mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-06-04 21:29:42 -04:00
use nlevitt fork of surt library for less stupid handling of mailto: urls, etc
This commit is contained in:
parent
ee50818dca
commit
231d019659
2 changed files with 2 additions and 2 deletions
|
@ -44,7 +44,7 @@ def is_permitted_by_robots(site, url):
|
|||
raise e.args[0]
|
||||
else:
|
||||
if tries_left > 0:
|
||||
logging.warn("caught exception %s fetching robots.txt (%s tries left) for %s", repr(e), tries_left, url)
|
||||
logging.warn("caught exception fetching robots.txt (%s tries left) for %s: %s", tries_left, url, repr(e))
|
||||
tries_left -= 1
|
||||
else:
|
||||
logging.error("caught exception fetching robots.txt (0 tries left) for %s: %s", url, repr(e), exc_info=True)
|
||||
|
|
|
@ -1,6 +1,6 @@
|
|||
argparse
|
||||
PyYAML
|
||||
git+https://github.com/ikreymer/surt.git@py3
|
||||
git+https://github.com/nlevitt/surt.git@py3
|
||||
# youtube_dl
|
||||
git+https://github.com/nlevitt/youtube-dl.git@brozzler
|
||||
git+https://github.com/seomoz/reppy.git
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue