mirror/archivebox
1
0
Fork 0
mirror of https://github.com/pirate/ArchiveBox.git synced 2025-08-21 13:52:30 +02:00
Code Issues Releases Wiki Activity

add timeout to title fetching

Browse Source
This commit is contained in:
Nick Sweeting
2019-01-23 01:06:59 -05:00
parent e1be96e597
commit db0461ec4e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
archivebox/util.py
View File

@@ -234,7 +234,7 @@ def fetch_page_title(url, default=True):
default = url default = url
try: try:
html_content = urllib.request.urlopen(url).read().decode('utf-8') html_content = urllib.request.urlopen(url, timeout=10).read().decode('utf-8')
match = re.search('<title>(.*?)</title>', html_content) match = re.search('<title>(.*?)</title>', html_content)
return match.group(1) if match else default or None return match.group(1) if match else default or None