nichkara/ninachloe
1
0
Fork 0
mirror of https://github.com/nichkara/InfinitumBotty.git synced 2026-06-11 06:36:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

add parsing for music.youtube, youtube/shorts, security: Do not parse url with ips/ports

Browse Source
This commit is contained in:
Context 77
2024-08-01 12:48:03 +02:00
parent 6afa0baf04
commit b8db5ed462
1 changed files with 37 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
FaustBot/Modules/TitleObserver.py
View File

@@ -23,14 +23,7 @@ class TitleObserver(PrivMsgObserverPrototype):
url = url.group() url = url.group()
print(url) print(url)
try: try:
headers = { title = self.getTitle(url)
"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)
resource = urllib.request.urlopen(req)
title = self.getTitle(resource)
print(title) print(title)
title = title[:350] title = title[:350]
connection.send_back(title, data) connection.send_back(title, data)
@@ -38,28 +31,52 @@ class TitleObserver(PrivMsgObserverPrototype):
print(exc) print(exc)
pass pass
def getTitle(self, resource): def getTitle(self, url):
encoding = resource.headers.get_content_charset() headers = {
url = resource.geturl() "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"
# 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): if re.search("https?://\\[[^/]*", url):
raise (Exception("Refusing to parse bare IPv6 Addresses"))
if re.search("https?://[^/:]*:[^/:]*", url):
raise (Exception("Refusing to parse URLs with Ports"))
if re.search("https?://[0-9]+.[0-9]+.[0-9]+.[^/]*", url):
raise (Exception("Refusing to parse bare IPv4 Addresses"))
if re.search("https?://music.youtube.com/", url):
url = url.replace("music.youtube.com/", "www.youtube.com/", 1)
if re.search("https?://[^/]*youtube.com/shorts/", url):
title_re = re.compile('''"reelPlayerHeaderRenderer":{"reelTitleText":{"runs":\[{"text":"([^"]*)"''')
headers["User-Agent"] = "curl/7.81.0"
elif re.search("https?://[^/]*youtube.com/", url):
title_re = re.compile( title_re = re.compile(
'''"results":{"contents":\[{"videoPrimaryInfoRenderer":{"title":{"runs":\[{"text":"([^"]*)"''' '''"results":{"contents":\[{"videoPrimaryInfoRenderer":{"title":{"runs":\[{"text":"([^"]*)"'''
) )
else: else:
title_re = re.compile("<title>(.+?)</title>") title_re = re.compile("<title>(.+?)</title>")
req = urllib.request.Request(url, None, headers)
# Keep the urlopen scope as short as possible (connection leaks)
with urllib.request.urlopen(req, timeout=10) as response:
encoding = response.headers.get_content_charset()
content_raw = response.read()
# 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 = content_raw.decode(encoding, errors="replace")
title_matches = title_re.search(content) title_matches = title_re.search(content)
if title_matches: if title_matches:
title = title_matches.group(1) title = title_matches.group(1)
else: else:
return "Could not Parse Title" #with open("content.html", "w") as file:
# file.write(content)
raise Exception("Could not Parse Title for {}".format(url))
title = html.unescape(title) title = html.unescape(title)
title = title.replace("\n", " ").replace("\r", "") title = title.replace("\n", " ").replace("\r", "")
@@ -67,5 +84,5 @@ class TitleObserver(PrivMsgObserverPrototype):
title = title.replace("&gt;", ">") title = title.replace("&gt;", ">")
title = title.replace("&amp;", "&") title = title.replace("&amp;", "&")
if title == "": if title == "":
title = "Empty Title" raise Exception("Empty Title for {}".format(url))
return title return title