RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Remove restriction of marking ignore-beneath only for img unpaired tags

This commit is contained in:
molveyra 2010-07-28 11:16:42 -03:00
parent 4e2859e5d5
commit 8781ef3914
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrapy/contrib/ibl/extraction/pageparsing.py
View File

@ -117,7 +117,7 @@ class TemplatePageParser(InstanceLearningParser):
def _handle_unpaired_tag(self, html_tag):
if self._read_bool_template_attribute(html_tag, "ignore") and html_tag.tag == "img":
self.ignored_regions.append((self.next_tag_index, self.next_tag_index + 1))
elif self._read_bool_template_attribute(html_tag, "ignore-beneath") and html_tag.tag == "img":
elif self._read_bool_template_attribute(html_tag, "ignore-beneath"):
self.ignored_regions.append((self.next_tag_index, None))
jannotation = self._read_template_annotation(html_tag)
if jannotation: