heckyel/yt-local
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Extraction: Move playlist extraction to yt_data_extract

Browse Source
This commit is contained in:
James Taylor 2019-09-08 18:42:08 -07:00
parent c362a5e834
commit 89e5761f8d
3 changed files with 38 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube/playlist.py
View File

@ -89,28 +89,20 @@ def get_playlist_page():
) )
gevent.joinall(tasks) gevent.joinall(tasks)
first_page_json, this_page_json = tasks[0].value, tasks[1].value 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] info = yt_data_extract.extract_playlist_info(this_page_json)
if page != '1':
info['metadata'] = yt_data_extract.extract_playlist_metadata(first_page_json)
yt_data_extract.prefix_urls(info['metadata'])
metadata = yt_data_extract.renderer_info(first_page_json['response']['header']) for item in info['items']:
yt_data_extract.prefix_urls(metadata) yt_data_extract.prefix_urls(item)
yt_data_extract.add_extra_html_info(item)
if 'description' not in metadata:
metadata['description'] = ''
video_count = int(metadata['size'].replace(',', ''))
metadata['size'] += ' videos'
return flask.render_template('playlist.html', return flask.render_template('playlist.html',
video_list = parsed_video_list, video_list = info['items'],
num_pages = math.ceil(video_count/20), num_pages = math.ceil(info['metadata']['size']/20),
parameters_dictionary = request.args, parameters_dictionary = request.args,
**metadata **info['metadata']
).encode('utf-8') ).encode('utf-8')

2
youtube/templates/playlist.html
View File

@ -55,7 +55,7 @@
<a class="playlist-author" href="{{ author_url }}">{{ author }}</a> <a class="playlist-author" href="{{ author_url }}">{{ author }}</a>
<div class="playlist-stats"> <div class="playlist-stats">
<div>{{ views }}</div> <div>{{ views }}</div>
<div>{{ size }}</div> <div>{{ size }} videos</div>
</div> </div>
<div class="playlist-description">{{ common_elements.text_runs(description) }}</div> <div class="playlist-description">{{ common_elements.text_runs(description) }}</div>
</div> </div>

27
youtube/yt_data_extract.py
View File

@ -449,3 +449,30 @@ def extract_search_info(polymer_json):
return info 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