mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-02-24 00:29:53 -05:00
recognize ConnectionError (of which ConnectionResetError is a subclass) in _warcprox_write_record as a proxy error
This commit is contained in:
parent
054625b8a5
commit
60c5a7c1c4
@ -208,7 +208,11 @@ class BrozzlerWorker:
|
|||||||
'WARCPROX_WRITE_RECORD request (expected 204)',
|
'WARCPROX_WRITE_RECORD request (expected 204)',
|
||||||
e.getcode(), e.info())
|
e.getcode(), e.info())
|
||||||
except urllib.error.URLError as e:
|
except urllib.error.URLError as e:
|
||||||
raise brozzler.ProxyError('_warcprox_write_record: %s', e)
|
raise brozzler.ProxyError(
|
||||||
|
'proxy error on WARCPROX_WRITE_RECORD %s' % url) from e
|
||||||
|
except ConnectionError as e:
|
||||||
|
raise brozzler.ProxyError(
|
||||||
|
'proxy error on WARCPROX_WRITE_RECORD %s' % url) from e
|
||||||
|
|
||||||
def _remember_videos(self, page, ydl_spy):
|
def _remember_videos(self, page, ydl_spy):
|
||||||
if not 'videos' in page:
|
if not 'videos' in page:
|
||||||
@ -266,7 +270,8 @@ class BrozzlerWorker:
|
|||||||
and self._proxy_for(site)):
|
and self._proxy_for(site)):
|
||||||
# connection problem when using a proxy == proxy error (XXX?)
|
# connection problem when using a proxy == proxy error (XXX?)
|
||||||
raise brozzler.ProxyError(
|
raise brozzler.ProxyError(
|
||||||
'youtube-dl hit apparent proxy error', e)
|
'youtube-dl hit apparent proxy error from '
|
||||||
|
'%s' % page.url) from e
|
||||||
else:
|
else:
|
||||||
raise
|
raise
|
||||||
|
|
||||||
@ -399,7 +404,8 @@ class BrozzlerWorker:
|
|||||||
page.url, proxies=proxies, headers=site.extra_headers(),
|
page.url, proxies=proxies, headers=site.extra_headers(),
|
||||||
verify=False)
|
verify=False)
|
||||||
except requests.exceptions.ProxyError as e:
|
except requests.exceptions.ProxyError as e:
|
||||||
raise brozzler.ProxyError(e)
|
raise brozzler.ProxyError(
|
||||||
|
'proxy error fetching %s' % page.url) from e
|
||||||
|
|
||||||
def _needs_browsing(self, page, brozzler_spy):
|
def _needs_browsing(self, page, brozzler_spy):
|
||||||
final_bounces = brozzler_spy.final_bounces(page.url)
|
final_bounces = brozzler_spy.final_bounces(page.url)
|
||||||
|
2
setup.py
2
setup.py
@ -32,7 +32,7 @@ def find_package_data(package):
|
|||||||
|
|
||||||
setuptools.setup(
|
setuptools.setup(
|
||||||
name='brozzler',
|
name='brozzler',
|
||||||
version='1.1b11.dev244',
|
version='1.1b11.dev245',
|
||||||
description='Distributed web crawling with browsers',
|
description='Distributed web crawling with browsers',
|
||||||
url='https://github.com/internetarchive/brozzler',
|
url='https://github.com/internetarchive/brozzler',
|
||||||
author='Noah Levitt',
|
author='Noah Levitt',
|
||||||
|
Loading…
x
Reference in New Issue
Block a user