Git-Mirrors/brozzler
1
0
Fork 0
mirror of https://github.com/internetarchive/brozzler.git synced 2025-04-21 16:16:28 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge branch 'behavior_timeout' into qa

Browse Source
This commit is contained in:
Barbara Miller 2017-08-31 10:31:55 -07:00
commit 17d410f000
3 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.rst
View File

@ -26,7 +26,8 @@ Requirements
Worth noting is that the browser requires a graphical environment to run. You
already have this on your laptop, but on a server it will probably require
deploying some additional infrastructure (typically X11). The vagrant
deploying some additional infrastructure (typically X11; note that Xvfb does
not support screenshots; Xvnc4, from package vnc4server, does). The vagrant
configuration in the brozzler repository (still a work in progress) has an
example setup.
@ -181,7 +182,7 @@ Headless Chrome (experimental)
`Headless Chromium <https://chromium.googlesource.com/chromium/src/+/master/headless/README.md>`_
is now available in stable Chrome releases for 64-bit Linux and may be
used to run the browser without a visibe window or X11 at all.
used to run the browser without a visible window or X11 at all.
To try this out, create a wrapper script like ~/bin/chrome-headless.sh:

4
brozzler/browser.py
View File

@ -381,7 +381,7 @@ class Browser:
on_request=None, on_response=None, on_screenshot=None,
username=None, password=None, hashtags=None,
skip_extract_outlinks=False, skip_visit_hashtags=False,
page_timeout=300):
page_timeout=300, behavior_timeout=900):
'''
Browses page in browser.
@ -448,7 +448,7 @@ class Browser:
on_screenshot(jpeg_bytes)
behavior_script = brozzler.behavior_script(
page_url, behavior_parameters)
self.run_behavior(behavior_script, timeout=900)
self.run_behavior(behavior_script, timeout=behavior_timeout)
if skip_extract_outlinks:
outlinks = []
else:

6
brozzler/worker.py
View File

@ -105,7 +105,7 @@ class BrozzlerWorker:
self, frontier, service_registry=None, max_browsers=1,
chrome_exe="chromium-browser", warcprox_auto=False, proxy=None,
skip_extract_outlinks=False, skip_visit_hashtags=False,
page_timeout=300):
page_timeout=300, behavior_timeout=900):
self._frontier = frontier
self._service_registry = service_registry
self._max_browsers = max_browsers
@ -117,6 +117,7 @@ class BrozzlerWorker:
self._skip_extract_outlinks = skip_extract_outlinks
self._skip_visit_hashtags = skip_visit_hashtags
self._page_timeout = page_timeout
self._behavior_timeout = behavior_timeout
self._browser_pool = brozzler.browser.BrowserPool(
max_browsers, chrome_exe=chrome_exe, ignore_cert_errors=True)
@ -419,7 +420,8 @@ class BrozzlerWorker:
on_request=on_request, hashtags=page.hashtags,
skip_extract_outlinks=self._skip_extract_outlinks,
skip_visit_hashtags=self._skip_visit_hashtags,
page_timeout=self._page_timeout)
page_timeout=self._page_timeout,
behavior_timeout=self._behavior_timeout)
if final_page_url != page.url:
page.note_redirect(final_page_url)
return outlinks