From f97b4ff7b6607f4da66bc0f67b14b29317011cd2 Mon Sep 17 00:00:00 2001
From: Adam Tauber <asciimoo@gmail.com>
Date: Mon, 15 Mar 2021 17:21:46 +0100
Subject: [PATCH] [fix] update youtube_noapi paging

---
 searx/engines/youtube_noapi.py | 79 +++++++++++++++++++++++++++++++---
 1 file changed, 72 insertions(+), 7 deletions(-)

diff --git a/searx/engines/youtube_noapi.py b/searx/engines/youtube_noapi.py
index 90b93f0a4..5b9e3e3f4 100644
--- a/searx/engines/youtube_noapi.py
+++ b/searx/engines/youtube_noapi.py
@@ -4,7 +4,7 @@
 """
 
 from functools import reduce
-from json import loads
+from json import loads, dumps
 from urllib.parse import quote_plus
 
 # about
@@ -20,12 +20,15 @@ about = {
 # engine dependent config
 categories = ['videos', 'music']
 paging = True
+language_support = False
 time_range_support = True
 
 # search-url
 base_url = 'https://www.youtube.com/results'
 search_url = base_url + '?search_query={query}&page={page}'
 time_range_url = '&sp=EgII{time_range}%253D%253D'
+# the key seems to be constant
+next_page_url = 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
 time_range_dict = {'day': 'Ag',
                    'week': 'Aw',
                    'month': 'BA',
@@ -40,21 +43,73 @@ base_youtube_url = 'https://www.youtube.com/watch?v='
 
 # do search-request
 def request(query, params):
-    params['url'] = search_url.format(query=quote_plus(query),
-                                      page=params['pageno'])
-    if params['time_range'] in time_range_dict:
-        params['url'] += time_range_url.format(time_range=time_range_dict[params['time_range']])
+    if not params['engine_data'].get('next_page_token'):
+        params['url'] = search_url.format(query=quote_plus(query), page=params['pageno'])
+        if params['time_range'] in time_range_dict:
+            params['url'] += time_range_url.format(time_range=time_range_dict[params['time_range']])
+    else:
+        print(params['engine_data']['next_page_token'])
+        params['url'] = next_page_url
+        params['method'] = 'POST'
+        params['data'] = dumps({
+            'context': {"client": {"clientName": "WEB", "clientVersion": "2.20210310.12.01"}},
+            'continuation': params['engine_data']['next_page_token'],
+        })
+        params['headers']['Content-Type'] = 'application/json'
 
     return params
 
 
 # get response from search-request
 def response(resp):
+    if resp.search_params.get('engine_data'):
+        return parse_next_page_response(resp.text)
+    return parse_first_page_response(resp.text)
+
+
+def parse_next_page_response(response_text):
     results = []
+    result_json = loads(response_text)
+    with open("/tmp/x", "w") as f:
+        f.write(response_text)
+    for section in (result_json['onResponseReceivedCommands'][0]
+                    .get('appendContinuationItemsAction')['continuationItems'][0]
+                    .get('itemSectionRenderer')['contents']):
+        if 'videoRenderer' not in section:
+            continue
+        section = section['videoRenderer']
+        content = "-"
+        if 'descriptionSnippet' in section:
+            content = ' '.join(x['text'] for x in section['descriptionSnippet']['runs'])
+        results.append({
+            'url': base_youtube_url + section['videoId'],
+            'title': ' '.join(x['text'] for x in section['title']['runs']),
+            'content': content,
+            'author': section['ownerText']['runs'][0]['text'],
+            'length': section['lengthText']['simpleText'],
+            'template': 'videos.html',
+            'embedded': embedded_url.format(videoid=section['videoId']),
+            'thumbnail': section['thumbnail']['thumbnails'][-1]['url'],
+        })
+    try:
+        token = result_json['onResponseReceivedCommands'][0]\
+            .get('appendContinuationItemsAction')['continuationItems'][1]\
+            .get('continuationItemRenderer')['continuationEndpoint']\
+            .get('continuationCommand')['token']
+        results.append({
+            "engine_data": token,
+            "key": "next_page_token",
+        })
+    except:
+        pass
 
-    results_data = resp.text[resp.text.find('ytInitialData'):]
+    return results
+
+
+def parse_first_page_response(response_text):
+    results = []
+    results_data = response_text[response_text.find('ytInitialData'):]
     results_data = results_data[results_data.find('{'):results_data.find(';</script>')]
-
     results_json = loads(results_data) if results_data else {}
     sections = results_json.get('contents', {})\
                            .get('twoColumnSearchResultsRenderer', {})\
@@ -63,6 +118,16 @@ def response(resp):
                            .get('contents', [])
 
     for section in sections:
+        if "continuationItemRenderer" in section:
+            next_page_token = section["continuationItemRenderer"]\
+                .get("continuationEndpoint", {})\
+                .get("continuationCommand", {})\
+                .get("token", "")
+            if next_page_token:
+                results.append({
+                    "engine_data": next_page_token,
+                    "key": "next_page_token",
+                })
         for video_container in section.get('itemSectionRenderer', {}).get('contents', []):
             video = video_container.get('videoRenderer', {})
             videoid = video.get('videoId')