import urllib.parse as urlparse
import html
from bs4 import BeautifulSoup
+import http.client
import re, json, datetime
return "%.2f%siB" % (b, table[i])
def _do_request(url, try_aia=False):
- """Returns the HTTPResponse object, or a string on error"""
+ """Returns the HTTPResponse object, or a string on error. Empty string -> no response."""
request = urllib2.Request(url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36', 'Sec-Ch-Ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"', 'Sec-Ch-Ua-Mobile': '?0', 'Sec-Ch-Ua-Platform': '"Linux"', 'Sec-Fetch-Dest': 'document', 'Sec-Fetch-Mode': 'navigate', 'Sec-Fetch-Site': 'same-origin', 'Sec-Fetch-User': '?1', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', 'Accept-Language': 'en-US,en;q=0.9', 'Cache-Control': 'no-cache', 'Pragma': 'no-cache', 'Upgrade-Insecure-Requests': '1'})
if try_aia:
opener = urllib2.build_opener(urllib2.HTTPSHandler(context=aia_session.ssl_context_from_url(url)), SmartRedirectHandler())
# Send request and handle errors
try:
response = opener.open(request, timeout=2)
+ except http.client.InvalidURL as e: # why does a method under urllib.request raise an exception under http.client???
+ return ''
except urllib2.HTTPError as e:
return 'Request error: %s %s' % (e.code, e.reason)
except urllib2.URLError as e:
except Exception as e:
return 'Unknown error: %s %r' % (type(e).__name__, e.args)
- return response
+ return response, try_aia
def goturl(url):
if regex.match(url):
return None
- response = _do_request(url)
+ response, used_aia = _do_request(url)
if isinstance(response, stringbase):
return response
else:
output.append("[no length] ")
+ if used_aia:
+ output.append("[AIA] ")
+
# Try to add title if HTML
if c_type == 'text/html':
try: