Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-04-20 23:56:34 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

handle http auth (#138)

Browse Source 
abort brozzling on insterstial (auth dialog)

because we have no other recourse at this point. waiting on Network.requestIntercepted auth challenge support. (didn't work in our latest testing)
https://chromedevtools.github.io/devtools-protocol/tot/Network#type-AuthChallengeResponse
This commit is contained in:
Barbara Miller 2018-11-16 15:10:30 -08:00 committed by Barbara Miller
parent 9db7744f2c
commit bc6a2f4b95
2 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
brozzler/worker.py
View File

@ -212,11 +212,10 @@ class BrozzlerWorker:
self.logger.info('needs browsing: %s', page)
try:
browser_outlinks = self._browse_page(
browser, site, page, on_screenshot, on_request)
browser, site, page, on_screenshot, on_request)
outlinks.update(browser_outlinks)
except brozzler.PageInterstitialShown:
self.logger.info('page interstitial shown (http auth): %s', page)
return outlinks
else:
if not self._already_fetched(page, ydl_fetches):
self.logger.info('needs fetch: %s', page)

12
tests/test_brozzling.py
View File

@ -62,6 +62,13 @@ def httpd(request):
self.send_header('Content-Length', len(payload))
self.end_headers()
self.wfile.write(payload)
elif self.path == '/401':
self.send_response(401)
self.send_header('WWW-Authenticate', 'Basic realm=\"Test\"')
self.send_header('Content-type', 'text/html')
self.end_headers()
self.wfile.write(self.headers.getheader('Authorization'))
self.wfile.write('not authenticated')
else:
super().do_GET()
@ -111,11 +118,12 @@ def test_aw_snap_hes_dead_jim():
with pytest.raises(brozzler.BrowsingException):
browser.browse_page('chrome://crash')
def test_page_interstitial_exception():
def test_page_interstitial_exception(httpd):
chrome_exe = brozzler.suggest_default_chrome_exe()
url = 'http://localhost:%s/401' % httpd.server_port
with brozzler.Browser(chrome_exe=chrome_exe) as browser:
with pytest.raises(brozzler.PageInterstitialShown):
browser.browse_page('https://monitor.archive.org/cgi-bin/nagios3/status.cgi?hostgroup=38.wbgrp')
browser.browse_page(url)
def test_on_response(httpd):
response_urls = []