def _extractor(txt, htmlpage=None):
if txt is None:
return
page = getattr(htmlpage, 'htmlpage', htmlpage)
if not hasattr(txt, 'text_content'):
txt = HtmlPageRegion(page, txt)
data = extractor.extract(txt)
if data:
return extractor.adapt(data, page)
def _extract_attribute(self, extraction_page, start_index, end_index, ignored_regions=None, **kwargs):
data = []
for (f, ta, ea) in self.tag_data:
tag_value = extraction_page.htmlpage_tag(start_index).attributes.get(ta)
if tag_value:
region = HtmlPageRegion(extraction_page.htmlpage, tag_value)
extracted = f(region)
if extracted is not None:
data.append((ea, extracted))
return data
def __new__(cls, htmlpage, regions):
text = u''.join(regions)
return HtmlPageRegion.__new__(cls, htmlpage, text)
def extract(self, region):
"""Extract a region from the region passed"""
text = self.extract_text(region)
return HtmlPageRegion(region.htmlpage, text) if text else None
def _exec(x):
ret = g(x)
if ret is not None:
ret = HtmlPageRegion(ret.htmlpage, remove_tags(ret.text_content))
return f(ret)
return None
def __new__(cls, htmlpage, regions):
text = u''.join(regions)
return HtmlPageRegion.__new__(cls, htmlpage, text)