Skip to content

Make the html cleaning for microdata faster #123

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.

Sign up for GitHub

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

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Make the html cleaning for microdata faster #123

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
754d697
Move tree cleaning to extract function
jakubwasikowski Jul 31, 2019
f70f8a7
Do not clear link and meta tags
jakubwasikowski Jul 31, 2019
7422c01
Get rid of _xp_clean_text
jakubwasikowski Jul 31, 2019
d8c03b7
Change place where cleaning document is applied
jakubwasikowski Aug 2, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 5 additions & 6 deletions extruct/w3cmicrodata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,8 +31,8 @@
javascript=False, # onclick attributes are fine
comments=True,
style=True,
links=True,
meta=True,
links=False, # e.g. availability is included in <link> tags
meta=False, # some sites use <meta> tags in body to provide property
page_structure=False, # <title> may be nice to have
processing_instructions=True,
embedded=False, # keep embedded content
Expand All @@ -49,7 +49,6 @@ class LxmlMicrodataExtractor(object):
_xp_prop = lxml.etree.XPath("""set:difference(.//*[@itemprop],
.//*[@itemscope]//*[@itemprop])""",
namespaces = {"set": "http://exslt.org/sets"})
_xp_clean_text = lxml.etree.XPath('descendant-or-self::*[not(self::script or self::style)]/text()')
# ancestor and preceding axes contain all elements before the context node
# so counting them gives the "document order" of the context node
_xp_item_docid = lxml.etree.XPath("""count(preceding::*[@itemscope])
Expand All @@ -70,11 +69,12 @@ def extract(self, htmlstring, base_url=None, encoding="UTF-8"):
return self.extract_items(tree, base_url)

def extract_items(self, document, base_url):
cleaned_document = cleaner.clean_html(document)
items_seen = set()
return [
item for item in (
self._extract_item(it, items_seen=items_seen, base_url=base_url)
for it in self._xp_item(document))
for it in self._xp_item(cleaned_document))
if item]

def _extract_item(self, node, items_seen, base_url):
Expand Down Expand Up @@ -203,8 +203,7 @@ def _extract_property_value(self, node, items_seen, base_url, force=False):
return self._extract_textContent(node)

def _extract_textContent(self, node):
clean_node = cleaner.clean_html(node)
return html_text.etree_to_text(clean_node)
return html_text.etree_to_text(node)


MicrodataExtractor = LxmlMicrodataExtractor