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

Log oulinks for all users of Browser.

Browse Source
This commit is contained in:
Neil Minton 2017-06-30 15:05:15 -07:00
parent 895bfbf913
commit 58b95fa7bf
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
brozzler/browser.py
View File

@ -452,6 +452,7 @@ class Browser:
outlinks = []
else:
outlinks = self.extract_outlinks()
logging.info('outlinks: \n\t%s', '\n\t'.join(sorted(outlinks)))
if not skip_visit_hashtags:
self.visit_hashtags(page_url, hashtags, outlinks)
final_page_url = self.url()

4
brozzler/cli.py
View File

@ -189,9 +189,7 @@ def brozzle_page(argv=None):
browser = brozzler.Browser(chrome_exe=args.chrome_exe)
try:
browser.start(proxy=args.proxy)
outlinks = worker.brozzle_page(
browser, site, page, on_screenshot=on_screenshot)
logging.info('outlinks: \n\t%s', '\n\t'.join(sorted(outlinks)))
worker.brozzle_page(browser, site, page, on_screenshot=on_screenshot)
except brozzler.ReachedLimit as e:
logging.error('reached limit %s', e)
finally: