Skip to content

Issue #1 #84

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

Issue #1 #84

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
dc17593
Issue #1
nabilm Dec 15, 2015
c6fa64c
Issue #2
nabilm Dec 16, 2015
889c721
Issue #2
nabilm Dec 16, 2015
59298a9
Issue #2
nabilm Dec 20, 2015
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
19 changes: 12 additions & 7 deletions scrapely/extraction/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,7 @@ class InstanceBasedLearningExtractor(object):
RepeatedDataExtractor,
RecordExtractor,
]
_ext_items_max_number = 2

def __init__(self, td_pairs, trace=False, apply_extrarequired=True):
"""Initialise this extractor
Expand Down Expand Up @@ -77,11 +78,11 @@ def __init__(self, td_pairs, trace=False, apply_extrarequired=True):
modified_parsed_tdpairs.append((parsed, (t, descriptor)))
# templates with more attributes are considered first
sorted_tdpairs = sorted(modified_parsed_tdpairs,
key=lambda x: _annotation_count(x[0]), reverse=True)
key=lambda x: _annotation_count(x[0]), reverse=True)
self.extraction_trees = [
self.build_extraction_tree(p, td[1], trace)
for p, td in sorted_tdpairs
]
]
self.validated = dict(
(td[0].page_id, td[1].validated if td[1] else self._filter_not_none)
for _, td in sorted_tdpairs
Expand All @@ -108,23 +109,27 @@ def extract(self, html, pref_template_id=None):
If pref_template_url is specified, the template with that url will be
used first.
"""
max_extracted_value = {}
correctly_extracted_template = ''
extraction_page = parse_extraction_page(self.token_dict, html)
if pref_template_id is not None:
extraction_trees = sorted(self.extraction_trees,
key=lambda x: x.template.id != pref_template_id)
key=lambda x: x.template.id != pref_template_id)
else:
extraction_trees = self.extraction_trees

for extraction_tree in extraction_trees:
extracted = extraction_tree.extract(extraction_page)
correctly_extracted = self.validated[extraction_tree.template.id](extracted)
if len(correctly_extracted) > 0:
return correctly_extracted, extraction_tree.template
return None, None
if len(correctly_extracted[0]) > len(max_extracted_value):
max_extracted_value = correctly_extracted[0]
correctly_extracted_template = extraction_tree.template

return [max_extracted_value], correctly_extracted_template

def __str__(self):
return "InstanceBasedLearningExtractor[\n%s\n]" % \
(',\n'.join(map(str, self.extraction_trees)))
(',\n'.join(map(str, self.extraction_trees)))

@staticmethod
def _filter_not_none(items):
Expand Down