nichkara/ninachloe
1
0
Fork 0
mirror of https://github.com/nichkara/InfinitumBotty.git synced 2026-06-10 22:26:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

Adding youtube-special-case handling to extract title

Browse Source
This commit is contained in:
Context 77
2024-08-01 02:33:04 +02:00
parent 968a0e5029
commit 832cb74645
1 changed files with 34 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
FaustBot/Modules/TitleObserver.py
View File

@@ -18,12 +18,14 @@ class TitleObserver(PrivMsgObserverPrototype):
def update_on_priv_msg(self, data, connection: Connection):
regex = "(?P<url>https?://[^\s]+)"
url = re.search(regex, data['messageCaseSensitive'])
url = re.search(regex, data["messageCaseSensitive"])
if url is not None:
url = url.group()
print(url)
try:
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36'}
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36"
}
url = url
req = urllib.request.Request(url, None, headers)
@@ -37,18 +39,33 @@ class TitleObserver(PrivMsgObserverPrototype):
pass
def getTitle(self, resource):
encoding = resource.headers.get_content_charset()
# der erste Fall kann raus, wenn ein anderer Channel benutzt wird
if resource.geturl().find('rehakids.de') != -1:
encoding = 'windows-1252'
if not encoding:
encoding = 'utf-8'
content = resource.read().decode(encoding, errors='replace')
encoding = resource.headers.get_content_charset()
url = resource.geturl()
# der erste Fall kann raus, wenn ein anderer Channel benutzt wird
if url.find("rehakids.de") != -1:
encoding = "windows-1252"
if not encoding:
encoding = "utf-8"
content = resource.read().decode(encoding, errors="replace")
if re.search("http[s]+://[^/]*youtube.com/", url):
title_re = re.compile(
'''"results":{"contents":\[{"videoPrimaryInfoRenderer":{"title":{"runs":\[{"text":"([^"]*)"'''
)
else:
title_re = re.compile("<title>(.+?)</title>")
title = title_re.search(content).group(1)
title = html.unescape(title)
title = title.replace('\n', ' ').replace('\r', '')
title = title.replace("&lt;", "<")
title = title.replace("&gt;", ">")
title = title.replace("&amp;", "&")
return title
title_matches = title_re.search(content)
if title_matches:
title = title_matches.group(1)
else:
return "Could not Parse Title"
title = html.unescape(title)
title = title.replace("\n", " ").replace("\r", "")
title = title.replace("&lt;", "<")
title = title.replace("&gt;", ">")
title = title.replace("&amp;", "&")
if title == "":
title = "Empty Title"
return title