Archiveteam/grab-site
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

global igset: Ignore a loop on archive.org

Browse Source
This commit is contained in:
Ivan Kozik 2015-12-16 13:11:16 +00:00
parent 38f733f9d2
commit 4ea80eec80
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
libgrabsite/__init__.py
View File

@ -1 +1 @@
__version__ = '0.9.7' __version__ = '0.9.8'

1
libgrabsite/ignore_sets/global
View File

@ -220,6 +220,7 @@
^https?://static\.licdn\.com/sc/p/.+/f// ^https?://static\.licdn\.com/sc/p/.+/f//
^https?://tm\.uol\.com\.br/h/.+/h/ ^https?://tm\.uol\.com\.br/h/.+/h/
^https?://((s-)?static\.ak\.fbcdn\.net|(connect\.|www\.)?facebook\.com)/connect\.php/js/.*rsrc\.php ^https?://((s-)?static\.ak\.fbcdn\.net|(connect\.|www\.)?facebook\.com)/connect\.php/js/.*rsrc\.php
^https?://web\.archive\.org/web/[^/]+/https?\:/[^/]+\.addthis\.com/.+/static/.+/static/
# This specifically catches only *invalid* flickr.com links extracted by wpull # This specifically catches only *invalid* flickr.com links extracted by wpull
^https?://www\.flickr\.com/(explore/|photos/[^/]+/(sets/\d+/(page\d+/)?)?)\d+_[a-f0-9]+(_[a-z])?\.jpg$ ^https?://www\.flickr\.com/(explore/|photos/[^/]+/(sets/\d+/(page\d+/)?)?)\d+_[a-f0-9]+(_[a-z])?\.jpg$