From 68752000f0213f801a7c5e8127b77afeba644f7d Mon Sep 17 00:00:00 2001 From: Jesus E Date: Sun, 28 May 2023 21:04:36 -0400 Subject: Update channel to new ctoken format Huge thanks to @michaelweiser Different sortings still don't work for videos and playlists --- youtube/yt_data_extract/everything_else.py | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'youtube/yt_data_extract/everything_else.py') diff --git a/youtube/yt_data_extract/everything_else.py b/youtube/yt_data_extract/everything_else.py index 56a2e68..9a6e31a 100644 --- a/youtube/yt_data_extract/everything_else.py +++ b/youtube/yt_data_extract/everything_else.py @@ -9,7 +9,7 @@ import re import urllib from math import ceil -def extract_channel_info(polymer_json, tab): +def extract_channel_info(polymer_json, tab, continuation=False): response, err = extract_response(polymer_json) if err: return {'error': err} @@ -23,7 +23,8 @@ def extract_channel_info(polymer_json, tab): # channel doesn't exist or was terminated # example terminated channel: https://www.youtube.com/channel/UCnKJeK_r90jDdIuzHXC0Org - if not metadata: + # metadata and microformat are not present for continuation requests + if not metadata and not continuation: if response.get('alerts'): error_string = ' '.join( extract_str(deep_get(alert, 'alertRenderer', 'text'), default='') @@ -44,7 +45,7 @@ def extract_channel_info(polymer_json, tab): info['approx_subscriber_count'] = extract_approx_int(deep_get(response, 'header', 'c4TabbedHeaderRenderer', 'subscriberCountText')) - # stuff from microformat (info given by youtube for every page on channel) + # stuff from microformat (info given by youtube for first page on channel) info['short_description'] = metadata.get('description') if info['short_description'] and len(info['short_description']) > 730: info['short_description'] = info['short_description'][0:730] + '...' @@ -69,8 +70,8 @@ def extract_channel_info(polymer_json, tab): info['ctoken'] = None # empty channel - if 'contents' not in response and 'continuationContents' not in response: - return info + #if 'contents' not in response and 'continuationContents' not in response: + # return info if tab in ('videos', 'playlists', 'search'): items, ctoken = extract_items(response) -- cgit v1.2.3