Spaces:
Paused
Paused
:zap: [Enhance] Add ignore classes for wikipedia.org
Browse files
networks/network_configs.py
CHANGED
|
@@ -1,17 +1,22 @@
|
|
| 1 |
IGNORE_TAGS = ["script", "style", "button"]
|
| 2 |
IGNORE_CLASSES = [
|
|
|
|
| 3 |
"sidebar",
|
| 4 |
"footer",
|
| 5 |
"related",
|
| 6 |
"comment",
|
| 7 |
"topbar",
|
| 8 |
-
# "menu",
|
| 9 |
"offcanvas",
|
| 10 |
"navbar",
|
| 11 |
# 163.com
|
| 12 |
"post_(top)|(side)|(recommends)|(crumb)|(statement)|(next)|(jubao)",
|
| 13 |
"ntes\-.*nav",
|
| 14 |
"nav\-bottom",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
]
|
| 16 |
|
| 17 |
IGNORE_HOSTS = [
|
|
|
|
| 1 |
IGNORE_TAGS = ["script", "style", "button"]
|
| 2 |
IGNORE_CLASSES = [
|
| 3 |
+
# common
|
| 4 |
"sidebar",
|
| 5 |
"footer",
|
| 6 |
"related",
|
| 7 |
"comment",
|
| 8 |
"topbar",
|
|
|
|
| 9 |
"offcanvas",
|
| 10 |
"navbar",
|
| 11 |
# 163.com
|
| 12 |
"post_(top)|(side)|(recommends)|(crumb)|(statement)|(next)|(jubao)",
|
| 13 |
"ntes\-.*nav",
|
| 14 |
"nav\-bottom",
|
| 15 |
+
# wikipedia.org
|
| 16 |
+
"language\-list",
|
| 17 |
+
"vector\-(header)|(column)|(sticky\-pinned)|(dropdown\-content)",
|
| 18 |
+
"navbox",
|
| 19 |
+
"catlinks",
|
| 20 |
]
|
| 21 |
|
| 22 |
IGNORE_HOSTS = [
|