new boilerplate extractor for related videos

ythdd_extractor.py

@@ -1,5 +1,6 @@
 #!/usr/bin/python3
-import yt_dlp, toml
+import yt_dlp, requests, json
+import ythdd_globals
 
 ytdl_opts = {
 	#"format": "bv*[height<=720]+ba", # to be defined by the user
@@ -14,11 +15,53 @@ ytdl_opts = {
 	"simulate": True
 }
 
-def extract(url, getcomments=False, maxcomments=""):
+def extract(url: str, getcomments=False, maxcomments=""):
+	if len(url) == 11:
+		url = "https://www.youtube.com/watch?v=" + url
 	if getcomments:
 		ytdl_opts['getcomments'] = True
 	if maxcomments:
 		ytdl_opts['extractor_args'] = {'youtube': {'max_comments': [maxcomments, "all", "all", "all"]}}
 	with yt_dlp.YoutubeDL(ytdl_opts) as ytdl:
 		result = ytdl.extract_info(url, download=False)
-	return result
+	return result
+
+def related(url: str):
+	# WARNING! HIGHLY EXPERIMENTAL, DUE TO BREAK ANYTIME
+	if len(url) == 11:
+		params = {'v': url}
+	else:
+		videoId = url.find("https://www.youtube.com/watch?v=") # len() = 32
+		if videoId == -1:
+			raise BaseException
+		videoId = url[32:44]
+		params = {'v': videoId}
+
+	user_agent = 'Mozilla/5.0 (Windows NT 10.0; rv:130.0) Gecko/20100101 Firefox/130.0'
+	if ythdd_globals.config['extractor']['user-agent']:
+		user_agent = ythdd_globals.config['extractor']['user-agent']
+
+	headers = {
+		'User-Agent': user_agent,
+		'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/png,image/svg+xml,*/*;q=0.8',
+		'Accept-Language': 'en-US,en;q=0.5',
+		'DNT': '1',
+		'Sec-GPC': '1',
+		'Connection': 'keep-alive',
+		'Upgrade-Insecure-Requests': '1',
+		'Sec-Fetch-Dest': 'document',
+		'Sec-Fetch-Mode': 'navigate',
+		'Sec-Fetch-Site': 'none',
+		'Sec-Fetch-User': '?1',
+		'Priority': 'u=0, i',
+		'Pragma': 'no-cache',
+		'Cache-Control': 'no-cache',
+	}
+	response = requests.get(url, headers=headers, params=params)
+	extracted_string = str(response.content.decode('utf8', 'unicode_escape'))
+	start = extracted_string.find('{"responseContext":{"serviceTrackingParams":')
+	start2 = extracted_string.find('{"responseContext":{"serviceTrackingParams":', start + 1)
+	end = extracted_string.find(';</script>', start2)
+	extracted_json = json.loads(extracted_string[start2:end])
+
+	return extracted_json["contents"]['twoColumnWatchNextResults']["secondaryResults"]