Skip to content

refactor text extractor and ignore xml declarations #36

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

Merged
merged 1 commit into from
Apr 10, 2013
Merged

refactor text extractor and ignore xml declarations #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 4 additions & 6 deletions scrapely/extractors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,6 @@
'b' : 'strong',
'i' : 'em',
}

# tags whoose content will be completely removed (recursively)
# (overrides tags_to_keep and tags_to_replace)
_TAGS_TO_PURGE = ('script', 'img', 'input')
Expand Down Expand Up @@ -91,12 +90,11 @@ def text(region):
HTML entities are converted to text
>>> t(u"only £42")
u'only \\xa342'

>>> t(u"<p>The text</p><?xml:namespace blabla/><p>is here</p>")
u'The text is here'
"""
chunks = _process_markup(region,
lambda text: remove_entities(text, encoding=region.htmlpage.encoding),
lambda tag: u' '
)
text = u''.join(chunks)
text = remove_entities(region.text_content, encoding=region.htmlpage.encoding)
return _WS.sub(u' ', text).strip()

def safehtml(region, allowed_tags=_TAGS_TO_KEEP, replace_tags=_TAGS_TO_REPLACE,
Expand Down
2 changes: 1 addition & 1 deletion scrapely/htmlpage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -200,7 +200,7 @@ def __repr__(self):
_TAG = "<(\/?)(\w+(?::\w+)?)((?:\s*" + _ATTR + ")+\s*|\s*)(\/?)>?"
_DOCTYPE = r"<!DOCTYPE.*?>"
_SCRIPT = "(<script.*?>)(.*?)(</script.*?>)"
_COMMENT = "(<!--.*?-->)"
_COMMENT = "(<!--.*?-->|<\?.+?>)"

_ATTR_REGEXP = re.compile(_ATTR, re.I | re.DOTALL)
_HTML_REGEXP = re.compile("%s|%s|%s" % (_COMMENT, _SCRIPT, _TAG), re.I | re.DOTALL)
Expand Down
7 changes: 7 additions & 0 deletions scrapely/tests/test_htmlpage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,3 +138,10 @@ def test_malformed2(self):
def test_empty_subregion(self):
htmlpage = HtmlPage(body=u"")
self.assertEqual(htmlpage.subregion(), u"")

def test_ignore_xml_declaration(self):
"""Ignore xml declarations inside html"""
parsed = list(parse_html(u"<p>The text</p><?xml:namespace blabla/><p>is here</p>"))
self.assertFalse(parsed[3].is_text_content)