jkhsjdhjs/nxy
1
0
Fork 0
Code Issues 4 Pull Requests Projects Releases Wiki Activity

urlinfo: check content-type before downloading + handle timeouts

Browse Source 
improve codestyle and formatting
This commit is contained in:
jkhsjdhjs
2021-05-20 00:23:15 +00:00
parent e7b89e7fdb
commit 9c3cd2f816
1 changed files with 10 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
bot/urlinfo.py
View File

@@ -16,6 +16,7 @@ class URLInfo(Plugin):
"^https?:\/\/(?:(?:vid|img|thumb)\.)?pr0gramm\.com" "^https?:\/\/(?:(?:vid|img|thumb)\.)?pr0gramm\.com"
] ]
# set the size limit to 2 MB so we don't fully download too large resources
SIZE_LIMIT = 2 * 1024 ** 2 SIZE_LIMIT = 2 * 1024 ** 2
@irc3.event(r'(?i)^:\S+ PRIVMSG (?P<target>\S+) :.*(?P<url>https?:\/\/\S+\.\S+).*') @irc3.event(r'(?i)^:\S+ PRIVMSG (?P<target>\S+) :.*(?P<url>https?:\/\/\S+\.\S+).*')
@@ -23,26 +24,27 @@ class URLInfo(Plugin):
for regex in self.BLACKLIST: for regex in self.BLACKLIST:
if re.match(regex, url): if re.match(regex, url):
return return
bytes_io = io.BytesIO() bytes_io = io.BytesIO()
try: try:
with requests.get(url, timeout=10, stream=True) as r: with requests.get(url, timeout=10, stream=True) as r:
r.raise_for_status() r.raise_for_status()
mime_type = r.headers.get("content-type")
if mime_type is not None and mime_type.split(";")[0] != "text/html":
return
size = 0 size = 0
for chunk in r.iter_content(chunk_size=1024 ** 2): for chunk in r.iter_content(chunk_size=1024 ** 2):
size += len(chunk) size += len(chunk)
if size >= self.SIZE_LIMIT: if size >= self.SIZE_LIMIT:
return return
bytes_io.write(chunk) bytes_io.write(chunk)
except (requests.exceptions.ConnectionError, requests.exceptions.HTTPError) as e: except (requests.exceptions.ConnectionError, requests.exceptions.HTTPError, requests.exceptions.ReadTimeout):
return return
mime_type = r.headers.get("content-type")
if mime_type is not None:
if mime_type.split(";")[0] != "text/html":
return
bytes_io.seek(0) bytes_io.seek(0)
tree = etree.parse(bytes_io, etree.HTMLParser()).getroot() tree = etree.parse(bytes_io, etree.HTMLParser()).getroot()
title = tree.xpath("/html/head/title") title_elements = tree.xpath("/html/head/title")
if len(title) > 0: if len(title_elements) > 0:
self.bot.privmsg(target, '\x02[URLInfo]\x02 ' + title[0].text.strip()) self.bot.privmsg(target, '\x02[URLInfo]\x02 ' + title_elements[0].text.strip())