From 4faf8099ce8ec77957049ab64eab72d7216fcb0b Mon Sep 17 00:00:00 2001
From: Timothyxxx <384084775@qq.com>
Date: Sat, 16 Dec 2023 22:10:11 +0800
Subject: [PATCH] Add nextPageToken call for exhausting the content

---
 .../youtube/vlc_player/vlc_player.py          | 42 ++++++++++++-------
 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/resouce_collection/youtube/vlc_player/vlc_player.py b/resouce_collection/youtube/vlc_player/vlc_player.py
index c33a653..9533761 100644
--- a/resouce_collection/youtube/vlc_player/vlc_player.py
+++ b/resouce_collection/youtube/vlc_player/vlc_player.py
@@ -3,25 +3,39 @@ import os
 from googleapiclient.discovery import build
 
 
-def search_youtube(api_key, query, max_results=50):
+def search_youtube(api_key, query, max_results=50, language="en"):
     youtube = build('youtube', 'v3', developerKey=api_key)
 
-    search_response = youtube.search().list(
-        q=query,
-        part="id,snippet",
-        maxResults=max_results,
-        type="video"
-    ).execute()
-
     videos = []
+    next_page_token = None
+    total_results = 0
 
-    for search_result in search_response.get("items", []):
-        if search_result["id"]["kind"] == "youtube#video":
-            video_id = search_result["id"]["videoId"]
-            video_metadata = get_video_metadata(api_key, video_id)
-            videos.append(video_metadata)
+    while True:
+        search_response = youtube.search().list(
+            q=query,
+            part="id,snippet",
+            maxResults=max_results,
+            pageToken=next_page_token,
+            type="video",
+            relevanceLanguage=language
+        ).execute()
 
-    return videos
+        video_ids = [item['id']['videoId'] for item in search_response.get("items", []) if
+                     item['id']['kind'] == 'youtube#video']
+
+        # Fetch metadata for each video
+        videos.extend([get_video_metadata(api_key, video_id) for video_id in video_ids])
+
+        total_results += len(video_ids)
+        next_page_token = search_response.get('nextPageToken')
+
+        if not next_page_token or total_results >= max_results:
+            break
+
+    # Sort videos by view count
+    sorted_videos = sorted(videos, key=lambda x: int(x['items'][0]['statistics']['viewCount']), reverse=True)
+
+    return sorted_videos
 
 
 def get_video_metadata(api_key, video_id):