-
Notifications
You must be signed in to change notification settings - Fork 25
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix-bug: missing-pick-sentences #33
base: master
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -16,3 +16,4 @@ lib/ | |
local/ | ||
man/ | ||
share/ | ||
.idea/ | ||
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -21,7 +21,6 @@ | |
) | ||
from .utils import cached_property, shrink_text | ||
|
||
|
||
html_cleaner = Cleaner( | ||
scripts=True, javascript=True, comments=True, | ||
style=True, links=True, meta=False, add_nofollow=False, | ||
|
@@ -30,7 +29,6 @@ | |
annoying_tags=False, remove_tags=None, kill_tags=("noscript", "iframe"), | ||
remove_unknown_tags=False, safe_attrs_only=False) | ||
|
||
|
||
SCORABLE_TAGS = ("div", "p", "td", "pre", "article") | ||
ANNOTATION_TAGS = ( | ||
"a", "abbr", "acronym", "b", "big", "blink", "blockquote", "br", "cite", | ||
|
@@ -193,6 +191,7 @@ def clean_document(node): | |
logger.debug("Dropping <%s>, it's insignificant", n.tag) | ||
to_drop.append(n) | ||
|
||
""" modified by guojw | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Not sure why this is being commented out. prefer to have the reasoning behind the commenting out rather than just a name. |
||
# drop block element without content and children | ||
if n.tag in ("div", "p"): | ||
text_content = shrink_text(n.text_content()) | ||
|
@@ -204,6 +203,7 @@ def clean_document(node): | |
# finally try out the conditional cleaning of the target node | ||
if clean_conditionally(n): | ||
to_drop.append(n) | ||
""" | ||
|
||
drop_nodes_with_parents(to_drop) | ||
|
||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -13,7 +13,6 @@ | |
from ._compat import to_bytes | ||
from .utils import normalize_whitespace | ||
|
||
|
||
# A series of sets of attributes we check to help in determining if a node is | ||
# a potential candidate or not. | ||
CLS_UNLIKELY = re.compile( | ||
|
@@ -140,7 +139,9 @@ def is_unlikely_node(node): | |
|
||
def score_candidates(nodes): | ||
"""Given a list of potential nodes, find some initial scores to start""" | ||
MIN_HIT_LENTH = 25 | ||
# guojw | ||
# MIN_HIT_LENTH = 25 | ||
MIN_HIT_LENTH = 1 | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. What's the reasoning behind changing this to 1? |
||
candidates = {} | ||
|
||
for node in nodes: | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
please remove this directory.