        yt_data_extract.add_extra_html_info(item)
 
     return flask.render_template('playlist.html',
-        video_list = parsed_video_list,
-        num_pages = math.ceil(video_count/20),
+        video_list = info['items'],
+        num_pages = math.ceil(info['metadata']['size']/20),
         parameters_dictionary = request.args,
 
-        **metadata
+        **info['metadata']
     ).encode('utf-8')
diff --git a/youtube/templates/playlist.html b/youtube/templates/playlist.html
index ab2640f..52c468e 100644
--- a/youtube/templates/playlist.html
+++ b/youtube/templates/playlist.html
@@ -55,7 +55,7 @@
         <a class="playlist-author" href="{{ author_url }}">{{ author }}</a>
         <div class="playlist-stats">
             <div>{{ views }}</div>
-            <div>{{ size }}</div>
+            <div>{{ size }} videos</div>
         </div>
         <div class="playlist-description">{{ common_elements.text_runs(description) }}</div>
     </div>
diff --git a/youtube/yt_data_extract.py b/youtube/yt_data_extract.py
index 95c68bc..e7a2f1e 100644
--- a/youtube/yt_data_extract.py
+++ b/youtube/yt_data_extract.py
@@ -449,3 +449,30 @@ def extract_search_info(polymer_json):
 
 
     return info
+
+def extract_playlist_metadata(polymer_json):
+    metadata = renderer_info(polymer_json['response']['header'])
+
+    if 'description' not in metadata:
+        metadata['description'] = ''
+
+    metadata['size'] = int(metadata['size'].replace(',', ''))
+
+    return metadata
+
+def extract_playlist_info(polymer_json):
+    info = {}
+    try:    # first page
+        video_list = polymer_json['response']['contents']['singleColumnBrowseResultsRenderer']['tabs'][0]['tabRenderer']['content']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents'][0]['playlistVideoListRenderer']['contents']
+        first_page = True
+    except KeyError:    # other pages
+        video_list = polymer_json['response']['continuationContents']['playlistVideoListContinuation']['contents']
+        first_page = False
+
+    info['items'] = [renderer_info(renderer) for renderer in video_list]
+
+    if first_page:
+        info['metadata'] = extract_playlist_metadata(polymer_json)
+
+    return info
+