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

Run JS behaviors only on HTML

Browse Source 
Make method `Browser.page_is_html` which return boolean. The method uses
`document.contentType` to get current page's conent-type.

If page is not HTML, skip JS behavior.

Capture performance increases greatly for non html pages.
This commit is contained in:
Vangelis Banos 2019-10-16 21:35:51 +00:00
parent ba85917f70
commit d36431b878
1 changed files with 17 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
brozzler/browser.py
View File

@ -655,7 +655,24 @@ class Browser:
message = self.websock_thread.pop_result(msg_id)
return message['result']['result']['value']
def page_is_html(self, timeout=10):
'''
Check if current page is HTML.
'''
self.websock_thread.expect_result(self._command_id.peek())
msg_id = self.send_to_chrome(
method='Runtime.evaluate', suppress_logging=True,
params={'expression': 'document.contentType'})
self._wait_for(lambda: self.websock_thread.received_result(msg_id),
timeout=timeout)
message = self.websock_thread.pop_result(msg_id)
return 'html' in message['result']['result']['value']
def run_behavior(self, behavior_script, timeout=900):
# Skip running JS behavior if page is not HTML.
if not self.page_is_html():
return
self.send_to_chrome(
method='Runtime.evaluate', suppress_logging=True,
params={'expression': behavior_script})